gokayfem-ComfyUI-fal-API/data/fal_registry.json

{"model_count":1391,"models":[{"category":"image-to-video","description":"Alibaba's #1-ranked Happy Horse 1.0 — generate 1080p video with synchronized native audio and multilingual lip-sync from text prompts or images.","endpoint_id":"alibaba/happy-horse/image-to-video","family":"Happy Horse","inputs":[{"default":null,"description":"URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Dimensions must be at least 300px. Aspect ratio must be between 1:2.5 and 2.5:1. Max 10 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional text prompt guiding the animation. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (3-15).","enum":[3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.14/second.  For 1080p video you will be charged $0.28/second.","published_at":"2026-04-27T10:31:27.614000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a975556/jB--KHf1a0VK5l_IML8nX_9a0d18b9f1cf4292a33907002e02a1ba.jpg","title":"Happy Horse"},{"category":"image-to-video","description":"Generate 1080p video with synchronized native audio from a text prompt and references. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","endpoint_id":"alibaba/happy-horse/reference-to-video","family":"Happy Horse","inputs":[{"default":null,"description":"Text prompt describing the desired video. Reference subjects from your images using ``character1``, ``character2``, ... up to ``character9`` (the order matches the order of ``image_urls``). Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for subject consistency (1-9 images). Formats: JPEG, JPG, PNG, WEBP. Shortest side must be at least 400 px (720P or higher recommended). Max 10 MB each.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (3-15).","enum":[3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.14/second.  For 1080p video you will be charged $0.28/second.","published_at":"2026-04-27T11:45:32+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97e906/Sv4Xl8Vak5gLNHrBjEMMO_03a850ef23034759adf81fb7121bf35a.jpg","title":"Happy Horse"},{"category":"text-to-video","description":"Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","endpoint_id":"alibaba/happy-horse/text-to-video","family":"Happy Horse","inputs":[{"default":null,"description":"Text prompt describing the desired video. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (3-15).","enum":[3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.14/second.  For 1080p video you will be charged $0.28/second.","published_at":"2026-04-27T10:31:20.339000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a975556/O6OH_JWwjWGMR4ujnmQPC_b3d0863dc24748e28b1e44880d861185.jpg","title":"Happy Horse"},{"category":"image-to-video","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This image-to-video endpoint animates a still image into 1080p video with synchronized native audio and multilingual lip-sync","endpoint_id":"alibaba/happy-horse/v1.1/image-to-video","family":"Happy Horse","inputs":[{"default":null,"description":"URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Dimensions must be at least 300px. Aspect ratio must be between 1:2.5 and 2.5:1. Max 20 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional text prompt guiding the animation. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (3-15).","enum":[3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.14/second.  For 1080p video you will be charged $0.18/second.","published_at":"2026-06-22T06:15:01.070000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f396f/HeOG8Txxcrw0irt78kQYt_108f8bf0e80940b49fe4a66cb732e3af.jpg","title":"Happy Horse 1.1 Image to Video"},{"category":"image-to-video","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This reference-to-video endpoint turns up to 9 reference images into 1080p video with synchronized native audio and multilingual lip-sync for consistent characters.","endpoint_id":"alibaba/happy-horse/v1.1/reference-to-video","family":"Happy Horse","inputs":[{"default":null,"description":"Text prompt describing the desired video. Reference subjects from your images using ``character1``, ``character2``, ... up to ``character9`` (the order matches the order of ``image_urls``). Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for subject consistency (1-9 images). Formats: JPEG, JPG, PNG, WEBP. Shortest side must be at least 400 px (720P or higher recommended). Max 20 MB each.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (3-15).","enum":[3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.14/second.  For 1080p video you will be charged $0.18/second.","published_at":"2026-06-22T06:14:49.115000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f3974/T-uOql0vSiumA6r6rZ8LA_ffa69b109cba4d33bae40af7e2bbc7d0.jpg","title":"Happy Horse 1.1 Reference to Video"},{"category":"text-to-video","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.","endpoint_id":"alibaba/happy-horse/v1.1/text-to-video","family":"Happy Horse","inputs":[{"default":null,"description":"Text prompt describing the desired video. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (3-15).","enum":[3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.14/second.  For 1080p video you will be charged $0.18/second.","published_at":"2026-06-22T06:14:39.813000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f395f/8hP5jLvVFWOWXKzo9BWRv_1b09aff553b045fb98313142db068d58.jpg","title":"Happy Horse 1.1 Text to Video"},{"category":"video-to-video","description":"HappyHorse video editing supports advanced video editing through natural language instructions. It allows for local or global editing of video elements using up to 5 reference images.","endpoint_id":"alibaba/happy-horse/video-edit","family":"Happy Horse","inputs":[{"default":null,"description":"URL of the source video to edit. Formats: MP4, MOV (H.264 recommended). Duration: 3-60 s. Longer side ≤ 2160 px, shorter side ≥ 320 px. Aspect ratio between 1:2.5 and 2.5:1. Frame rate > 8 fps. Max 100 MB. The output video preserves the source aspect ratio. Output duration matches the input video, capped at 15 s (longer inputs are truncated to the first 15 s).\n\nMax file size: 100.0MB, Min duration: 3s, Max duration: 60s, Timeout: 30.0s","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Text prompt describing the desired edit. Reference any supplied reference images using @Image1, @Image2, ... up to @Image5. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional reference images used to guide the edit (up to 5). Formats: JPEG, JPG, PNG, WEBP. Dimensions must be at least 300px. Aspect ratio between 1:2.5 and 2.5:1. Max 10 MB each.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":false,"type":"string"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Audio handling. 'auto': model decides whether to regenerate audio. 'origin': preserve the original audio from the input video.","enum":["auto","origin"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.28/second ($0.14  per input second and 0.14 per output second).  For 1080p video you will be charged $0.56/second.","published_at":"2026-04-27T11:46:52.471000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97eccf/ab4posrL6gDeMPjWA6iAY_0e23c382e58c4588a761c3dd7cc94e39.jpg","title":"Happy Horse Video Edit"},{"category":"audio-to-video","description":"High-quality avatar videos that feel real, generated from your audio","endpoint_id":"argil/avatars/audio-to-video","family":"","inputs":[{"default":null,"description":"Avatar","enum":["Mia outdoor (UGC)","Lara (Masterclass)","Ines (UGC)","Maria (Masterclass)","Emma (UGC)","Sienna (Masterclass)","Elena (UGC)","Jasmine (Masterclass)","Amara (Masterclass)","Ryan podcast (UGC)","Tyler (Masterclass)","Jayse (Masterclass)","Paul (Masterclass)","Matteo (UGC)","Daniel car (UGC)","Dario (Masterclass)","Viva (Masterclass)","Chen (Masterclass)","Alex (Masterclass)","Vanessa (UGC)","Laurent (UGC)","Noemie car (UGC)","Brandon (UGC)","Byron (Masterclass)","Calista (Masterclass)","Milo (Masterclass)","Fabien (Masterclass)","Rose (UGC)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"avatar","required":true,"type":"enum"},{"default":null,"description":"Audio Url","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":false,"description":"Enabling the remove background feature will result in a 50% increase in the price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_background","required":false,"type":"boolean"}],"lab":"Argil AI","output_kind":"video","output_props":["moderation_transcription","moderation_error","moderation_flagged","video"],"pricing":"","published_at":"2025-09-01T09:42:32.378000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a46/Gdzgjh37t0K2wz3FvC3Ln_kCn9Nl7J.png","title":"Avatars Audio to Video"},{"category":"text-to-video","description":"High-quality avatar videos that feel real, generated from your text","endpoint_id":"argil/avatars/text-to-video","family":"","inputs":[{"default":null,"description":"Avatar","enum":["Mia outdoor (UGC)","Lara (Masterclass)","Ines (UGC)","Maria (Masterclass)","Emma (UGC)","Sienna (Masterclass)","Elena (UGC)","Jasmine (Masterclass)","Amara (Masterclass)","Ryan podcast (UGC)","Tyler (Masterclass)","Jayse (Masterclass)","Paul (Masterclass)","Matteo (UGC)","Daniel car (UGC)","Dario (Masterclass)","Viva (Masterclass)","Chen (Masterclass)","Alex (Masterclass)","Vanessa (UGC)","Laurent (UGC)","Noemie car (UGC)","Brandon (UGC)","Byron (Masterclass)","Calista (Masterclass)","Milo (Masterclass)","Fabien (Masterclass)","Rose (UGC)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"avatar","required":true,"type":"enum"},{"default":null,"description":"Text","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Voice","enum":["Rachel","Clyde","Roger","Sarah","Laura","Thomas","Charlie","George","Callum","River","Harry","Liam","Alice","Matilda","Will","Jessica","Lilly","Bill","Oxley","Luna"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":false,"description":"Enabling the remove background feature will result in a 50% increase in the price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_background","required":false,"type":"boolean"}],"lab":"Argil AI","output_kind":"video","output_props":["moderation_transcription","moderation_error","moderation_flagged","video"],"pricing":"","published_at":"2025-09-01T09:50:49.180000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939c/qxEjoZW0MWzptt2r_-QcP_rpdWjdHD.png","title":"Avatars Text to Video"},{"category":"text-to-speech","description":"Generate professional-quality voiceovers in seconds with Async TTS Pro model text-based control over pauses, emphasis, and timing. Voice ids can be found at https://async.com/developer/voice-library","endpoint_id":"async/tts-pro/v1.0","family":"Async TTS Pro","inputs":[{"default":null,"description":"Text to convert to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transcript","required":true,"type":"string"},{"default":null,"description":"Voice to use for synthesis.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"json"},{"default":null,"description":"Audio output configuration.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"json"},{"default":null,"description":"Force synthesis in a specific language (ISO 639-1).","enum":["en","fr","es","de","it","pt"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"}],"lab":"Async","output_kind":"audio","output_props":["size_bytes","content_type","audio"],"pricing":"You are going to be billed by the length of the input text, at a flat rate of $0.01 per 1,000 characters.","published_at":"2026-06-18T12:47:57.503000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eca5b/cH54hF2DKMzegWqU-YP8X_c6ea3f36c9234aa9a137acf1b53cac01.jpg","title":"Async Text to Speech Pro V1.0"},{"category":"video-to-video","description":"A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.","endpoint_id":"bria/bria_video_eraser/erase/keypoints","family":"","inputs":[{"default":"mp4_h264","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, gif, mov_h264, mov_h265, mov_proresks, mkv_h264, mkv_h265, mkv_vp9, mkv_mpeg4.","enum":["mp4_h265","mp4_h264","webm_vp9","gif","mov_h264","mov_h265","mov_proresks","mkv_h264","mkv_h265","mkv_vp9","mkv_mpeg4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"auto trim the video, to working duration ( 5s )","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_trim","required":false,"type":"boolean"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input keypoints [x,y] to erase or keep from the video. Format like so: {'x':100, 'y':100, 'type':'positive/negative'}","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keypoints","required":true,"type":"string"},{"default":null,"description":"Input video to erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-12-17T16:54:16.002000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875807/hufu-WhXnSbIHPs2JUqFE_f40049919fd148f293c7e9aeb04c71ce.jpg","title":"Bria Video Eraser"},{"category":"video-to-video","description":"A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.","endpoint_id":"bria/bria_video_eraser/erase/mask","family":"Fibo","inputs":[{"default":"mp4_h264","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, gif, mov_h264, mov_h265, mov_proresks, mkv_h264, mkv_h265, mkv_vp9, mkv_mpeg4.","enum":["mp4_h265","mp4_h264","webm_vp9","gif","mov_h264","mov_h265","mov_proresks","mkv_h264","mkv_h265","mkv_vp9","mkv_mpeg4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"auto trim the video, to working duration ( 5s )","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_trim","required":false,"type":"boolean"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input video to erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Input video to mask erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-12-17T16:58:00.177000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875792/fiFX5LR2jtecUmE7yLyY8_340c579c0b1e408ab0d7920d3a2d3e32.jpg","title":"Bria Video Eraser Erase Mask"},{"category":"video-to-video","description":"A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency","endpoint_id":"bria/bria_video_eraser/erase/prompt","family":"Fibo","inputs":[{"default":"mp4_h264","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, gif, mov_h264, mov_h265, mov_proresks, mkv_h264, mkv_h265, mkv_vp9, mkv_mpeg4.","enum":["mp4_h265","mp4_h264","webm_vp9","gif","mov_h264","mov_h265","mov_proresks","mkv_h264","mkv_h265","mkv_vp9","mkv_mpeg4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"auto trim the video, to working duration ( 5s )","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_trim","required":false,"type":"boolean"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input prompt to detect object to erase","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Input video to erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-12-17T16:53:08.608000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875a33/-FGyIBxFrcWVZh-vsPpsC_f673e5d46d864e53becd4f71174b73ec.jpg","title":"Bria Video Eraser"},{"category":"image-to-image","description":"Seamlessly embed products into any scene with pixel-perfect control, automatic perspective, and natural lighting. Trained on licensed data - risk-free for advertising and eCommerce production.","endpoint_id":"bria/embed-product","family":"","inputs":[{"default":null,"description":"URL of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_source","required":false,"type":"string"},{"default":null,"description":"List of products to embed in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"products","required":false,"type":"json"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2026-02-25T09:19:44.473000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8fdfd4/H2lXEigbOn30Hkye83ook_6b580f1bdcf84ddfad9d091f1c504cdd.jpg","title":"Embed Product"},{"category":"image-to-image","description":"Bria Extract Object uses text prompts to isolate a selected object from an image and return it as an RGBA PNG with a transparent background. Ideal for product, ecommerce, advertising, and creative editing workflows. Bria's Extract Object API leads in product shot extraction, outperforming SAM 3.1 where it counts most for commercial use.","endpoint_id":"bria/extract-object","family":"","inputs":[{"default":"https://bria-datasets.s3.amazonaws.com/object-extraction/tools_construction_flatlay.jpg","description":"Source image as a public URL or raw base64-encoded image bytes (no data-URI prefix).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":"yellow hammer","description":"Natural-language description of the object to act on, e.g. 'the red car'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":false,"description":"Tighten the output canvas to the extracted object.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"autocrop","required":false,"type":"boolean"},{"default":false,"description":"When True, refine the cutout alpha with background removal (RMBG). When False (default), use the SAM segmentation mask as the cutout's alpha -- faster, with no salient-object matting (helpful when RMBG over-trims text, logos, or graphics).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_background","required":false,"type":"boolean"}],"lab":"Bria AI","output_kind":"image","output_props":["mask","image"],"pricing":"","published_at":"2026-06-29T16:24:20.718000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa0257a/9ELrmKOSBXCg7yslCX0W0.jpg","title":"Extract Object"},{"category":"text-to-image","description":"A preview to the next level of control of Text-to-Image models.","endpoint_id":"bria/fibo-bbq-preview/generate","family":"","inputs":[{"default":null,"description":"Prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"1:1","description":"Aspect ratio. Options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The structured prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_prompt","required":false,"type":"json"},{"default":null,"description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"steps_num","required":false,"type":"integer"},{"default":"","description":"Negative prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for text.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":3,"multiline":false,"name":"guidance_scale","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"images","output_props":["images","image","structured_prompt"],"pricing":"","published_at":"2026-03-02T16:33:06.785000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9092be/b2ug7xgblKYS8lrgaVxX2_f43d03bdbaf04ed793b0daee79e59a0d.jpg","title":"Fibo Bbq Preview"},{"category":"image-to-image","description":"Precisely insert new objects into images with structured spatial commands. Context-aware, high-quality editing with seamless blending. Trained on licensed data for risk-free commercial and brand-safe use.","endpoint_id":"bria/fibo-edit/add_object_by_text","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The full natural language command describing what to add and where.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instruction","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:11:21.771000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b236f/uXgjCOumhqoBoOk1AZ91X_ed4e0c8f0cfb46acb1bdb5e2b66a2a58.jpg","title":"Fibo Edit [Add Object by Text]"},{"category":"image-to-image","description":"image composition model. Combine and blend multiple image parts into complex compositions through natural language and sequential editing.","endpoint_id":"bria/fibo-edit/blend","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Instruct what elements you would like to blend in your image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instruction","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T10:52:43.996000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b230a/PtoYXkoWgYDMAFJqgvf9S_a050e81fc32d471893dd30080051ac7f.jpg","title":"Fibo Edit [Blend]"},{"category":"image-to-image","description":"Image colorization and color-grading model. Bring color to black-and-white photos or apply curated color treatments using simple style-based commands.","endpoint_id":"bria/fibo-edit/colorize","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Select the color palette or aesthetic for the output image","enum":["contemporary color","vivid color","black and white colors","sepia vintage"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color","required":true,"type":"enum"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T10:37:07.394000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b22ac/WkSYi-IgNLEv3uRGvcvAc_13b3ad6702bb451086ff8971fb1b302f.jpg","title":"Fibo Edit [Colorize]"},{"category":"image-to-image","description":"High-fidelity image editing model with state-of-the-art controllability. Combines JSON + Mask + Image for precise, fine-grained edits ideal for production and enterprise workflows. Trained on licensed data - safe for commercial use.","endpoint_id":"bria/fibo-edit/edit","family":"Fibo","inputs":[{"default":null,"description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Mask image (file or URL). Optional","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":null,"description":"Instruction for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instruction","required":false,"type":"string"},{"default":null,"description":"The structured prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_instruction","required":false,"type":"json"},{"default":null,"description":"The original vgl used to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_vgl","required":false,"type":"json"},{"default":null,"description":"The new vgl describing image after edit.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"new_vgl","required":false,"type":"json"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"Number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"steps_num","required":false,"type":"integer"},{"default":"","description":"Negative prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for text.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_scale","required":false,"type":"number"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:15:43.270000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2391/TzByxh26B-nDqx9gTZc0b_f58ca08fafa840de8434a2793b9f2d93.jpg","title":"Fibo Edit"},{"category":"text-to-json","description":"Structured Instructions Generation endpoint for Fibo Edit, Bria's newest editing model.","endpoint_id":"bria/fibo-edit/edit/structured_instruction","family":"Fibo","inputs":[{"default":null,"description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Reference image mask (file or URL). Optional.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":null,"description":"Instruction for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instruction","required":false,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2026-01-20T11:55:38.689000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2483/UZdf2yfDnuLfTMdQeTNzT_328d7729251342ac8fbc5c8721feb5c5.jpg","title":"Fibo Edit [Structured Instruction]"},{"category":"image-to-image","description":"Remove unwanted objects from images with a text prompt - fast, precise editing that seamlessly blends results. Built for production scale and trained on licensed data for safe commercial use.","endpoint_id":"bria/fibo-edit/erase_by_text","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The name of the object to remove.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"object_name","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:21:02.673000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b23af/c69cfQKwEcq8-r1yWTAQp_7190e3ad18a141e9b2c0b5f64311be31.jpg","title":"Fibo Edit [Erase by Text]"},{"category":"image-to-image","description":"Precise, controllable photo re-lighting with structured text inputs. Apply natural lighting styles, soften harsh shadows, and transform scene illumination - production-ready and trained exclusively on licensed data.","endpoint_id":"bria/fibo-edit/relight","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Where the light comes from.","enum":["front","side","bottom","top-down"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"light_direction","required":true,"type":"enum"},{"default":null,"description":"The quality/style/time of day.","enum":["midday","blue hour light","low-angle sunlight","sunrise light","spotlight on subject","overcast light","soft overcast daylight lighting","cloud-filtered lighting","fog-diffused lighting","moonlight lighting","starlight nighttime","soft bokeh lighting","harsh studio lighting"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"light_type","required":true,"type":"enum"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:40:09.156000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2423/RcBGC6N3eWjIoh-8jqvlr_6a7d71be051c495a8d0243021b8d8bbc.jpg","title":"Fibo Edit [Relight]"},{"category":"image-to-image","description":"Replace any object in an image using plain language with fine-grained, precise edits and strong prompt adherence. Trained on licensed data for risk-free commercial and brand-safe use.","endpoint_id":"bria/fibo-edit/replace_object_by_text","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The full natural language command describing what to replace.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instruction","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:53:35.783000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b245d/SpzMANTE7n5ZH288jVUam_35cae278412f4e99b5d165d94df62ddc.jpg","title":"Fibo Edit [Replace Object by Text]"},{"category":"image-to-image","description":"Transform the season or weather of an image - summer to winter, sunny to rainy - with realistic atmosphere and lighting. Trained exclusively on licensed data for risk-free commercial use.","endpoint_id":"bria/fibo-edit/reseason","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The desired season.","enum":["spring","summer","autumn","winter"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"season","required":true,"type":"enum"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:43:27.199000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2436/-APQ6KojmPWSlZmt9kQbv_0cb651b353f94746b86aed13325cd8aa.jpg","title":"Fibo Edit [Reseason]"},{"category":"image-to-image","description":"Photo restoration model that automatically denoises, deblurs, and enhances old or damaged photos - removes imperfections while preserving original character.","endpoint_id":"bria/fibo-edit/restore","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:45:44.048000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2441/xs0GaTAO7yUEIyxNUFA1t_358414183ebb4bc6b8e418880de46a03.jpg","title":"Fibo Edit [Restore]"},{"category":"image-to-image","description":"Production-grade style transfer that maps photos to distinct artistic styles using curated, brand-safe presets. Trained exclusively on licensed data for risk-free commercial use.","endpoint_id":"bria/fibo-edit/restyle","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Select the desired artistic style for the output image.","enum":["3D Render","Cubism","Oil Painting","Anime","Cartoon","Coloring Book","Retro Ad","Pop Art Halftone","Vector Art","Story Board","Art Nouveau","Cross Etching","Wood Cut"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":true,"type":"enum"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:37:52.937000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2411/GadXEuWQwSpq7dk3M0Civ_2a6ab9491a874596aa41f3cbdf72c774.jpg","title":"Fibo Edit [Restyle]"},{"category":"image-to-image","description":"Precisely rewrite text inside images while preserving typography, fonts, and layout. High-quality, brand-safe edits trained exclusively on licensed data for safe commercial use.","endpoint_id":"bria/fibo-edit/rewrite_text","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The new text string to appear in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"new_text","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:29:10.540000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b23df/jVMIrmCsypj236JttkUFB_2380773a816f493d8da21bd425688bd5.jpg","title":"Fibo Edit [Rewrite Text]"},{"category":"image-to-image","description":"Convert line drawings and sketches into photorealistic, fully colored images with preserved structure. Trained exclusively on licensed data for safe commercial and design use.","endpoint_id":"bria/fibo-edit/sketch_to_colored_image","family":"Fibo","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-01-20T11:47:45.178000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b2450/yOdy5RpOKQGnFgoxvGmc8_40b069cd42a04bf383c544a3702518c2.jpg","title":"Fibo Edit [Sketch to Image]"},{"category":"text-to-image","description":"Fast, low-latency text-to-image model with high-quality output and full JSON-structured controllability. Open-source, trained on licensed data, and optimized for production-scale generation.","endpoint_id":"bria/fibo-lite/generate","family":"Fibo","inputs":[{"default":null,"description":"The prompt to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The structured prompt to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_prompt","required":false,"type":"json"},{"default":null,"description":"Input image URL","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":7,"description":"Seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"1:1","description":"Aspect ratio. Options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"Negative prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of inference steps.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":4,"multiline":false,"name":"steps_num","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_prompt","images","image"],"pricing":"","published_at":"2025-12-16T14:07:05.087000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a868a4a/_QE3Hulvi5T-kP4GZwZxf_35c1ffe448b0481183bdb17a0618ef52.jpg","title":"Fibo Lite"},{"category":"text-to-json","description":"Convert plain text into Fibo-Lite's transparent JSON-structured prompts - Bria's unique controllability layer that no closed model offers. Built for agentic and enterprise workflows.","endpoint_id":"bria/fibo-lite/generate/structured_prompt","family":"Fibo","inputs":[{"default":null,"description":"The prompt to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The structured prompt to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_prompt","required":false,"type":"json"},{"default":null,"description":"Input image URL","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":7,"description":"Seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2026-01-19T10:37:06.298000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b00e9/MkX4-gN9W49Ijknjs_Qzh_ef502877702747e39edfab1d2fe5a86f.jpg","title":"Fibo Lite"},{"category":"text-to-json","description":"Structured Prompt Generation endpoint for Fibo-Lite, Bria's SOTA Open source model","endpoint_id":"bria/fibo-lite/generate/structured_prompt/lite","family":"Fibo","inputs":[{"default":null,"description":"Prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The structured prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_prompt","required":false,"type":"json"},{"default":null,"description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2026-01-19T10:34:58.616000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8affc0/46xH4G2e60X5umkgM0rrW_da15955ad9b04677b5f071d149bf4d0b.jpg","title":"Fibo Lite"},{"category":"text-to-image","description":"SOTA open-source text-to-image model delivering high-fidelity outputs with accurate typography. JSON-structured prompts provide production-ready controllability for enterprise and agentic workflows. Trained exclusively on licensed data.","endpoint_id":"bria/fibo/generate","family":"Fibo","inputs":[{"default":null,"description":"Prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The structured prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_prompt","required":false,"type":"json"},{"default":null,"description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Tailored model name. Use hf- prefix for Hugging Face repo ids.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tailored_model_name","required":false,"type":"string"},{"default":null,"description":"Optional checkpoint step for the tailored model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tailored_model_checkpoint","required":false,"type":"integer"},{"default":1,"description":"Influence of the tailored model LoRA.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"tailored_model_influence","required":false,"type":"number"},{"default":50,"description":"Number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"steps_num","required":false,"type":"integer"},{"default":"1:1","description":"Aspect ratio. Options: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"Negative prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"1MP","description":"Output image resolution","enum":["1MP","4MP"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"Bria AI","output_kind":"images","output_props":["structured_prompt","images","image"],"pricing":"","published_at":"2025-10-29T10:12:55.756000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/KZ0Rdf_H7CtVE7Gpqk7XB_430bc50472c44700aaee472dd73c18f1.jpg","title":"Fibo"},{"category":"text-to-json","description":"Structured Prompt Generation endpoint for Fibo, Bria's SOTA Open source model.","endpoint_id":"bria/fibo/generate/structured_prompt","family":"Fibo","inputs":[{"default":null,"description":"Prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The structured prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structured_prompt","required":false,"type":"json"},{"default":null,"description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-10-29T15:47:29.106000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/0DWtoqgo_Rli062CkYFDy_1329a7c4a855435c94b1e9d7169fe405.jpg","title":"Fibo"},{"category":"image-to-image","description":"The GenFill Route enables the generation of objects by prompt in a specific region of an image.\nYou can define the area for object generation by using a mask that outlines the region where the object will be created. Our model is optimized to work seamlessly with blob-shaped masks.","endpoint_id":"bria/genfill/v2","family":"","inputs":[{"default":null,"description":"The source image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"Instruct what elements you would like to fill in your image based on the mask.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instruction","required":true,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"Number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"steps_num","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["structured_instruction","images","image"],"pricing":"","published_at":"2026-06-10T18:55:53.634000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d7ee2/ePYzrUawXgdh7Hq4be-v6_bd443c983e2e47d39d3ebd5ad65406a9.jpg","title":"Genfill"},{"category":"image-to-image","description":"Generate professional, eCommerce-ready product shots by replacing backgrounds with realistic lighting and accurate perspective from a simple text prompt. Trained exclusively on licensed data for safe commercial use.","endpoint_id":"bria/replace-background","family":"","inputs":[{"default":null,"description":"Prompt for background replacement.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"https://v3b.fal.media/files/b/0a8bea8c/Mztgx0NG3HPdby-4iPqwH_a_coffee_machine_standing_in_the_kitchen.png","description":"Reference image (file or URL).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":4925634,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"Number of inference steps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"steps_num","required":false,"type":"integer"},{"default":"","description":"Negative prompt for background replacement.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2026-01-27T11:10:25.377000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c0fb2/wNeDpxdQqIVEIpNSmlnG0_20782e56e2b946beba84550451577cf3.jpg","title":"Replace Background"},{"category":"image-to-image","description":"Professional-grade creative upscaler that doubles resolution up to 10MP, regenerating sharper textures, refined details, and cleaner faces. Trained exclusively on licensed data for risk-free commercial use.","endpoint_id":"bria/upscale/creative","family":"","inputs":[{"default":"https://bria-datasets.s3.us-east-1.amazonaws.com/upscale/wild-west.png","description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":5555,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Preserve alpha channel from input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_alpha","required":false,"type":"boolean"}],"lab":"Bria AI","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2026-02-23T11:28:54.474000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f7bca/m78uzt7MEVkgCcaEux179_4ef74caf0e414da78bd587bde2272ee2.jpg","title":"Upscale"},{"category":"video-to-video","description":"Automatically remove backgrounds from videos -perfect for creating clean, professional content without a green screen.","endpoint_id":"bria/video/background-removal","family":"","inputs":[{"default":"webm_vp9","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, mov_h265, mov_proresks, mkv_h265, mkv_h264, mkv_vp9, gif.","enum":["mp4_h265","mp4_h264","webm_vp9","mov_h265","mov_proresks","mkv_h265","mkv_h264","mkv_vp9","gif"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input video to remove background from. Size should be less than 4000x4000 and duration less than 30s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"Black","description":"Background color. Options: Transparent, Black, White, Gray, Red, Green, Blue, Yellow, Cyan, Magenta, Orange.","enum":["Transparent","Black","White","Gray","Red","Green","Blue","Yellow","Cyan","Magenta","Orange"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"enum"}],"lab":"Bria AI","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.0042 per second.","published_at":"2025-06-30T06:13:15.906000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Video"},{"category":"video-to-video","description":"Remove video backgrounds in real time with Bria’s VRMBG 3.0 model. Built for live streaming, real-time video apps, content creation, and low-latency workflows that need fast, accurate background removal.","endpoint_id":"bria/video/background-removal/realtime","family":"Background","inputs":[{"default":50,"description":"Background blur strength, 0-100 (used when background_type is 'blur').","enum":null,"is_list":false,"max":100,"media_kind":null,"min":0,"multiline":false,"name":"blur_strength","required":false,"type":"integer"},{"default":"Black","description":"Solid background colour (used when background_type is 'color').","enum":["Black","White","Gray","Red","Green","Blue","Yellow","Cyan","Magenta","Orange"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"enum"},{"default":"color","description":"How to replace the background: 'color', 'image', or 'blur'.","enum":["color","image","blur"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_type","required":false,"type":"enum"},{"default":"","description":"Playground webcam/video source. Media is sent over WebRTC.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Background image URL or data URI (used when background_type is 'image').","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"background_image_url","required":false,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"Your request will cost $0.0042 per second.","published_at":"2026-06-10T13:40:59.435000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d92ae/8pODM5dvxzvcRlvKxkjJt_da7ef3699aa947fdaca7b12cdc223500.jpg","title":"Bria's VRMBG 3.0 Realtime"},{"category":"video-to-video","description":"Remove backgrounds from any video with Bria's VRMBG 3.0. Fast, accurate background removal across talking heads, podcasts, product videos, commercials, and cinematic footage.","endpoint_id":"bria/video/background-removal/v3","family":"","inputs":[{"default":"webm_vp9","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, mov_h265, mov_proresks, mkv_h265, mkv_h264, mkv_vp9, gif.","enum":["mp4_h265","mp4_h264","webm_vp9","mov_h265","mov_proresks","mkv_h265","mkv_h264","mkv_vp9","gif"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input video to remove background from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"Black","description":"Background color. Options: Transparent, Black, White, Gray, Red, Green, Blue, Yellow, Cyan, Magenta, Orange.","enum":["Transparent","Black","White","Gray","Red","Green","Blue","Yellow","Cyan","Magenta","Orange"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","request_id"],"pricing":"Your request will cost $0.0042 per second.","published_at":"2026-06-10T13:41:05.678000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d7900/xGTehR9rmBwM3AQm_wwzT_473aa24e726a4f71a494e03c354fd91f.jpg","title":"Bria's VRMBG 3.0"},{"category":"video-to-video","description":"High-fidelity keypoint-driven video object removal - minimal input, strong temporal consistency. Trained on licensed data for risk-free commercial video editing.","endpoint_id":"bria/video/erase/keypoints","family":"","inputs":[{"default":"mp4_h264","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, gif, mov_h264, mov_h265, mov_proresks, mkv_h264, mkv_h265, mkv_vp9, mkv_mpeg4.","enum":["mp4_h265","mp4_h264","webm_vp9","gif","mov_h264","mov_h265","mov_proresks","mkv_h264","mkv_h265","mkv_vp9","mkv_mpeg4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"auto trim the video, to working duration ( 5s )","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_trim","required":false,"type":"boolean"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input keypoints [x,y] to erase or keep from the video. Format like so: {'x':100, 'y':100, 'type':'positive/negative'}","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keypoints","required":true,"type":"string"},{"default":null,"description":"Input video to erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-12-23T19:47:59.068000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875807/hufu-WhXnSbIHPs2JUqFE_f40049919fd148f293c7e9aeb04c71ce.jpg","title":"Video"},{"category":"video-to-video","description":"High-fidelity mask-based video object removal with strong temporal consistency. Erase unwanted objects, people, or elements while preserving aesthetic quality. Trained on licensed data for risk-free commercial use.","endpoint_id":"bria/video/erase/mask","family":"","inputs":[{"default":"mp4_h264","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, gif, mov_h264, mov_h265, mov_proresks, mkv_h264, mkv_h265, mkv_vp9, mkv_mpeg4.","enum":["mp4_h265","mp4_h264","webm_vp9","gif","mov_h264","mov_h265","mov_proresks","mkv_h264","mkv_h265","mkv_vp9","mkv_mpeg4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"auto trim the video, to working duration ( 5s )","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_trim","required":false,"type":"boolean"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input video to erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Input video to mask erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-12-23T19:20:38.011000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875792/fiFX5LR2jtecUmE7yLyY8_340c579c0b1e408ab0d7920d3a2d3e32.jpg","title":"Video"},{"category":"video-to-video","description":"Erase unwanted objects, people, or elements from video with a text prompt. High-fidelity output with strong temporal consistency, trained on licensed data for safe commercial use.","endpoint_id":"bria/video/erase/prompt","family":"","inputs":[{"default":"mp4_h264","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, gif, mov_h264, mov_h265, mov_proresks, mkv_h264, mkv_h265, mkv_vp9, mkv_mpeg4.","enum":["mp4_h265","mp4_h264","webm_vp9","gif","mov_h264","mov_h265","mov_proresks","mkv_h264","mkv_h265","mkv_vp9","mkv_mpeg4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"auto trim the video, to working duration ( 5s )","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_trim","required":false,"type":"boolean"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input prompt to detect object to erase","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Input video to erase object from. duration must be less than 5s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-12-23T19:39:44.048000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875a33/-FGyIBxFrcWVZh-vsPpsC_f673e5d46d864e53becd4f71174b73ec.jpg","title":"Video"},{"category":"video-to-video","description":"Professional-grade video upscaler with strong temporal consistency, enhancing videos up to 8K resolution. Trained on fully licensed and commercially safe data - risk-free for production and enterprise use.","endpoint_id":"bria/video/increase-resolution","family":"","inputs":[{"default":"webm_vp9","description":"Output container and codec. Options: mp4_h265, mp4_h264, webm_vp9, mov_h265, mov_proresks, mkv_h265, mkv_h264, mkv_vp9, gif.","enum":["mp4_h265","mp4_h264","webm_vp9","mov_h265","mov_proresks","mkv_h265","mkv_h264","mkv_vp9","gif"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_container_and_codec","required":false,"type":"enum"},{"default":true,"description":"If true, audio will be preserved in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":null,"description":"Input video to increase resolution. Size should be less than 7680,4320 and duration less than 30s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"2","description":"desired_increase factor. Options: 2x, 4x.","enum":["2","4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"desired_increase","required":false,"type":"enum"}],"lab":"Bria AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-08-26T07:20:19.877000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9394/Gv2DUNHmUD1RlZKOjKTDI_6LS6WM1Y.png","title":"Video"},{"category":"image-to-video","description":"Generate subject consistent videos using Lynx from ByteDance!","endpoint_id":"bytedance/lynx","family":"","inputs":[{"default":null,"description":"The URL of the subject image to be used for video generation","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text prompt to guide video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Bright tones, overexposed, blurred background, static, subtitles, style, works, paintings, images, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"Negative prompt to guide what should not appear in the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":75,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p)","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9, 9:16, or 1:1)","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"Identity preservation scale. Controls how closely the generated video preserves the subject's identity from the reference image.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"ip_scale","required":false,"type":"number"},{"default":1,"description":"Reference image scale. Controls the influence of the reference image on the generated video.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"Image guidance scale. Controls how closely the generated video follows the reference image. Higher values increase adherence to the reference image but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":81,"description":"Number of frames in the generated video. Must be between 9 to 100.","enum":null,"is_list":false,"max":81,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2025-11-18T01:53:22.544000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/46Az_CH4LkzpoBBIJYiSf_c6c1e1cb386b4e30b7c0e8eee627379c.jpg","title":"Lynx"},{"category":"text-to-audio","description":"Seed Audio 1.0 is a new audio model from Bytedance that can generate high-quality, natural sounding audio using text, reference audios or an image.","endpoint_id":"bytedance/seed-audio-1.0","family":"Seed Audio 1.0","inputs":[{"default":null,"description":"Prompt or text to synthesize. Reference audio inputs by order with @Audio1, @Audio2, @Audio3.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice to use for synthesis: either a preset voice name or a cloned voice id.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"string"},{"default":null,"description":"Up to 3 reference audio URLs, referenced in prompt as @Audio1, @Audio2, @Audio3. Each clip: up to 30s, 10MB, wav/mp3/pcm/ogg_opus.","enum":null,"is_list":true,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_urls","required":false,"type":"string"},{"default":null,"description":"A single reference image URL (jpeg/png/webp, up to 10MB). Cannot be combined with audio references.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":"mp3","description":"Output audio format.","enum":["wav","mp3","pcm","ogg_opus"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":24000,"description":"Sample rate of the output audio in Hz.","enum":[8000,16000,24000,32000,44100,48000],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sample_rate","required":false,"type":"enum"},{"default":1,"description":"Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.5,"multiline":false,"name":"speed","required":false,"type":"number"},{"default":1,"description":"Volume. 1.0 is normal volume, 0.5 is half, 2.0 is double.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.5,"multiline":false,"name":"volume","required":false,"type":"number"},{"default":0,"description":"Voice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":-12,"multiline":false,"name":"pitch","required":false,"type":"integer"}],"lab":"Bytedance","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-06-25T12:18:58.344000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fb613/LcZVbUHHvdKBUIFSlv9Yx.jpg","title":"Seed Audio 1.0"},{"category":"image-to-video","description":"ByteDance's most advanced image-to-video model, fast tier. Lower latency and cost with synchronized audio, start and end frame control, and motion prompts.","endpoint_id":"bytedance/seedance-2.0/fast/image-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt describing the desired motion and action for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"standard","description":"Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.","enum":["standard","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate_mode","required":false,"type":"enum"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.2419/second. Your request will cost $0.0112 per 1000 tokens. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.","published_at":"2026-04-01T18:43:34.817000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9460fd/T3K2mVx51M-pOewqVAb1g_408d1bcc1efc4cfa902293ac5b1f378d.jpg","title":"Seedance 2.0 Fast Image to Video"},{"category":"image-to-video","description":"ByteDance's most advanced reference-to-video model, fast tier. Lower latency and cost with up to 9 images, 3 videos, and 3 audio clips as inputs.","endpoint_id":"bytedance/seedance-2.0/fast/reference-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt used to generate the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required.","enum":null,"is_list":true,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_urls","required":false,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"standard","description":"Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.","enum":["standard","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate_mode","required":false,"type":"enum"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.2419/second. Your request will cost $0.0112 per 1000 tokens. The number of tokens is given by (height of output video * width of output video * (input video duration + output video duration) * 24) / 1024. If video inputs are provided the price is multiplied by 0.6. With video inputs and 720p resolution the price is $0.14515 per second.","published_at":"2026-04-01T18:46:16.471000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f0f/CksSmhus-kf2wceFqGv6u_28b605ee7aca4793871852ab3ecd70b6.jpg","title":"Seedance 2.0 Fast Reference to Video"},{"category":"text-to-video","description":"ByteDance's most advanced text-to-video model, fast tier. Lower latency and cost with cinematic output, native audio, multi-shot editing, and director-level camera control.","endpoint_id":"bytedance/seedance-2.0/fast/text-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"standard","description":"Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.","enum":["standard","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate_mode","required":false,"type":"enum"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.2419/second. Your request will cost $0.0112 per 1000 tokens. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.","published_at":"2026-04-01T18:47:38.648000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f1c/JJWaVP5VEiyeEiqaEXWli_321bd6ab4d3f4ee8bf0003a332814416.jpg","title":"Seedance 2.0 Fast Text to Video"},{"category":"image-to-video","description":"ByteDance's most advanced image-to-video model. Animate still images into cinematic video with synchronized audio, start and end frame control, and motion prompts.","endpoint_id":"bytedance/seedance-2.0/image-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt describing the desired motion and action for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality, 4k for highest quality.","enum":["480p","720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"standard","description":"Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.","enum":["standard","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate_mode","required":false,"type":"enum"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.3034/second and for 1080p you will be charged $0.682/second. Your request will cost $0.014 per 1000 tokens for 480p, 720p and 1080p. Your request will cost $0.008 per 1000 tokens for 4k. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.","published_at":"2026-04-01T18:47:20.614000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f2b/C5HNQz1oux7K-6Tqfd_-9_c4a7c912a6db402686fe2c01591a1687.jpg","title":"Seedance 2 Image to Video"},{"category":"image-to-video","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","endpoint_id":"bytedance/seedance-2.0/mini/image-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt describing the desired motion and action for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the starting frame image to animate. Supported formats: JPEG, PNG, WebP. Max 30 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the last frame of the video. When provided, the generated video will transition from the starting image to this ending image. Supported formats: JPEG, PNG, WebP. Max 30 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to infer from the input image.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of video generated, you will be charged roughly $0.0721/second for 480p and $0.1547/second for 720p.\nActual cost calculations are based on token prices, with token costs being $0.007 per 1,000 tokens for both 480p and 720p. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.","published_at":"2026-06-24T11:19:18.937000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f7e64/hqSxiLW2DPExuIrP_Nh6e_9e1fcd4255554d659310e3fd469b3cb3.jpg","title":"Seedance 2.0 Mini Image to Video"},{"category":"image-to-video","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","endpoint_id":"bytedance/seedance-2.0/mini/reference-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt used to generate the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required.","enum":null,"is_list":true,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_urls","required":false,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of video generated, you will be charged roughly $0.0721/second for 480p and $0.1547/second for 720p.\nIf a video input is provided, the video input is charged at 0.6 times the per-second price for the selected resolution. This is roughly $0.0433/second for 480p video and $0.0928/second for 720p video. You will be charged for video input and output, at the rate for the output resolution.\nActual cost calculations are based on token prices, with token costs being $0.007 per 1,000 tokens for both 480p and 720p. The number of tokens is given by (height of output video * width of output video * (input video duration + output video duration) * 24) / 1024.","published_at":"2026-06-24T11:19:25.749000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f7e63/evQshZj8rTqx3E564ZJOf_17a33801d0344490944bae38639ba9fd.jpg","title":"Seedance 2.0 Mini"},{"category":"text-to-video","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","endpoint_id":"bytedance/seedance-2.0/mini/text-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of video generated, you will be charged roughly $0.0721/second for 480p and $0.1547/second for 720p.\nActual cost calculations are based on token prices, with token costs being $0.007 per 1000 tokens for both 480p and 720p. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.","published_at":"2026-06-24T11:19:12.864000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f7e59/QR4fszdxC1WKHff7uSfwK_027c3c79ba7b49ab855976d21fc1171b.jpg","title":"Seedance 2.0 Mini Text to Video"},{"category":"image-to-video","description":"ByteDance's most advanced reference-to-video model. Generate video from up to 9 images, 3 videos, and 3 audio clips with native audio and cinematic camera control.","endpoint_id":"bytedance/seedance-2.0/reference-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt used to generate the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file.If audio is provided, at least one reference image or video is required.","enum":null,"is_list":true,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_urls","required":false,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality, 4k for highest quality.","enum":["480p","720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"standard","description":"Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.","enum":["standard","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate_mode","required":false,"type":"enum"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.3034/second and for 1080p you will be charged $0.682/second. Your request will cost $0.014 per 1000 tokens for 480p, 720p and 1080p. Your request will cost $0.008 per 1000 tokens for 4k. The number of tokens is given by (height of output video * width of output video * (input video duration + output video duration) * 24) / 1024.  If video inputs are provided the price is multiplied by 0.6. With video inputs and 720p resolution the price is $0.1814 per second.","published_at":"2026-04-01T18:48:22.239000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f1a/nie2992p9QXZaJbgszHZY_d584fa3e77b44d57a33417a48fac06ab.jpg","title":"Seedance 2 Reference to Video"},{"category":"text-to-video","description":"ByteDance's most advanced text-to-video model. Cinematic output with native audio, multi-shot editing, real-world physics, and director-level camera control.","endpoint_id":"bytedance/seedance-2.0/text-to-video","family":"Seedance 2","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality, 4k for highest quality.","enum":["480p","720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Duration of the video in seconds. Supports 4 to 15 seconds, or auto to let the model decide based on the prompt.","enum":["auto","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.","enum":["auto","21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"standard","description":"Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.","enum":["standard","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate_mode","required":false,"type":"enum"},{"default":null,"description":"The unique user ID of the end user.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_user_id","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","seed"],"pricing":"For every second of 720p video you generated, you will be charged $0.3034/second and for 1080p you will be charged $0.682/second. Your request will cost $0.014 per 1000 tokens for 480p, 720p and 1080p. Your request will cost $0.008 per 1000 tokens for 4k . The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.","published_at":"2026-04-01T18:49:18.123000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f13/XcRHMX9gZIMSYL7ImArbn_ed7636768b1f41d286c66ed5ebc0521d.jpg","title":"Seedance 2.0 Text to Video API"},{"category":"text-to-audio","description":"CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.","endpoint_id":"cassetteai/music-generator","family":"","inputs":[{"default":null,"description":"The prompt to generate music from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The duration of the generated music in seconds.","enum":null,"is_list":false,"max":180,"media_kind":null,"min":10,"multiline":false,"name":"duration","required":true,"type":"integer"}],"lab":"Cassette AI","output_kind":"json","output_props":["audio_file"],"pricing":"Your request will cost $0.02 per output minute.","published_at":"2025-03-27T15:08:50.013000+00:00","thumbnail":"https://fal.media/files/rabbit/sMvFmn2J_7gVG77CCgseb_728490598d0242a2abf19f7fae6a93a6.jpg","title":"music generator"},{"category":"text-to-audio","description":"Create stunningly realistic sound effects in seconds - CassetteAI's Sound Effects Model generates high-quality SFX up to 30 seconds long in just 1 second of processing time","endpoint_id":"cassetteai/sound-effects-generator","family":"","inputs":[{"default":null,"description":"The prompt to generate SFX.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The duration of the generated SFX in seconds.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":true,"type":"integer"}],"lab":"Cassette AI","output_kind":"json","output_props":["audio_file"],"pricing":"","published_at":"2025-04-03T22:14:05.362000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/cassetteai-sound-effects-generator.webp","title":"Sound Effects Generator"},{"category":"video-to-video","description":"Add sound effects to your videos","endpoint_id":"cassetteai/video-sound-effects-generator","family":"","inputs":[{"default":null,"description":"A video file to analyze & re-sound with generated SFX.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_url","required":true,"type":"json"}],"lab":"Cassette AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-04-07T21:35:38.015000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/cassetteai-video-sound-effects-generator.webp","title":"Video Sound Effects Generator"},{"category":"image-to-image","description":"An advanced image enhancement tool designed specifically for facial details and portrait photography, utilizing Clarity AI's upscaling technology.","endpoint_id":"clarityai/crystal-upscaler","family":"Crystal","inputs":[{"default":null,"description":"URL to the input image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":2,"description":"Scale factor","enum":null,"is_list":false,"max":200,"media_kind":null,"min":1,"multiline":false,"name":"scale_factor","required":false,"type":"number"},{"default":0,"description":"Creativity level for upscaling","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"creativity","required":false,"type":"number"},{"default":"jpg","description":"Output image format","enum":["png","jpg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Clarity AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-11-25T13:16:15.815000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/MXXDFIdMKdUafM9WsY5sk_10934786a1c846acbb01d7ae9c2bdab1.jpg","title":"Crystal Upscaler"},{"category":"video-to-video","description":"Do high precision video upscaling that respects the original video perfectly using Crystal Upscaler's new video upscaling method!","endpoint_id":"clarityai/crystal-video-upscaler","family":"Crystal","inputs":[{"default":null,"description":"URL to the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":2,"description":"Scale factor. The scale factor must be chosen such that the upscaled video does not exceed 5K resolution.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":1,"multiline":false,"name":"scale_factor","required":false,"type":"number"}],"lab":"Clarity AI","output_kind":"video","output_props":["video"],"pricing":"Pricing is $0.10 per megapixel per second. The total cost is multiplied based on the video’s frame rate (FPS), using 30-FPS increments:\n- Up to 30 FPS → 1× multiplier\n- Up to 60 FPS → 2× multiplier\n- Up to 90 FPS → 3× multiplier\n\n\nFor instance, a video upscaled to a resolution of 2440 × 1440, with a frame rate of 30 FPS and a duration of 4 seconds, is priced as follows: \n3.5 (megapixels) × 4 (seconds) × 1 (FPS multiplier for 0–30 FPS) × $0.10 = $1.40","published_at":"2025-12-17T18:13:38.786000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86b01d/L1t7sXzCg1McwUfjIr5AO_747a16db692443928b48959e58c268e3.jpg","title":"Crystal Upscaler [Video]"},{"category":"video-to-video","description":"Edit outfits, objects, faces, or restyle your video - all with maximum detail retention.","endpoint_id":"decart/lucy-edit/pro","family":"Lucy","inputs":[{"default":null,"description":"Text description of the desired video content","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the video to edit","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"720p","description":"Resolution of the generated video","enum":["720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"}],"lab":"Decart","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.15 per video second for 720p, $0.10 per video second for 480p.","published_at":"2025-09-18T16:11:33.328000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/_g9nFjAdwfSx3rZckDkCG_7076290e770c43a094a751a42799f16b.jpg","title":"Lucy Edit [Pro]"},{"category":"video-to-video","description":"Restyle videos up to 30 min long - maintaining maximum detail quality.","endpoint_id":"decart/lucy-restyle","family":"Lucy","inputs":[{"default":null,"description":"Text description of the desired video content","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the video to edit","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Seed for video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video","enum":["720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"}],"lab":"Decart","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-18T18:15:56.727000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875784/qqR_QkwlbbQ2ARTcqKcKT_2afde46d6ba14b16a21637286fc188aa.jpg","title":"Lucy Restyle"},{"category":"video-to-video","description":"Realtime Try On experience with Decart Lucy 2.1 VTON","endpoint_id":"decart/lucy2-vton/realtime","family":"Lucy","inputs":[{"default":"Substitute the current top with the outfit from the reference image, matching its color, material, and fit","description":"Text prompt for the real-time transformation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"Image data URI or HTTP(S) URL for realtime frame input. Data URI format: data:image/<type>;base64,...","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":"https://v3b.fal.media/files/b/0a985506/y57_APcgGHlPxOOHIOqYO_15129.png","description":"Reference image URL or data URI. When set, Lucy 2 will use this as a character reference for the transformation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"}],"lab":"Decart","output_kind":"json","output_props":[],"pricing":"","published_at":"2026-04-30T19:03:01.639000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8dec83/HYSrrZyh0t83bYaiRt7jK_01253b85d4d54911b45e23f8cfeafd69.jpg","title":"Lucy 2.1 VTON Realtime"},{"category":"text-to-audio","description":"Generate music with lyrics from text using ACE-Step","endpoint_id":"fal-ai/ace-step","family":"","inputs":[{"default":null,"description":"Comma-separated list of genre tags to control the style of the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tags","required":true,"type":"string"},{"default":"","description":"Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics","required":false,"type":"string"},{"default":60,"description":"The duration of the generated audio in seconds.","enum":null,"is_list":false,"max":240,"media_kind":null,"min":5,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":27,"description":"Number of steps to generate the audio.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":3,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"euler","description":"Scheduler to use for the generation process.","enum":["euler","heun"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"apg","description":"Type of CFG to use for the generation process.","enum":["cfg","apg","cfg_star"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_type","required":false,"type":"enum"},{"default":10,"description":"Granularity scale for the generation process. Higher values can reduce artifacts.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"granularity_scale","required":false,"type":"integer"},{"default":0.5,"description":"Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval","required":false,"type":"number"},{"default":0,"description":"Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval_decay","required":false,"type":"number"},{"default":15,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Minimum guidance scale for the generation after the decay.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"minimum_guidance_scale","required":false,"type":"number"},{"default":5,"description":"Tag guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tag_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"Lyric guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"lyric_guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["tags","lyrics","audio","seed"],"pricing":"Your request will cost $0.0002 per second of generated audio. For $1 you can run generate 5000 seconds (83 minutes) of music from lyrics.","published_at":"2025-05-08T21:47:06.754000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b3/9VL1XeX8WQ9GzM0BA_gC7_MYE49kWH.png","title":"ACE Step"},{"category":"audio-to-audio","description":"Modify a portion of provided audio with lyrics and/or style using ACE-Step","endpoint_id":"fal-ai/ace-step/audio-inpaint","family":"","inputs":[{"default":null,"description":"URL of the audio file to be inpainted.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"start","description":"Whether the start time is relative to the start or end of the audio.","enum":["start","end"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"start_time_relative_to","required":false,"type":"enum"},{"default":0,"description":"start time in seconds for the inpainting process.","enum":null,"is_list":false,"max":240,"media_kind":null,"min":0,"multiline":false,"name":"start_time","required":false,"type":"number"},{"default":"start","description":"Whether the end time is relative to the start or end of the audio.","enum":["start","end"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_time_relative_to","required":false,"type":"enum"},{"default":30,"description":"end time in seconds for the inpainting process.","enum":null,"is_list":false,"max":240,"media_kind":null,"min":0,"multiline":false,"name":"end_time","required":false,"type":"number"},{"default":null,"description":"Comma-separated list of genre tags to control the style of the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tags","required":true,"type":"string"},{"default":"","description":"Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics","required":false,"type":"string"},{"default":0.5,"description":"Variance for the inpainting process. Higher values can lead to more diverse results.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"variance","required":false,"type":"number"},{"default":27,"description":"Number of steps to generate the audio.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":3,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"euler","description":"Scheduler to use for the generation process.","enum":["euler","heun"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"apg","description":"Type of CFG to use for the generation process.","enum":["cfg","apg","cfg_star"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_type","required":false,"type":"enum"},{"default":10,"description":"Granularity scale for the generation process. Higher values can reduce artifacts.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"granularity_scale","required":false,"type":"integer"},{"default":0.5,"description":"Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval","required":false,"type":"number"},{"default":0,"description":"Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval_decay","required":false,"type":"number"},{"default":15,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Minimum guidance scale for the generation after the decay.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"minimum_guidance_scale","required":false,"type":"number"},{"default":5,"description":"Tag guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tag_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"Lyric guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"lyric_guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["tags","lyrics","audio","seed"],"pricing":"Your request will cost $0.0002 per second of generated audio. For $1 you can run generate 5000 seconds (83 minutes) of music from lyrics.","published_at":"2025-05-11T17:55:55.827000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"ACE Step Audio Inpaint"},{"category":"audio-to-audio","description":"Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step","endpoint_id":"fal-ai/ace-step/audio-outpaint","family":"","inputs":[{"default":null,"description":"URL of the audio file to be outpainted.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Duration in seconds to extend the audio from the start.","enum":null,"is_list":false,"max":107,"media_kind":null,"min":0,"multiline":false,"name":"extend_before_duration","required":false,"type":"number"},{"default":30,"description":"Duration in seconds to extend the audio from the end.","enum":null,"is_list":false,"max":107,"media_kind":null,"min":0,"multiline":false,"name":"extend_after_duration","required":false,"type":"number"},{"default":null,"description":"Comma-separated list of genre tags to control the style of the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tags","required":true,"type":"string"},{"default":"","description":"Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics","required":false,"type":"string"},{"default":27,"description":"Number of steps to generate the audio.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":3,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"euler","description":"Scheduler to use for the generation process.","enum":["euler","heun"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"apg","description":"Type of CFG to use for the generation process.","enum":["cfg","apg","cfg_star"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_type","required":false,"type":"enum"},{"default":10,"description":"Granularity scale for the generation process. Higher values can reduce artifacts.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"granularity_scale","required":false,"type":"integer"},{"default":0.5,"description":"Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval","required":false,"type":"number"},{"default":0,"description":"Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval_decay","required":false,"type":"number"},{"default":15,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Minimum guidance scale for the generation after the decay.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"minimum_guidance_scale","required":false,"type":"number"},{"default":5,"description":"Tag guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tag_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"Lyric guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"lyric_guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["tags","lyrics","audio","seed"],"pricing":"Your request will cost $0.0002 per second of generated audio. For $1 you can run generate 5000 seconds (83 minutes) of music from lyrics.","published_at":"2025-05-11T17:57:21.159000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"ACE Step Audio Outpaint"},{"category":"audio-to-audio","description":"Generate music from a lyrics and example audio using ACE-Step","endpoint_id":"fal-ai/ace-step/audio-to-audio","family":"","inputs":[{"default":null,"description":"URL of the audio file to be outpainted.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"remix","description":"Whether to edit the lyrics only or remix the audio.","enum":["lyrics","remix"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"edit_mode","required":false,"type":"enum"},{"default":null,"description":"Original tags of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_tags","required":true,"type":"string"},{"default":"","description":"Original lyrics of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_lyrics","required":false,"type":"string"},{"default":null,"description":"Comma-separated list of genre tags to control the style of the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tags","required":true,"type":"string"},{"default":"","description":"Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics","required":false,"type":"string"},{"default":27,"description":"Number of steps to generate the audio.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":3,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"euler","description":"Scheduler to use for the generation process.","enum":["euler","heun"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"apg","description":"Type of CFG to use for the generation process.","enum":["cfg","apg","cfg_star"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_type","required":false,"type":"enum"},{"default":10,"description":"Granularity scale for the generation process. Higher values can reduce artifacts.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"granularity_scale","required":false,"type":"integer"},{"default":0.5,"description":"Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval","required":false,"type":"number"},{"default":0,"description":"Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval_decay","required":false,"type":"number"},{"default":15,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Minimum guidance scale for the generation after the decay.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"minimum_guidance_scale","required":false,"type":"number"},{"default":5,"description":"Tag guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tag_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"Lyric guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"lyric_guidance_scale","required":false,"type":"number"},{"default":null,"description":"Original seed of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_seed","required":false,"type":"integer"}],"lab":"","output_kind":"audio","output_props":["tags","lyrics","audio","seed"],"pricing":"Your request will cost $0.0002 per second of generated audio. For $1 you can run generate 5000 seconds (83 minutes) of music from lyrics.","published_at":"2025-05-11T17:53:31.579000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cf/hzzRn42s_9muLz0OmggMY_AltNTjLY.png","title":"ACE Step Audio To Audio"},{"category":"text-to-audio","description":"Generate music from a simple prompt using ACE-Step","endpoint_id":"fal-ai/ace-step/prompt-to-audio","family":"","inputs":[{"default":null,"description":"Prompt to control the style of the generated audio. This will be used to generate tags and lyrics.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to generate an instrumental version of the audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"instrumental","required":false,"type":"boolean"},{"default":60,"description":"The duration of the generated audio in seconds.","enum":null,"is_list":false,"max":240,"media_kind":null,"min":5,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":27,"description":"Number of steps to generate the audio.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":3,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"euler","description":"Scheduler to use for the generation process.","enum":["euler","heun"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"apg","description":"Type of CFG to use for the generation process.","enum":["cfg","apg","cfg_star"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_type","required":false,"type":"enum"},{"default":10,"description":"Granularity scale for the generation process. Higher values can reduce artifacts.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"granularity_scale","required":false,"type":"integer"},{"default":0.5,"description":"Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval","required":false,"type":"number"},{"default":0,"description":"Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"guidance_interval_decay","required":false,"type":"number"},{"default":15,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Minimum guidance scale for the generation after the decay.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":0,"multiline":false,"name":"minimum_guidance_scale","required":false,"type":"number"},{"default":5,"description":"Tag guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tag_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"Lyric guidance scale for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"lyric_guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["tags","lyrics","audio","seed"],"pricing":"Your request will cost $0.0002 per second of generated audio. For $1 you can run generate 5000 seconds (83 minutes) of music from lyrics.","published_at":"2025-05-11T17:51:47.356000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b4/vrSrTlTF5lgNXOblHW2w7_rCiFN1PF.png","title":"ACE Step Prompt To Audio"},{"category":"image-to-video","description":"MultiTalk model generates a multi-person conversation video from an image and audio files. Creates a realistic scene where multiple people speak in sequence.","endpoint_id":"fal-ai/ai-avatar/multi","family":"","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the Person 1 audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"first_audio_url","required":true,"type":"string"},{"default":null,"description":"The URL of the Person 2 audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"second_audio_url","required":false,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":181,"description":"Number of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":241,"media_kind":null,"min":41,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the video to generate. Must be either 480p or 720p.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":81,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":4294967295,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to use only the first audio file.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_only_first_audio","required":false,"type":"boolean"},{"default":"regular","description":"The acceleration level to use for generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-06-23T16:34:01.663000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound.jpg","title":"AI Avatar Multi"},{"category":"image-to-video","description":"MultiTalk model generates a multi-person conversation video from an image and text inputs. Converts text to speech for each person, generating a realistic conversation scene.","endpoint_id":"fal-ai/ai-avatar/multi-text","family":"","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text input to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"first_text_input","required":true,"type":"string"},{"default":null,"description":"The text input to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"second_text_input","required":true,"type":"string"},{"default":"Sarah","description":"The first person's voice to use for speech generation","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice1","required":false,"type":"enum"},{"default":"Roger","description":"The second person's voice to use for speech generation","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice2","required":false,"type":"enum"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":191,"description":"Number of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":241,"media_kind":null,"min":41,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the video to generate. Must be either 480p or 720p.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":81,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":4294967295,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-06-23T16:34:48.424000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound.jpg","title":"AI Avatar Multi Text"},{"category":"image-to-video","description":"MultiTalk model generates a talking avatar video from an image and text. Converts text to speech automatically, then generates the avatar speaking with lip-sync.","endpoint_id":"fal-ai/ai-avatar/single-text","family":"","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text input to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_input","required":true,"type":"string"},{"default":null,"description":"The voice to use for speech generation","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":136,"description":"Number of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":241,"media_kind":null,"min":41,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the video to generate. Must be either 480p or 720p.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":42,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":4294967295,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-06-23T16:36:23.549000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d3/GGyonkybjHXVatjApR-ZR_uN2w1Yg9.png","title":"AI Avatar Single Text"},{"category":"video-to-video","description":"Interpolate between video frames","endpoint_id":"fal-ai/amt-interpolation","family":"","inputs":[{"default":null,"description":"URL of the video to be processed","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":24,"description":"Output frames per second","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_fps","required":false,"type":"integer"},{"default":2,"description":"Number of recursive interpolation passes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"recursive_interpolation_passes","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/amt-interpolation.webp","title":"AMT Interpolation"},{"category":"image-to-video","description":"Interpolate between image frames","endpoint_id":"fal-ai/amt-interpolation/frame-interpolation","family":"","inputs":[{"default":null,"description":"Frames to interpolate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"frames","required":true,"type":"json"},{"default":24,"description":"Output frames per second","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_fps","required":false,"type":"integer"},{"default":4,"description":"Number of recursive interpolation passes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"recursive_interpolation_passes","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-07-18T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/amt-interpolation.webp","title":"AMT Frame Interpolation"},{"category":"audio-to-audio","description":"A audio understanding model to analyze audio content and answer questions about what's happening in the audio based on user prompts.","endpoint_id":"fal-ai/audio-understanding","family":"","inputs":[{"default":null,"description":"URL of the audio file to analyze","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"The question or prompt about the audio content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to request a more detailed analysis of the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detailed_analysis","required":false,"type":"boolean"}],"lab":"","output_kind":"text","output_props":["output"],"pricing":"","published_at":"2025-10-24T16:53:57.084000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/6SXguUXRvg1XrEdf_zZcM_023b35fa7e9e4777b3e7fa0934ebb13a.jpg","title":"Audio Understanding"},{"category":"text-to-image","description":"AuraFlow v0.3 is an open-source flow-based text-to-image generation model that achieves state-of-the-art results on GenEval. The model is currently in beta.","endpoint_id":"fal-ai/aura-flow","family":"","inputs":[{"default":null,"description":"The prompt to generate images from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generating images","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"Classifier free guidance scale","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"The number of inference steps to take","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to perform prompt expansion (recommended)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2024-12-02T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/aura-flow.webp","title":"AuraFlow"},{"category":"image-to-image","description":"Upscale your images with AuraSR.","endpoint_id":"fal-ai/aura-sr","family":"","inputs":[{"default":null,"description":"URL of the image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":4,"description":"Upscaling factor. More coming soon.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_factor","required":false,"type":"integer"},{"default":false,"description":"Whether to use overlapping tiles for upscaling. Setting this to true helps remove seams but doubles the inference time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"overlapping_tiles","required":false,"type":"boolean"},{"default":"v1","description":"Checkpoint to use for upscaling. More coming soon.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"checkpoint","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["image","timings"],"pricing":"","published_at":"2024-04-11T00:00:00+00:00","thumbnail":"https://v3.fal.media/files/koala/rW7Rhmjtkjvb8gnOPUhNN_b14088de7d684d4b8489db59d53ae3f7.jpg","title":"AuraSR"},{"category":"video-to-video","description":"Automatically generates text captions for your videos from the audio as per text colour/font specifications","endpoint_id":"fal-ai/auto-caption","family":"","inputs":[{"default":null,"description":"URL to the .mp4 video with audio. Only videos of size <400MB are allowed.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"white","description":"Colour of the text. Can be a RGB tuple, a color name, or an hexadecimal notation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"txt_color","required":false,"type":"string"},{"default":"Standard","description":"Font for generated captions. Choose one in 'Arial','Standard','Garamond', 'Times New Roman','Georgia', or pass a url to a .ttf file","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"txt_font","required":false,"type":"string"},{"default":24,"description":"Size of text in generated captions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_size","required":false,"type":"integer"},{"default":1,"description":"Width of the text strokes in pixels","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"stroke_width","required":false,"type":"integer"},{"default":"center","description":"Left-to-right alignment of the text. Can be a string ('left', 'center', 'right') or a float (0.0-1.0)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"left_align","required":false,"type":"string"},{"default":"center","description":"Top-to-bottom alignment of the text. Can be a string ('top', 'center', 'bottom') or a float (0.0-1.0)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"top_align","required":false,"type":"string"},{"default":1.5,"description":"Number of seconds the captions should stay on screen. A higher number will also result in more text being displayed at once.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0.5,"multiline":false,"name":"refresh_interval","required":false,"type":"number"},{"default":"default","description":"Capitalization to apply to subtitle text. 'upper' converts text to UPPERCASE, 'lower' converts to lowercase, and 'default' preserves the original casing produced by the speech recognizer.","enum":["default","upper","lower"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_case","required":false,"type":"enum"}],"lab":"","output_kind":"text","output_props":["video_url"],"pricing":"","published_at":"2025-01-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/caption_thumbnail.webp","title":"Auto-Captioner"},{"category":"text-to-image","description":"Bagel is a 7B parameter from Bytedance-Seed multimodal model that can generate both text and images.","endpoint_id":"fal-ai/bagel","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to use thought tokens for generation. If set to true, the model will \"think\" to potentially improve generation quality. Increases generation time and increases the cost by 20%.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_thought","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","timings","prompt"],"pricing":"","published_at":"2025-05-21T18:27:20.822000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bagel.webp","title":"Bagel"},{"category":"image-to-image","description":"Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both images and text.","endpoint_id":"fal-ai/bagel/edit","family":"","inputs":[{"default":null,"description":"The prompt to edit the image with.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to use thought tokens for generation. If set to true, the model will \"think\" to potentially improve generation quality. Increases generation time and increases the cost by 20%.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_thought","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","timings","prompt"],"pricing":"","published_at":"2025-05-21T18:30:09.512000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bagel.webp","title":"Bagel"},{"category":"image-to-json","description":"Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both text and images.","endpoint_id":"fal-ai/bagel/understand","family":"","inputs":[{"default":null,"description":"The image for the query.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to query the image with.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["text","seed","timings","prompt"],"pricing":"","published_at":"2025-05-21T18:37:27.397000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bagel.webp","title":"Bagel"},{"category":"image-to-image","description":"A fast and high quality model for image background removal.","endpoint_id":"fal-ai/ben/v2/image","family":"","inputs":[{"default":null,"description":"URL of image to be used for background removal","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/Ben2/FepDP7G4K2nxlX0sq6AMB_945a221d079e447c9bcfea77f931cdc1.webp","title":"ben-v2-image"},{"category":"video-to-video","description":"A model for high quality and smooth background removal for videos.","endpoint_id":"fal-ai/ben/v2/video","family":"","inputs":[{"default":null,"description":"URL of video to be used for background removal.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional RGB values (0-255) for the background color. If not provided, the background will be transparent. For ex: [0, 0, 0]","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":"mp4","description":"Output video format. Use \"webm\" for true transparency support (VP9 codec with alpha channel). MP4 format does not support transparency and will render transparent areas as black.","enum":["mp4","webm"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/Ben2/Vi9PBzFF8BfuKGsLCvoH-_773fe2c0efc744af900eaac2047b9b5f.webp","title":"Ben-Video-Bg-Rm"},{"category":"image-to-image","description":"Edit any image with a natural-language instruction using Bernini-R, changing the weather, materials, objects, or style while preserving the original composition.","endpoint_id":"fal-ai/bernini-r/edit-image","family":"Bernini","inputs":[{"default":null,"description":"Text prompt or editing instruction.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative prompt. Defaults to the standard Wan2.2 negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":848,"description":"Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.","enum":null,"is_list":false,"max":1280,"media_kind":null,"min":256,"multiline":false,"name":"max_image_size","required":false,"type":"integer"},{"default":null,"description":"Seed for reproducibility. Random when omitted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Source image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"image","output_props":["seed","actual_prompt","image"],"pricing":"$0.03 per megapixel of the output image, rounded up (units = ceil(width × height ÷ 1,048,576)). Most edits are 1 MP = $0.03; a large 1280×1280 edit is 2 MP = $0.06.","published_at":"2026-06-09T11:04:32.605000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d825b/sgocUWuUHMa_Dej-g8D7u_a17a98a9853844219a5d214e8504e3a3.jpg","title":"Bernini-R Edit Image"},{"category":"video-to-video","description":"Edit any video with a natural-language instruction using Bernini-R, changing objects, weather, background, or camera angle while keeping the rest of the scene intact.","endpoint_id":"fal-ai/bernini-r/edit-video","family":"Bernini","inputs":[{"default":null,"description":"Text prompt or editing instruction.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative prompt. Defaults to the standard Wan2.2 negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":848,"description":"Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.","enum":null,"is_list":false,"max":1280,"media_kind":null,"min":256,"multiline":false,"name":"max_image_size","required":false,"type":"integer"},{"default":null,"description":"Seed for reproducibility. Random when omitted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":81,"description":"Number of frames. Snapped internally to 4k+1.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":5,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Output frames per second.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"none","description":"Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Source video to edit.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["actual_prompt","seed","video"],"pricing":"For every second of 848px (default) video you generated, you will be charged $0.08/second. Your request will be scaled by resolution along the longest edge. The scaling multiplier is given by 0.5 for ≤576px, 1 for 848px, and 2 for 1280px.","published_at":"2026-06-09T11:04:12.652000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d8156/Id_OtIbUS5Zk9ivk4tOuI_9416b514fc6b4de7ae727285aec5bacf.jpg","title":"Bernini-R Edit Video"},{"category":"video-to-video","description":"Edit a video guided by reference images with Bernini-R, bringing an object, material, background, style, or weather from a reference image into your video.","endpoint_id":"fal-ai/bernini-r/reference-edit-video","family":"Bernini","inputs":[{"default":null,"description":"Text prompt or editing instruction.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative prompt. Defaults to the standard Wan2.2 negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":848,"description":"Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.","enum":null,"is_list":false,"max":1280,"media_kind":null,"min":256,"multiline":false,"name":"max_image_size","required":false,"type":"integer"},{"default":null,"description":"Seed for reproducibility. Random when omitted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":81,"description":"Number of frames. Snapped internally to 4k+1.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":5,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Output frames per second.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"none","description":"Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Source video to edit.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Reference image(s) guiding the edit; up to 5.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["actual_prompt","seed","video"],"pricing":"For every second of 848px (default) video you generated, you will be charged $0.08/second. Your request will be scaled by resolution along the longest edge. The scaling multiplier is given by 0.5 for ≤576px, 1 for 848px, and 2 for 1280px.","published_at":"2026-06-09T11:04:20.410000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d8233/HjxyBEnMK-Hg5zdp7rqvj_fe33464759ce4900be125ea15e254a6c.jpg","title":"Bernini-R Reference Edit Video"},{"category":"image-to-video","description":"Turn up to five reference images into one continuous, consistent video with Bernini-R, with smooth, stable camera motion and no scene cuts.","endpoint_id":"fal-ai/bernini-r/reference-to-video","family":"Bernini","inputs":[{"default":null,"description":"Text prompt or editing instruction.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative prompt. Defaults to the standard Wan2.2 negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":848,"description":"Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.","enum":null,"is_list":false,"max":1280,"media_kind":null,"min":256,"multiline":false,"name":"max_image_size","required":false,"type":"integer"},{"default":null,"description":"Seed for reproducibility. Random when omitted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":81,"description":"Number of frames. Snapped internally to 4k+1.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":5,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Output frames per second.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"none","description":"Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Reference subject image(s); up to 5.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":"16:9","description":"Output aspect ratio.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Bytedance","output_kind":"video","output_props":["actual_prompt","seed","video"],"pricing":"For every second of 848px (default) video you generated, you will be charged $0.08/second. Your request will be scaled by resolution along the longest edge. The scaling multiplier is given by 0.5 for ≤576px, 1 for 848px, and 2 for 1280px.","published_at":"2026-06-09T11:04:26.700000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d8246/duVIuiorJ_0xR-azlCIv8_20f794b611d8484ba1bf6bc90dddc4f3.jpg","title":"Bernini-R Reference to Video"},{"category":"text-to-video","description":"Generate high-quality video from a text prompt with Bernini-R, ByteDance's unified video generation and editing model.","endpoint_id":"fal-ai/bernini-r/text-to-video","family":"Bernini","inputs":[{"default":null,"description":"Text prompt or editing instruction.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative prompt. Defaults to the standard Wan2.2 negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":848,"description":"Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.","enum":null,"is_list":false,"max":1280,"media_kind":null,"min":256,"multiline":false,"name":"max_image_size","required":false,"type":"integer"},{"default":null,"description":"Seed for reproducibility. Random when omitted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":81,"description":"Number of frames. Snapped internally to 4k+1.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":5,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Output frames per second.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"none","description":"Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"16:9","description":"Output aspect ratio.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Bytedance","output_kind":"video","output_props":["actual_prompt","seed","video"],"pricing":"For every second of 848px (default) video you generated, you will be charged $0.08/second. Your request will be scaled by resolution along the longest edge. The scaling multiplier is given by 0.5 for ≤576px, 1 for 848px, and 2 for 1280px.","published_at":"2026-06-09T11:04:04.621000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d8204/OiKWO51vPgqD1ig4wZk8R_54d4adc0062f4b389933c71a4bcb826b.jpg","title":"Bernini-R Text to Video"},{"category":"image-to-image","description":"bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)","endpoint_id":"fal-ai/birefnet","family":"Birefnet","inputs":[{"default":"General Use (Light)","description":"Model to use for background removal.\n            The 'General Use (Light)' model is the original model used in the BiRefNet repository.\n            The 'General Use (Heavy)' model is a slower but more accurate model.\n            The 'Portrait' model is a model trained specifically for portrait images.\n            The 'General Use (Light)' model is recommended for most use cases.\n\n            The corresponding models are as follows:\n            - 'General Use (Light)': BiRefNet-DIS_ep580.pth\n    ","enum":["General Use (Light)","General Use (Heavy)","Portrait"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":"1024x1024","description":"The resolution to operate on. The higher the resolution, the more accurate the output will be for high res input images.","enum":["1024x1024","2048x2048"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"operating_resolution","required":false,"type":"enum"},{"default":false,"description":"Whether to output the mask used to remove the background","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_mask","required":false,"type":"boolean"},{"default":true,"description":"Whether to refine the foreground using the estimated mask","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refine_foreground","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to remove background from","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"png","description":"The format of the output image","enum":["webp","png","gif"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["mask_image","image"],"pricing":"","published_at":"2024-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/birefnet.webp","title":"Birefnet Background Removal"},{"category":"image-to-image","description":"bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)","endpoint_id":"fal-ai/birefnet/v2","family":"Birefnet","inputs":[{"default":"General Use (Light)","description":"Model to use for background removal.\n            The 'General Use (Light)' model is the original model used in the BiRefNet repository.\n            The 'General Use (Light 2K)' model is the original model used in the BiRefNet repository but trained with 2K images.\n            The 'General Use (Heavy)' model is a slower but more accurate model.\n            The 'Matting' model is a model trained specifically for matting images.\n            The 'Portrait' model is a model trained specifically for p","enum":["General Use (Light)","General Use (Light 2K)","General Use (Heavy)","Matting","Portrait","General Use (Dynamic)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":"1024x1024","description":"The resolution to operate on. The higher the resolution, the more accurate the output will be for high res input images. The '2304x2304' option is only available for the 'General Use (Dynamic)' model.","enum":["1024x1024","2048x2048","2304x2304"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"operating_resolution","required":false,"type":"enum"},{"default":false,"description":"Whether to output the mask used to remove the background","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_mask","required":false,"type":"boolean"},{"default":true,"description":"Whether to refine the foreground using the estimated mask","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refine_foreground","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to remove background from","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"png","description":"The format of the output image","enum":["webp","png","gif"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Whether to return only the segmentation mask without applying it to the image. When set to `True`, only the mask will be returned and foreground refinement will be skipped. Useful for reducing computation and data transfer when only the mask is needed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mask_only","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["mask_image","image"],"pricing":"","published_at":"2024-10-28T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/birefnet.webp","title":"Birefnet Background Removal V2"},{"category":"video-to-video","description":"Video background removal version of bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)","endpoint_id":"fal-ai/birefnet/v2/video","family":"Birefnet","inputs":[{"default":"General Use (Light)","description":"Model to use for background removal.\n            The 'General Use (Light)' model is the original model used in the BiRefNet repository.\n            The 'General Use (Light 2K)' model is the original model used in the BiRefNet repository but trained with 2K images.\n            The 'General Use (Heavy)' model is a slower but more accurate model.\n            The 'Matting' model is a model trained specifically for matting images.\n            The 'Portrait' model is a model trained specifically for p","enum":["General Use (Light)","General Use (Light 2K)","General Use (Heavy)","Matting","Portrait","General Use (Dynamic)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":"1024x1024","description":"The resolution to operate on. The higher the resolution, the more accurate the output will be for high res input images. The '2304x2304' option is only available for the 'General Use (Dynamic)' model.","enum":["1024x1024","2048x2048","2304x2304"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"operating_resolution","required":false,"type":"enum"},{"default":false,"description":"Whether to output the mask used to remove the background","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_mask","required":false,"type":"boolean"},{"default":true,"description":"Whether to refine the foreground using the estimated mask","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refine_foreground","required":false,"type":"boolean"},{"default":null,"description":"URL of the video to remove background from","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","mask_video"],"pricing":"","published_at":"2025-10-26T18:13:23.036000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/SKrLsOM3RMOk-QuNj8-io_6356be1b301e454394d2e0a853b98c76.jpg","title":"Birefnet"},{"category":"text-to-image","description":"Image generation with BitDance. Fast, high-resolution photorealistic images using an autoregressive LLM— for efficient, high-quality results.","endpoint_id":"fal-ai/bitdance","family":"","inputs":[{"default":null,"description":"Text prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image. Will be snapped to the nearest supported resolution.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":25,"description":"Number of diffusion sampling steps per decoding step. Higher values (e.g. 50) improve quality at the cost of speed.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Classifier-free guidance scale. Higher values follow the prompt more closely.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility. The same seed and prompt will produce the same image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["prompt","seed","has_nsfw_concepts","images"],"pricing":"You will be charged $0.01 per image generated.","published_at":"2026-02-21T01:51:17.239000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f4e53/xqlOok44eA6yVc8iTGjFQ_2677d5ffa13447518f24e4ed1477fca1.jpg","title":"Bitdance"},{"category":"text-to-image","description":"Text To Image Model using Boogu-Image","endpoint_id":"fal-ai/boogu-image","family":"","inputs":[{"default":null,"description":"The instruction describing the image to generate. Boogu-Image is bilingual — English and Chinese instructions are both supported. Detailed, descriptive prompts produce the best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Describes what should NOT appear in the image. Used for classifier-free guidance; leave empty to disable text negative guidance.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image. The model's maximum native resolution is 2K; larger requests are clamped. Dimensions are aligned to multiples of 16.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of denoising steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"Controls how closely generation follows the text instruction. Higher values stick more closely to the prompt. A value of 1.0 disables text classifier-free guidance.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0,"description":"Start of the timestep fraction over which CFG is applied.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_range_start","required":false,"type":"number"},{"default":1,"description":"End of the timestep fraction over which CFG is applied.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_range_end","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If true, the safety checker is run on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["timings","prompt","has_nsfw_concepts","images","seed"],"pricing":"Your request will cost $0.04 per megapixel of each generated image (a 1024×1024 image is 1 megapixel). For example, a 1MP image costs $0.04 and a 2048×2048 (4MP) image costs $0.16. Generating multiple images multiplies the cost by the number of images.","published_at":"2026-06-18T00:07:35.793000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eb742/8QNsn7JFWdvxtbkhJsDym_1e782ca20ecb4a9187294c4d2e1140d6.jpg","title":"Boogu Image"},{"category":"image-to-image","description":"Image To Image Model using Boogu-Image","endpoint_id":"fal-ai/boogu-image/edit","family":"","inputs":[{"default":null,"description":"The edit instruction describing how to transform the input image. Boogu-Image supports English and Chinese instructions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"Describes what should NOT appear in the edited image. Used for classifier-free guidance; leave empty to disable text negative guidance.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The output size. If omitted, the edited image follows the input image aspect ratio while respecting the model's 2K native limit.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of denoising steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"Controls how closely the edit follows the text instruction. Higher values stick more closely to the prompt.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"Reference-image guidance strength. A value of 1.0 disables image CFG; higher values preserve the input image more strongly.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"image_guidance_scale","required":false,"type":"number"},{"default":0,"description":"Start of the timestep fraction over which CFG is applied.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_range_start","required":false,"type":"number"},{"default":1,"description":"End of the timestep fraction over which CFG is applied.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_range_end","required":false,"type":"number"},{"default":1,"description":"The number of edited images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed, prompt, and input image given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If true, the safety checker is run on the input and output images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["timings","prompt","has_nsfw_concepts","images","seed"],"pricing":"Your request will cost $0.04 per megapixel of each generated image (a 1024×1024 image is 1 megapixel). For example, a 1MP image costs $0.04 and a 2048×2048 (4MP) image costs $0.16. Generating multiple images multiplies the cost by the number of images.","published_at":"2026-06-18T00:07:26.597000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eb89f/j82hUH1BOPbfNF6F0etgy_2e7f4e89b0314bc997a85a38dd833d2b.jpg","title":"Boogu Image"},{"category":"image-to-image","description":"Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use. Model weights for commercial use are available here: https://share-eu1.hsforms.com/2GLpEVQqJTI2Lj7AMYwgfIwf4e04","endpoint_id":"fal-ai/bria/background/remove","family":"Background","inputs":[{"default":null,"description":"Input image to remove background from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Bria AI","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b0/MLLgU8RVRvmMXjLkFNHwH_DWC4dcir.png","title":"Bria RMBG 2.0"},{"category":"image-to-image","description":"Bria Background Replace allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use","endpoint_id":"fal-ai/bria/background/replace","family":"","inputs":[{"default":null,"description":"Input Image to erase from","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"The URL of the reference image to be used for generating the new background. Use \"\" to leave empty. Either ref_image_url or bg_prompt has to be provided but not both. If both ref_image_url and ref_image_file are provided, ref_image_url will be used. Accepted formats are jpeg, jpg, png, webp.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"ref_image_url","required":false,"type":"string"},{"default":null,"description":"The prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"The negative prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to refine prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refine_prompt","required":false,"type":"boolean"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to use the fast model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fast","required":false,"type":"boolean"},{"default":1,"description":"Number of Images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Background Replace"},{"category":"image-to-image","description":"Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us","endpoint_id":"fal-ai/bria/eraser","family":"","inputs":[{"default":null,"description":"Input Image to erase from","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the binary mask image that represents the area that will be cleaned.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":"manual","description":"You can use this parameter to specify the type of the input mask from the list. 'manual' opttion should be used in cases in which the mask had been generated by a user (e.g. with a brush tool), and 'automatic' mask type should be used when mask had been generated by an algorithm like 'SAM'.","enum":["manual","automatic"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mask_type","required":false,"type":"enum"},{"default":false,"description":"If set to true, attempts to preserve the alpha channel of the input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_alpha","required":false,"type":"boolean"}],"lab":"Bria AI","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Eraser"},{"category":"image-to-image","description":"Bria Expand expands images beyond their borders in high quality. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us","endpoint_id":"fal-ai/bria/expand","family":"","inputs":[{"default":null,"description":"The URL of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The desired size of the final image, after the expansion. should have an area of less than 5000x5000 pixels.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"canvas_size","required":true,"type":"integer"},{"default":null,"description":"The desired aspect ratio of the final image. Will be used over original_image_size and original_image_location if provided.","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The desired size of the original image, inside the full canvas. Ensure that the ratio of input image foreground or main subject to the canvas area is greater than 15% to achieve optimal results. Will be ignored if aspect_ratio is provided.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_image_size","required":false,"type":"integer"},{"default":null,"description":"The desired location of the original image, inside the full canvas. Provide the location of the upper left corner of the original image. The location can also be outside the canvas (the original image will be cropped). Will be ignored if aspect_ratio is provided.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_image_location","required":false,"type":"integer"},{"default":"","description":"Text on which you wish to base the image expansion. This parameter is optional. Bria currently supports prompts in English only, excluding special characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"You can choose whether you want your generated expension to be random or predictable. You can recreate the same result in the future by using the seed value of a result from the response. You can exclude this parameter if you are not interested in recreating your results. This parameter is optional.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"The negative prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Bria AI","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Expand Image"},{"category":"image-to-image","description":"Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us","endpoint_id":"fal-ai/bria/genfill","family":"","inputs":[{"default":null,"description":"Input Image to erase from","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the binary mask image that represents the area that will be cleaned.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"The prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of Images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria GenFill"},{"category":"image-to-image","description":"Place any product in any scenery with just a prompt or reference image while maintaining high integrity of the product. Trained exclusively on licensed data for safe and risk-free commercial use and optimized for eCommerce.","endpoint_id":"fal-ai/bria/product-shot","family":"","inputs":[{"default":null,"description":"The URL of the product shot to be placed in a lifestyle shot. If both image_url and image_file are provided, image_url will be used. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text description of the new scene or background for the provided product shot. Bria currently supports prompts in English only, excluding special characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"scene_description","required":false,"type":"string"},{"default":"","description":"The URL of the reference image to be used for generating the new scene or background for the product shot. Use \"\" to leave empty.Either ref_image_url or scene_description has to be provided but not both. If both ref_image_url and ref_image_file are provided, ref_image_url will be used. Accepted formats are jpeg, jpg, png, webp.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"ref_image_url","required":false,"type":"string"},{"default":true,"description":"Whether to optimize the scene description","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"optimize_description","required":false,"type":"boolean"},{"default":1,"description":"The number of lifestyle product shots you would like to generate. You will get num_results x 10 results when placement_type=automatic and according to the number of required placements x num_results if placement_type=manual_placement.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_results","required":false,"type":"integer"},{"default":true,"description":"Whether to use the fast model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fast","required":false,"type":"boolean"},{"default":"manual_placement","description":"This parameter allows you to control the positioning of the product in the image. Choosing 'original' will preserve the original position of the product in the image. Choosing 'automatic' will generate results with the 10 recommended positions for the product. Choosing 'manual_placement' will allow you to select predefined positions (using the parameter 'manual_placement_selection'). Selecting 'manual_padding' will allow you to control the position and size of the image by defining the desired p","enum":["original","automatic","manual_placement","manual_padding"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"placement_type","required":false,"type":"enum"},{"default":false,"description":"This flag is only relevant when placement_type=original. If true, the output image retains the original input image's size; otherwise, the image is scaled to 1 megapixel (1MP) while preserving its aspect ratio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_quality","required":false,"type":"boolean"},{"default":[1000,1000],"description":"The desired size of the final product shot. For optimal results, the total number of pixels should be around 1,000,000. This parameter is only relevant when placement_type=automatic or placement_type=manual_placement.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_size","required":false,"type":"integer"},{"default":"bottom_center","description":"If you've selected placement_type=manual_placement, you should use this parameter to specify which placements/positions you would like to use from the list. You can select more than one placement in one request.","enum":["upper_left","upper_right","bottom_left","bottom_right","right_center","left_center","upper_center","bottom_center","center_vertical","center_horizontal"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"manual_placement_selection","required":false,"type":"enum"},{"default":null,"description":"The desired padding in pixels around the product, when using placement_type=manual_padding. The order of the values is [left, right, top, bottom]. For optimal results, the total number of pixels, including padding, should be around 1,000,000. It is recommended to first use the product cutout API, get the cutout and understand the size of the result, and then define the required padding and use the cutout as an input for this API.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"padding_values","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Product Shot"},{"category":"image-to-image","description":"Structure Reference allows generating new images while preserving the structure of an input image, guided by text prompts. Perfect for transforming sketches, illustrations, or photos into new illustrations. Trained exclusively on licensed data for safe and risk-free commercial use.","endpoint_id":"fal-ai/bria/reimagine","family":"","inputs":[{"default":null,"description":"The prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The URL of the structure reference image. Use \"\" to leave empty. Accepted formats are jpeg, jpg, png, webp.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"structure_image_url","required":false,"type":"string"},{"default":0.75,"description":"The influence of the structure reference on the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"structure_ref_influence","required":false,"type":"number"},{"default":1,"description":"How many images you would like to generate. When using any Guidance Method, Value is set to 1.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_results","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to use the fast model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fast","required":false,"type":"boolean"},{"default":30,"description":"The number of iterations the model goes through to refine the generated image. This parameter is optional.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"Bria AI","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-07-08T06:49:49.700000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a4/DhMb6TGEeLweW90G0C9dc_htR2FUth.png","title":"Bria"},{"category":"text-to-image","description":"Bria's Text-to-Image model, trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us","endpoint_id":"fal-ai/bria/text-to-image/base","family":"","inputs":[{"default":null,"description":"The prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":4,"description":"How many images you would like to generate. When using any Guidance Method, Value is set to 1.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the image. When a guidance method is being used, the aspect ratio is defined by the guidance image and this parameter is ignored.","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"The number of iterations the model goes through to refine the generated image. This parameter is optional.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"When set to true, enhances the provided prompt by generating additional, more descriptive variations, resulting in more diverse and creative output images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_enhancement","required":false,"type":"boolean"},{"default":null,"description":"Which medium should be included in your generated images. This parameter is optional.","enum":["photography","art"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"medium","required":false,"type":"enum"},{"default":"[]","description":"Guidance images to use for the generation. Up to 4 guidance methods can be combined during a single inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance","required":false,"type":"json"}],"lab":"Bria AI","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Text-to-Image Base"},{"category":"text-to-image","description":"Bria's Text-to-Image model with perfect harmony of latency and quality. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us","endpoint_id":"fal-ai/bria/text-to-image/fast","family":"","inputs":[{"default":null,"description":"The prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":4,"description":"How many images you would like to generate. When using any Guidance Method, Value is set to 1.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the image. When a guidance method is being used, the aspect ratio is defined by the guidance image and this parameter is ignored.","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":8,"description":"The number of iterations the model goes through to refine the generated image. This parameter is optional.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"When set to true, enhances the provided prompt by generating additional, more descriptive variations, resulting in more diverse and creative output images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_enhancement","required":false,"type":"boolean"},{"default":null,"description":"Which medium should be included in your generated images. This parameter is optional.","enum":["photography","art"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"medium","required":false,"type":"enum"},{"default":"[]","description":"Guidance images to use for the generation. Up to 4 guidance methods can be combined during a single inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance","required":false,"type":"json"}],"lab":"Bria AI","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Text-to-Image Fast"},{"category":"text-to-image","description":"Bria's Text-to-Image model for HD images. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us","endpoint_id":"fal-ai/bria/text-to-image/hd","family":"","inputs":[{"default":null,"description":"The prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt you would like to use to generate images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":4,"description":"How many images you would like to generate. When using any Guidance Method, Value is set to 1.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the image. When a guidance method is being used, the aspect ratio is defined by the guidance image and this parameter is ignored.","enum":["1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"The number of iterations the model goes through to refine the generated image. This parameter is optional.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"When set to true, enhances the provided prompt by generating additional, more descriptive variations, resulting in more diverse and creative output images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_enhancement","required":false,"type":"boolean"},{"default":null,"description":"Which medium should be included in your generated images. This parameter is optional.","enum":["photography","art"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"medium","required":false,"type":"enum"},{"default":"[]","description":"Guidance images to use for the generation. Up to 4 guidance methods can be combined during a single inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance","required":false,"type":"json"}],"lab":"Bria AI","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/bria.webp","title":"Bria Text-to-Image HD"},{"category":"video-to-video","description":"Upscale videos with Bytedance's video upscaler.","endpoint_id":"fal-ai/bytedance-upscaler/upscale/video","family":"","inputs":[{"default":null,"description":"The URL of the video to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"1080p","description":"The target resolution of the video to upscale.","enum":["1080p","2k","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_resolution","required":false,"type":"enum"},{"default":"30fps","description":"The target FPS of the video to upscale.","enum":["30fps","60fps"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_fps","required":false,"type":"enum"},{"default":"general","description":"The enhancement preset optimized for specific video scenarios. 'general' is a general-purpose template, 'ugc' targets user-generated short videos, 'short_series' is for short dramas, 'aigc' is for AI-generated content, and 'old_film' is for classic film restoration.","enum":["general","ugc","short_series","aigc","old_film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhancement_preset","required":false,"type":"enum"},{"default":"standard","description":"The enhancement quality tier. 'fast' provides essential upscaling with good speed, 'standard' uses adaptive algorithms for better visual texture, 'pro' uses large-model restoration for cinematic quality (longer processing time), and 10 times the cost of `standard` and `fast`.","enum":["fast","standard","pro"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhancement_tier","required":false,"type":"enum"},{"default":null,"description":"The scaling ratio for the output video resolution. When set, overrides target_resolution and scales the input resolution by this factor (e.g., 2.0 doubles the resolution). Range: 1.1 to 10.0. Please note that this is valid only up to 4k resolution, and trying to scale beyond 4k will result in an error. (4k is defined as having atotal pixel count of 3840x2160).","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1.1,"multiline":false,"name":"scale_ratio","required":false,"type":"number"},{"default":"high","description":"The enhancement intensity. 'high' applies mild enhancement while keeping visual texture close to the source video. 'medium' provides a balanced image quality enhancement.","enum":["high","medium"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fidelity","required":false,"type":"enum"}],"lab":"Bytedance","output_kind":"video","output_props":["video","duration"],"pricing":"Upscaling to 1080p costs $0.0072/s, 2K costs $0.0144/s, and 4K costs $0.0288/s, at a 30fps rate. Processing at 60fps doubles the cost for any resolution. Processing in `pro` mode makes the price 10 times of the normal price ($0.072/s, $0.144/s, $0.288/s for 1080p,2K, 4K at 30fps respectively, at 60fps these prices are further doubled.)","published_at":"2025-10-31T16:15:01.762000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/LorVpq4fAORdnn1YHRM-A_d801feeaa1764cefb7de0c3381ecaf84.jpg","title":"Bytedance Upscaler Upscale Video"},{"category":"video-to-video","description":"Transfer motion from a video to characters in an image using Dreamactor v2. Great performance for non-human and multiple characters","endpoint_id":"fal-ai/bytedance/dreamactor/v2","family":"Dreamactor","inputs":[{"default":null,"description":"The URL of the reference image to animate. Supports real people, animation, pets, etc. Format: jpeg, jpg or png. Max size: 4.7 MB. Resolution: between 480x480 and 1920x1080 (larger images will be proportionally reduced).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the driving template video providing motion, facial expressions, and lip movement reference. Max duration: 30 seconds. Format: mp4, mov or webm. Resolution: between 200x200 and 2048x1440. Supports full face and body driving.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"Whether to crop the first second of the output video. The output has a 1-second transition at the beginning; enable this to remove it.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trim_first_second","required":false,"type":"boolean"}],"lab":"Bytedance","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-02-06T12:48:06.506000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d637e/N5mi3-AcAN8uaBxsYdrtu_753b8ee0acc440c488d57f7197c12fc6.jpg","title":"Bytedance Dreamactor V2"},{"category":"text-to-image","description":"Dreamina showcases superior picture effects, with significant improvements in picture aesthetics, precise and diverse styles, and rich details.","endpoint_id":"fal-ai/bytedance/dreamina/v3.1/text-to-image","family":"Dreamina 3.1","inputs":[{"default":null,"description":"The text prompt used to generate the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":1536,"width":2048},"description":"The size of the generated image. Width and height must be between 512 and 2048.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":false,"description":"Whether to use an LLM to enhance the prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Random seed to control the stochasticity of image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Bytedance","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-08-06T16:21:39.741000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9227/K1_djFqBTasur6I8h_0c__0OKLVTZb.png","title":"Bytedance Dreamina V3.1 Text To Image"},{"category":"image-to-video","description":"OmniHuman generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.","endpoint_id":"fal-ai/bytedance/omnihuman","family":"Omnihuman","inputs":[{"default":null,"description":"The URL of the image used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file to generate the video. Audio must be under 30s long.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["video","duration"],"pricing":"","published_at":"2025-07-27T12:18:13.247000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound.jpg","title":"OmniHuman"},{"category":"image-to-video","description":"Omnihuman v1.5 is a new and improved version of Omnihuman. It generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.","endpoint_id":"fal-ai/bytedance/omnihuman/v1.5","family":"Omnihuman 1.5","inputs":[{"default":null,"description":"The text prompt used to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the image used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask image to apply to the image. Only the person in the white area of the mask will speak.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":null,"description":"The URL of the audio file to generate the video. Audio must be under 30s long for 1080p generation and under 60s long for 720p generation.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"},{"default":false,"description":"Generate a video at a faster rate with a slight quality trade-off.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"},{"default":"1080p","description":"The resolution of the generated video. Defaults to 1080p. 720p generation is faster and higher in quality. 1080p generation is limited to 30s audio and 720p generation is limited to 60s audio.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"Bytedance","output_kind":"video","output_props":["video","duration"],"pricing":"","published_at":"2025-09-23T14:00:56.925000+00:00","thumbnail":"https://v3.fal.media/files/penguin/E4JFEyBXM1DccJUOvp5_e_6414b61bc2e141edb34671e5308addef.jpg","title":"Bytedance Omnihuman V1.5"},{"category":"text-to-speech","description":"Seed Speech developed by ByteDance, is a family of large-scale text-to-speech models capable of synthesizing speech that is virtually indistinguishable from human speech.","endpoint_id":"fal-ai/bytedance/seed-speech/tts/v2","family":"Seed Speech","inputs":[{"default":null,"description":"The text to synthesize into speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"stokie_en","description":"Voice to use for synthesis. The preset name encodes the voice and its supported language codes. 'mixed_en_zh' means the voice can seamlessly blend English and Chinese; separate codes (e.g. 'en_zh') mean the voice supports each language independently.","enum":["vivi_mixed_en_zh_ja_es_id","mindy_en_es_id_pt_zh","stokie_en","dacey_en","tim_en","kian_en_zh","cedric_en_zh","sophie_en_zh","jean_en_zh","magnus_en_zh","mabel_en_zh","nadia_en_zh","opal_en_zh","pearl_en_zh","quentin_en_zh","vienna_mixed_en_zh","alina_mixed_en_zh","corinne_mixed_en_zh","esther_mixed_en_zh","freya_mixed_en_zh","gigi_mixed_en_zh","holly_mixed_en_zh","lyla_mixed_en_zh","daisy_mixed_en_zh","tracy_es_zh","jess_ja_es_id_pt_en_zh","pinky_es_ko_mixed_en_zh","sweety_ja_es","sandy_es_mixed_en_zh","sven_de","minimi_ja","usseau_fr","felipe_es","han_id","martins_pt","enzo_it","shane_ko","bonnie_zh","felix_zh","celeste_zh","monkey_king_zh"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":"mp3","description":"Output audio format. 'mp3' returns MP3 audio; 'opus' returns Opus audio in an Ogg container.","enum":["mp3","opus"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":24000,"description":"Sample rate of the output audio in Hz.","enum":[8000,16000,22050,24000,32000,44100,48000],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sample_rate","required":false,"type":"enum"},{"default":1,"description":"Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.5,"multiline":false,"name":"speed","required":false,"type":"number"},{"default":1,"description":"Volume. 1.0 is normal volume, 0.5 is half, 2.0 is double.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.5,"multiline":false,"name":"volume","required":false,"type":"number"},{"default":0,"description":"Voice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":-12,"multiline":false,"name":"pitch","required":false,"type":"integer"},{"default":null,"description":"Force the text to be read as a single language, disabling automatic language detection. Leave unset for automatic detection (including seamless Chinese/English mixing on bilingual voices). Codes: zh (Chinese), en (English), ja (Japanese), es-mx (Mexican Spanish), id (Indonesian), pt-br (Brazilian Portuguese), ko (Korean), it (Italian), de (German), fr (French).","enum":["zh","en","ja","es-mx","id","pt-br","ko","it","de","fr"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":null,"description":"Optional natural-language instruction that steers the delivery (tone, emotion, pace, volume), e.g. 'Speak in a cheerful tone' or 'Could you speak a bit slower?'. It is not spoken aloud and does not affect billing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"voice_instruction","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-06-05T00:29:41.130000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d0262/si1_Zv34axRlg3Uy9vzy__91af02a234d44b6485784f7e6c6c5f93.jpg","title":"Bytedance Seed Speech Text to Speech"},{"category":"llm","description":"Seed 2.0 Mini is a high-performance multimodal model optimized for low latency and high concurrency. It supports text, image, and video input with 256K context and configurable thinking/reasoning modes.","endpoint_id":"fal-ai/bytedance/seed/v2/mini","family":"Seed 2.0","inputs":[{"default":null,"description":"The text prompt or question for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of images for visual understanding. Supported formats: JPEG, PNG, WebP. A maximum of 6 images is supported. Any additional images will be ignored.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"URLs of videos for video understanding. Supported formats: MP4, MOV. Audio comprehension is not supported. A maximum of 3 videos is supported. Any additional videos will be ignored.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Optional system prompt to guide the model's behavior.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Optional prior conversation history for multi-turn conversations. Pass back the `messages` field from a previous response to provide context. The current `prompt`, `image_urls`, `video_urls`, and `system_prompt` are always appended as the latest user turn.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"messages","required":false,"type":"json"},{"default":"enabled","description":"Controls the model's chain-of-thought reasoning. `enabled` always includes reasoning, `disabled` never includes reasoning, `auto` lets the model decide based on the query.","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking","required":false,"type":"enum"},{"default":null,"description":"Controls the depth of reasoning before the model responds. Only applicable when `thinking` is `enabled` or `auto`. `minimal` for immediate response, `low` for faster response with light reasoning, `medium` for balanced speed and depth, `high` for deep analysis of complex issues.","enum":["minimal","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning_effort","required":false,"type":"enum"},{"default":4096,"description":"Controls the maximum length of the model's output, including both the model's response and its chain-of-thought content, measured in tokens.","enum":null,"is_list":false,"max":65536,"media_kind":null,"min":1,"multiline":false,"name":"max_completion_tokens","required":false,"type":"integer"},{"default":1,"description":"Controls randomness in the response. Lower values make output more focused and deterministic, higher values make it more creative.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.7,"description":"Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass. Lower values narrow the token selection.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"Bytedance","output_kind":"json","output_props":["messages","reasoning_content","output"],"pricing":"Your request will cost $0.0001 per 1000 units. For inputs under 128k tokens, the units per input token is 1. For inputs of over 128k tokens, 2 units will be charged per token. Similarly, each output token costs 4 units, provided the total output length (reasoning + output) is under 128k tokens, and 8 units per token otherwise.","published_at":"2026-03-17T10:53:52.704000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a928503/e-dm_JGXZbPGSsdMydlWI_9ca940576311462d821457a498e6e4d9.jpg","title":"Bytedance Seed V2 Mini"},{"category":"image-to-video","description":"Generate videos with audio with Seedance 1.5 (supports start & end frame)","endpoint_id":"fal-ai/bytedance/seedance/v1.5/pro/image-to-video","family":"Pro Seedance 1.5","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["21:9","16:9","4:3","1:1","3:4","9:16","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the video in seconds","enum":["4","5","6","7","8","9","10","11","12"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to fix the camera position","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_fixed","required":false,"type":"boolean"},{"default":null,"description":"Random seed to control video generation. Use -1 for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate audio for the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The URL of the image used to generate video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image the video ends with. Defaults to None.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"Each 720p 5 second video with audio costs roughly $0.26. For other resolutions, 1 million video tokens with audio costs $2.4. Without audio, the price is 1.2 per millition tokens. tokens(video)  = (height x width x FPS x duration) / 1024.","published_at":"2025-12-23T06:56:11.614000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a876c74/q6J8OsmO08A3zCFGCtsUj_cb48562eeef345b29269689dd4f95671.jpg","title":"Bytedance Seedance V1.5 Pro Image To Video"},{"category":"text-to-video","description":"Generate videos with audio with Seedance 1.5","endpoint_id":"fal-ai/bytedance/seedance/v1.5/pro/text-to-video","family":"Pro Seedance 1.5","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["21:9","16:9","4:3","1:1","3:4","9:16","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the video in seconds","enum":["4","5","6","7","8","9","10","11","12"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to fix the camera position","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_fixed","required":false,"type":"boolean"},{"default":null,"description":"Random seed to control video generation. Use -1 for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate audio for the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"Each 720p 5 second video with audio costs roughly $0.26. For other resolutions, 1 million video tokens with audio costs $2.4. Without audio, the price is 1.2 per millition tokens. tokens(video)  = (height x width x FPS x duration) / 1024.","published_at":"2025-12-23T06:59:34.673000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a876c8c/7ieGsrCnzZmiES-uDGNXs_d16568d7e335443fb7a8dece1f9a9b0d.jpg","title":"Bytedance Seedance V1.5 Pro Text To Video"},{"category":"image-to-video","description":"Image to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost","endpoint_id":"fal-ai/bytedance/seedance/v1/pro/fast/image-to-video","family":"Pro Seedance 1","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video","enum":["21:9","16:9","4:3","1:1","3:4","9:16","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the video in seconds","enum":["2","3","4","5","6","7","8","9","10","11","12"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to fix the camera position","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_fixed","required":false,"type":"boolean"},{"default":null,"description":"Random seed to control video generation. Use -1 for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The number of frames to generate. If provided, will override duration.","enum":null,"is_list":false,"max":289,"media_kind":null,"min":29,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":null,"description":"The URL of the image used to generate video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"Each 1080p 5 second video costs roughly $0.243. For other resolutions, 1 million video tokens costs $1.0. tokens(video)  = (height x width x FPS x duration) / 1024.","published_at":"2025-10-24T11:57:48.061000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/OHnRF5artsmMtvv5DikBL_0d31376b45fc47c28ad70e15245ca449.jpg","title":"Bytedance Seedance V1 Pro Fast Image To Video"},{"category":"text-to-video","description":"Text to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost","endpoint_id":"fal-ai/bytedance/seedance/v1/pro/fast/text-to-video","family":"Pro Seedance 1","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the video in seconds","enum":["2","3","4","5","6","7","8","9","10","11","12"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to fix the camera position","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_fixed","required":false,"type":"boolean"},{"default":null,"description":"Random seed to control video generation. Use -1 for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The number of frames to generate. If provided, will override duration.","enum":null,"is_list":false,"max":289,"media_kind":null,"min":29,"multiline":false,"name":"num_frames","required":false,"type":"integer"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"Each 1080p 5 second video costs roughly $0.245. For other resolutions, 1 million video tokens costs $1. tokens(video)  = (height x width x FPS x duration) / 1024.","published_at":"2025-10-24T11:54:23.140000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/vuOJvxcEA4z0fsRkw3r4Y_4930420a08f045c9ae3c401e3a6d20fc.jpg","title":"Bytedance Seedance V1 Pro Fast Text To Video"},{"category":"image-to-video","description":"Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.","endpoint_id":"fal-ai/bytedance/seedance/v1/pro/image-to-video","family":"Pro Seedance 1","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video","enum":["21:9","16:9","4:3","1:1","3:4","9:16","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the video in seconds","enum":["2","3","4","5","6","7","8","9","10","11","12"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to fix the camera position","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_fixed","required":false,"type":"boolean"},{"default":null,"description":"Random seed to control video generation. Use -1 for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The number of frames to generate. If provided, will override duration.","enum":null,"is_list":false,"max":289,"media_kind":null,"min":29,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":null,"description":"The URL of the image used to generate video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image the video ends with. Defaults to None.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"Each 1080p 5 second video costs roughly $0.62. For other resolutions, 1 million video tokens costs $2.5. tokens(video)  = (height x width x FPS x duration) / 1024.","published_at":"2025-06-16T16:19:27.807000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-3.jpg","title":"Seedance 1.0 Pro"},{"category":"text-to-video","description":"Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.","endpoint_id":"fal-ai/bytedance/seedance/v1/pro/text-to-video","family":"Pro Seedance 1","inputs":[{"default":null,"description":"The text prompt used to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["21:9","16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the video in seconds","enum":["2","3","4","5","6","7","8","9","10","11","12"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to fix the camera position","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_fixed","required":false,"type":"boolean"},{"default":null,"description":"Random seed to control video generation. Use -1 for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The number of frames to generate. If provided, will override duration.","enum":null,"is_list":false,"max":289,"media_kind":null,"min":29,"multiline":false,"name":"num_frames","required":false,"type":"integer"}],"lab":"Bytedance","output_kind":"video","output_props":["seed","video"],"pricing":"Each 1080p 5 second video costs roughly $0.62. For other resolutions, 1 million video tokens costs $2.5. tokens(video)  = (height x width x FPS x duration) / 1024.","published_at":"2025-06-16T16:22:01.447000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","title":"Seedance 1.0 Pro"},{"category":"image-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.","endpoint_id":"fal-ai/bytedance/seedream/v4.5/edit","family":"Seedream 4.5","inputs":[{"default":null,"description":"The text prompt used to edit the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":2048,"width":2048},"description":"The size of the generated image. Width and height must be between 1920 and 4096, or total number of pixels must be between 2560*1440 and 4096*4096.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto_2K","auto_4K","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of separate model generations to be run with the prompt.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`. The total number of images (image inputs + image outputs) must not exceed 15","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":null,"description":"Random seed to control the stochasticity of image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"List of URLs of input images for editing. Presently, up to 10 image inputs are allowed. If over 10 images are sent, only the last 10 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-12-03T10:44:48.263000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84910b/lDvWLqpxcFmzQHdadDA7t_4012f28b4f79444782d90d8927b42c29.jpg","title":"Bytedance Seedream V4.5 Edit"},{"category":"text-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.","endpoint_id":"fal-ai/bytedance/seedream/v4.5/text-to-image","family":"Seedream 4.5","inputs":[{"default":null,"description":"The text prompt used to generate the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":2048,"width":2048},"description":"The size of the generated image. Width and height must be between 1920 and 4096, or total number of pixels must be between 2560*1440 and 4096*4096.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto_2K","auto_4K","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of separate model generations to be run with the prompt.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":null,"description":"Random seed to control the stochasticity of image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Bytedance","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-12-03T10:46:15.916000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84c771/1bdm3n1K8bRK-TzYjLF04_57edae699adf457a8a66ae6665a17e3a.jpg","title":"Bytedance Seedream V4.5 Text To Image"},{"category":"image-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.","endpoint_id":"fal-ai/bytedance/seedream/v4/edit","family":"Seedream 4","inputs":[{"default":null,"description":"The text prompt used to edit the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":2048,"width":2048},"description":"The size of the generated image. The minimum total image area is 921600 pixels. Failing this, the image size will be adjusted to by scaling it up, while maintaining the aspect ratio.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","auto_2K","auto_4K","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of separate model generations to be run with the prompt.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`. The total number of images (image inputs + image outputs) must not exceed 15","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":null,"description":"Random seed to control the stochasticity of image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"standard","description":"The mode to use for enhancing prompt enhancement. Standard mode provides higher quality results but takes longer to generate. Fast mode provides average quality results but takes less time to generate.","enum":["standard","fast"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt_mode","required":false,"type":"enum"},{"default":null,"description":"List of URLs of input images for editing. Presently, up to 10 image inputs are allowed. If over 10 images are sent, only the last 10 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-09-09T08:30:47.714000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/lBQrYkMMpOYBrsUc7T56n_3f3e07d132b742eda53bb80c0647c768.jpg","title":"Bytedance Seedream V4 Edit"},{"category":"text-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.","endpoint_id":"fal-ai/bytedance/seedream/v4/text-to-image","family":"Seedream 4","inputs":[{"default":null,"description":"The text prompt used to generate the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":2048,"width":2048},"description":"The size of the generated image. Total pixels must be between 960x960 and 4096x4096.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","auto_2K","auto_4K","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of separate model generations to be run with the prompt.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":null,"description":"Random seed to control the stochasticity of image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"standard","description":"The mode to use for enhancing prompt enhancement. Standard mode provides higher quality results but takes longer to generate. Fast mode provides average quality results but takes less time to generate.","enum":["standard","fast"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt_mode","required":false,"type":"enum"}],"lab":"Bytedance","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-09-09T08:27:00.849000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91a9/M7ElK8gRPRsRHnAOcaujK_lpIjpXxA.png","title":"Bytedance Seedream V4 Text To Image"},{"category":"image-to-image","description":"Image editing endpoint for the fast Lite version of Seedream 5.0, supporting high quality intelligent image editing with multiple inputs.","endpoint_id":"fal-ai/bytedance/seedream/v5/lite/edit","family":"Seedream 5.0 Lite","inputs":[{"default":null,"description":"The text prompt used to edit the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto_2K","description":"The size of the generated image. Total pixels must be between 2560x1440 and 4096x4096. In case the image size does not fall within these parameters, the image size will be adjusted to by scaling.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto_2K","auto_3K","auto_4K","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of separate model generations to be run with the prompt.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"List of URLs of input images for editing. Presently, up to 10 image inputs are allowed. If over 10 images are sent, only the last 10 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Bytedance","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2026-02-23T08:04:09.398000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fb5/PIUPm_8kBdpdBoSkOebbz_bcfdbe1021324995bf3c36b05ab59c2c.jpg","title":"Bytedance Seedream V5 Lite Edit"},{"category":"text-to-image","description":"Text to Image endpoint for the fast Lite version of Seedream 5.0, supporting high quality intelligent text-to-image generation.","endpoint_id":"fal-ai/bytedance/seedream/v5/lite/text-to-image","family":"Seedream 5.0 Lite","inputs":[{"default":null,"description":"The text prompt used to generate the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto_2K","description":"The size of the generated image. Total pixels must be between 2560x1440 and 4096x4096. In case the image size does not fall within these parameters, the image size will be adjusted to by scaling.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto_2K","auto_3K","auto_4K","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of separate model generations to be run with the prompt.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"If set to a number greater than one, enables multi-image generation. The model will potentially return up to `max_images` images every generation, and in total, `num_images` generations will be carried out. In total, the number of images generated will be between `num_images` and `max_images*num_images`.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true returns seedance-2 trusted URLs. Please note these urls expire in 24 hours.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_byteplus_urls","required":false,"type":"boolean"}],"lab":"Bytedance","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2026-02-23T08:01:50.189000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f9a87/jRElAKkVlihQHtusciuoI_b73a05e10c45441bb15bce9cbed1bf25.jpg","title":"Bytedance Seedream V5 Lite Text To Image"},{"category":"image-to-image","description":"Transform images into 3D cartoon artwork using an AI model that applies cartoon stylization while preserving the original image's composition and details.","endpoint_id":"fal-ai/cartoonify","family":"","inputs":[{"default":null,"description":"URL of the image to apply cartoon style to","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"Scale factor for the Cartoon effect","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.1,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":3.5,"description":"Guidance scale for the generation","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":28,"description":"Number of inference steps","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use CFG zero","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_cfg_zero","required":false,"type":"boolean"},{"default":null,"description":"The seed for image generation. Same seed with same parameters will generate same image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["prompt","timings","has_nsfw_concepts","seed","images"],"pricing":"","published_at":"2025-04-14T21:28:54.080000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"Cartoonify"},{"category":"image-to-image","description":"Image based high quality Virtual Try-On","endpoint_id":"fal-ai/cat-vton","family":"","inputs":[{"default":null,"description":"Url for the human image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"human_image_url","required":true,"type":"string"},{"default":null,"description":"Url to the garment image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"garment_image_url","required":true,"type":"string"},{"default":null,"description":"Type of the Cloth to be tried on.\n\n        Options:\n        upper: Upper body cloth\n        lower: Lower body cloth\n        overall: Full body cloth\n        inner: Inner cloth, like T-shirt inside a jacket\n        outer: Outer cloth, like a jacket over a T-shirt","enum":["upper","lower","overall","inner","outer"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"cloth_type","required":true,"type":"enum"},{"default":"portrait_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same input given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-12-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/idm-vton.jpeg","title":"try-on"},{"category":"image-to-image","description":"SOTA Image Upscaler","endpoint_id":"fal-ai/ccsr","family":"","inputs":[{"default":null,"description":"The URL or data URI of the image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":2,"description":"The scale of the output image. The higher the scale, the bigger the output image will be.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":"none","description":"If specified, a patch-based sampling strategy will be used for sampling.","enum":["none","mix","gaussian"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tile_diffusion","required":false,"type":"enum"},{"default":1024,"description":"Size of patch.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":256,"multiline":false,"name":"tile_diffusion_size","required":false,"type":"integer"},{"default":512,"description":"Stride of sliding patch.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":128,"multiline":false,"name":"tile_diffusion_stride","required":false,"type":"integer"},{"default":false,"description":"If specified, a patch-based sampling strategy will be used for VAE decoding.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tile_vae","required":false,"type":"boolean"},{"default":226,"description":"Size of VAE patch.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_vae_decoder_size","required":false,"type":"integer"},{"default":1024,"description":"Size of latent image","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":128,"multiline":false,"name":"tile_vae_encoder_size","required":false,"type":"integer"},{"default":50,"description":"The number of steps to run the model for. The higher the number the better the quality and longer it will take to generate.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":0.6667,"description":"The ending point of uniform sampling strategy.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"t_max","required":false,"type":"number"},{"default":0.3333,"description":"The starting point of uniform sampling strategy.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"t_min","required":false,"type":"number"},{"default":"adain","description":"Type of color correction for samples.","enum":["none","wavelet","adain"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_fix_type","required":false,"type":"enum"},{"default":null,"description":"Seed for reproducibility. Different seeds will make slightly different results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2024-05-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ccsr.webp","title":"CCSR Upscaler"},{"category":"speech-to-speech","description":"Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.","endpoint_id":"fal-ai/chatterbox/speech-to-speech","family":"Chatterbox","inputs":[{"default":null,"description":"Source Audio Url","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"source_audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL to an audio file to use as a reference for the generated speech. If provided, the model will try to match the style and tone of the reference audio.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"target_voice_audio_url","required":false,"type":"string"}],"lab":"Resemble AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-06-01T19:56:11.760000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/chatterbox.webp","title":"Chatterbox"},{"category":"text-to-speech","description":"Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.","endpoint_id":"fal-ai/chatterbox/text-to-speech","family":"Chatterbox","inputs":[{"default":null,"description":"The text to be converted to speech (maximum 5000 characters). You can additionally add the following emotive tags: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"https://storage.googleapis.com/chatterbox-demo-samples/prompts/male_rickmorty.mp3","description":"Optional URL to an audio file to use as a reference for the generated speech. If provided, the model will try to match the style and tone of the reference audio.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":0.25,"description":"Exaggeration factor for the generated speech (0.0 = no exaggeration, 1.0 = maximum exaggeration).","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"exaggeration","required":false,"type":"number"},{"default":0.7,"description":"Temperature for generation (higher = more creative).","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.05,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.5,"description":"Cfg","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"cfg","required":false,"type":"number"},{"default":null,"description":"Useful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed..","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Resemble AI","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.025 per 1000 characters.","published_at":"2025-06-01T19:53:08.674000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b5/C6BmzEgQMkwwkihT3f3PK_UNKrS2mc.png","title":"Chatterbox"},{"category":"text-to-speech","description":"Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.","endpoint_id":"fal-ai/chatterbox/text-to-speech/multilingual","family":"Chatterbox","inputs":[{"default":null,"description":"The text to be converted to speech (maximum 300 characters). Supports 23 languages including English, French, German, Spanish, Italian, Portuguese, Hindi, Arabic, Chinese, Japanese, Korean, and more.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"english","description":"Language code for synthesis. In case using custom please provide audio url and select custom_audio_language.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"string"},{"default":null,"description":"If using a custom audio URL, specify the language of the audio here. Ignored if voice is not a custom url.","enum":["english","arabic","danish","german","greek","spanish","finnish","french","hebrew","hindi","italian","japanese","korean","malay","dutch","norwegian","polish","portuguese","russian","swedish","swahili","turkish","chinese"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"custom_audio_language","required":false,"type":"enum"},{"default":0.5,"description":"Controls speech expressiveness and emotional intensity (0.25-2.0). 0.5 is neutral, higher values increase expressiveness. Extreme values may be unstable.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.25,"multiline":false,"name":"exaggeration","required":false,"type":"number"},{"default":0.8,"description":"Controls randomness and variation in generation (0.05-5.0). Higher values create more varied speech patterns.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.05,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.5,"description":"Configuration/pace weight controlling generation guidance (0.0-1.0). Use 0.0 for language transfer to mitigate accent inheritance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible results. Set to 0 for random generation, or provide a specific number for consistent outputs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Resemble AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-09-04T18:18:45.389000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cd/Xk6x03JxHdjxnjLHfnxPh_uEN20ZZO.png","title":"Chatterbox"},{"category":"image-to-image","description":"NVIDIA's Logically Consistent and Physics-Aware Image Editing Model","endpoint_id":"fal-ai/chrono-edit","family":"","inputs":[{"default":null,"description":"The image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The guidance scale for the inference.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable temporal reasoning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_temporal_reasoning","required":false,"type":"boolean"},{"default":8,"description":"The number of temporal reasoning steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"num_temporal_reasoning_steps","required":false,"type":"integer"},{"default":"480p","description":"The resolution of the output image.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The seed for the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the output image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable turbo mode to use for faster inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","images","prompt"],"pricing":"Your request will cost $0.01 per image for 480p or $0.02 per image for 720p.","published_at":"2025-10-30T23:45:17.418000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/uV-q_E3zuBgfebtaTzlhM_d462e607525e4f8d9412b9e254c530e6.jpg","title":"Chrono Edit"},{"category":"image-to-image","description":"LoRA endpoint for the Chrono Edit model.","endpoint_id":"fal-ai/chrono-edit-lora","family":"","inputs":[{"default":null,"description":"The image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The guidance scale for the inference.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable temporal reasoning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_temporal_reasoning","required":false,"type":"boolean"},{"default":8,"description":"The number of temporal reasoning steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"num_temporal_reasoning_steps","required":false,"type":"integer"},{"default":"480p","description":"The resolution of the output image.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The seed for the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the output image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable turbo mode to use for faster inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"},{"default":"[]","description":"Optional additional LoRAs to merge for this request (max 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["prompt","seed","images"],"pricing":"Your request will cost $0.02 per image for 480p or $0.03 per image for 720p.","published_at":"2025-11-21T23:32:48.040000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/6I2osemyFuegWWmldrNn__8f3b1d1410d24e6bbe8a9cf8be154af6.jpg","title":"Chrono Edit Lora"},{"category":"image-to-image","description":"You can make edits simply by drawing a quick sketch on the input image.","endpoint_id":"fal-ai/chrono-edit-lora-gallery/paintbrush","family":"","inputs":[{"default":null,"description":"The image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional mask image where black areas indicate regions to sketch/paint.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":null,"description":"Describe how to transform the sketched regions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":8,"description":"Number of denoising steps to run.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"480p","description":"The resolution of the output image.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The scale factor for the LoRA adapter.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The seed for the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"png","description":"The format of the output image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable turbo mode to use faster inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"},{"default":"[]","description":"Optional additional LoRAs to merge (max 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"Your request will cost $0.02 per image for 480p or $0.03 per image for 720p.","published_at":"2025-11-21T23:29:01.055000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/lOE5FD0ts-9zPSD2B53yx_a7709febfd5748f18cb6fab03d071ab1.jpg","title":"Chrono Edit Lora Gallery"},{"category":"image-to-image","description":"Upscales and cleans up the image.","endpoint_id":"fal-ai/chrono-edit-lora-gallery/upscaler","family":"","inputs":[{"default":null,"description":"The image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":2,"description":"Target scale factor for the output resolution.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":1,"description":"The guidance scale for the inference.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":30,"description":"Number of inference steps for the upscaling pass.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The scale factor for the LoRA adapter.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The seed for the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the output image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"Optional additional LoRAs to merge (max 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"Your request will cost $0.02 per image for 480p or $0.03 per image for 720p.","published_at":"2025-11-21T23:13:05.893000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/gRS5bsrx2k_1RwNvQR4DV_4dbd7aad81e44b36af16c01a38fda769.jpg","title":"Chrono Edit Lora Gallery"},{"category":"image-to-image","description":"Clarity upscaler for upscaling images with high very fidelity.","endpoint_id":"fal-ai/clarity-upscaler","family":"Clarity","inputs":[{"default":null,"description":"The URL of the image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"masterpiece, best quality, highres","description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":2,"description":"The upscale factor","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":"(worst quality, low quality, normal quality:2)","description":"The negative prompt to use. Use it to address details that you don't want in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.35,"description":"The creativity of the model. The higher the creativity, the more the model will deviate from the prompt.\n            Refers to the denoise strength of the sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"creativity","required":false,"type":"number"},{"default":0.6,"description":"The resemblance of the upscaled image to the original image. The higher the resemblance, the more the model will try to keep the original image.\n            Refers to the strength of the ControlNet.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"resemblance","required":false,"type":"number"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":18,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Clarity AI","output_kind":"image","output_props":["image","timings","seed"],"pricing":"","published_at":"2024-02-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/controlnet-tile-upscaler.webp","title":"Clarity Upscaler"},{"category":"image-to-image","description":"Fix distorted or blurred photos of people with CodeFormer.","endpoint_id":"fal-ai/codeformer","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.5,"description":"Weight of the fidelity factor.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fidelity","required":false,"type":"number"},{"default":2,"description":"Upscaling factor","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":false,"description":"Should faces etc should be aligned.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aligned","required":false,"type":"boolean"},{"default":false,"description":"Should only center face be restored","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"only_center_face","required":false,"type":"boolean"},{"default":true,"description":"Should faces be upscaled","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_upscale","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2025-01-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/code_thumbnail.webp","title":"CodeFormer"},{"category":"text-to-video","description":"Generate videos from prompts using CogVideoX-5B","endpoint_id":"fal-ai/cogvideox-5b","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":480,"width":720},"description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to generate video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"The LoRAs to use for the image generation. We currently support one lora.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related video to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Use RIFE for video interpolation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_rife","required":false,"type":"boolean"},{"default":16,"description":"The target FPS of the video","enum":null,"is_list":false,"max":32,"media_kind":null,"min":4,"multiline":false,"name":"export_fps","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["seed","timings","video","prompt"],"pricing":"","published_at":"2025-01-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","title":"CogVideoX-5B"},{"category":"image-to-video","description":"Generate videos from images and prompts using CogVideoX-5B","endpoint_id":"fal-ai/cogvideox-5b/image-to-video","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":480,"width":720},"description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to generate video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"The LoRAs to use for the image generation. We currently support one lora.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related video to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Use RIFE for video interpolation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_rife","required":false,"type":"boolean"},{"default":16,"description":"The target FPS of the video","enum":null,"is_list":false,"max":32,"media_kind":null,"min":4,"multiline":false,"name":"export_fps","required":false,"type":"integer"},{"default":null,"description":"The URL to the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"video","output_props":["seed","timings","video","prompt"],"pricing":"","published_at":"2024-10-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","title":"CogVideoX-5B"},{"category":"video-to-video","description":"Generate videos from videos and prompts using CogVideoX-5B","endpoint_id":"fal-ai/cogvideox-5b/video-to-video","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":{"height":480,"width":720},"description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to generate video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"The LoRAs to use for the image generation. We currently support one lora.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related video to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Use RIFE for video interpolation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_rife","required":false,"type":"boolean"},{"default":16,"description":"The target FPS of the video","enum":null,"is_list":false,"max":32,"media_kind":null,"min":4,"multiline":false,"name":"export_fps","required":false,"type":"integer"},{"default":null,"description":"The video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":0.8,"description":"The strength to use for Video to Video.  1.0 completely remakes the video while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["seed","timings","video","prompt"],"pricing":"","published_at":"2024-10-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","title":"CogVideoX-5B"},{"category":"text-to-image","description":"Generate high quality images from text prompts using CogView4. Longer text prompts will result in better quality images.","endpoint_id":"fal-ai/cogview4","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","prompt","images","timings","has_nsfw_concepts"],"pricing":"","published_at":"2025-03-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/CogView4/CogView4.webp","title":"CogView"},{"category":"speech-to-text","description":"Cohere Transcribe turns your business audio into accurate text, ready for search, analytics, and automation","endpoint_id":"fal-ai/cohere-transcribe","family":"Cohere","inputs":[{"default":null,"description":"URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, flac.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"en","description":"Language of the audio (ISO 639-1 code). Supported: en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar.","enum":["en","fr","de","it","es","pt","el","nl","pl","zh","ja","ko","vi","ar"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":true,"description":"Whether to include punctuation and capitalization in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"punctuation","required":false,"type":"boolean"},{"default":256,"description":"Maximum number of tokens to generate per audio chunk.","enum":null,"is_list":false,"max":1014,"media_kind":null,"min":1,"multiline":false,"name":"max_new_tokens","required":false,"type":"integer"}],"lab":"Cohere","output_kind":"json","output_props":["text","timings"],"pricing":"","published_at":"2026-04-22T17:31:46.632000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a974bf5/gs1fpTrvtdkrKcBDh2gS8_ac4876872fb34e42a438031bb4fcdd00.jpg","title":"Cohere Transcribe"},{"category":"image-to-image","description":"ControlLight is a LoRA fine-tune of FLUX.2 [klein] 9B that enhances low-light images while preserving scene structure and fine details, with a single alpha parameter that gives continuous control over enhancement strength from subtle to full brightening.","endpoint_id":"fal-ai/control-light","family":"","inputs":[{"default":null,"description":"URL of the image to enhance.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.75,"description":"Strength of the lighting enhancement (LoRA adapter scale). 0.0 leaves the image essentially untouched; 1.0 applies the strongest exposure lift the LoRA was trained for.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"lighting_level","required":false,"type":"number"},{"default":"Enhance this low-light image by lifting exposure and recovering visible details while preserving identity, geometry, atmosphere, natural colors, and avoiding halos, noise, over-sharpening, or overexposure.","description":"Restoration prompt fed to FLUX.2 [klein].","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducible generation. If not set, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable the safety checker for the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"Output image format.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":4,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-05-27T16:24:37.692000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9be8bb/8dTehLaCr78bz4vpkcZhb_a5bf209765d449658613b94c03976271.jpg","title":"ControlLight"},{"category":"video-to-video","description":"Foley Control is a video-to-audio model that automatically generates synchronized sound effects for videos, using text prompts to shape the type of sound while matching the timing and action on screen.","endpoint_id":"fal-ai/controlfoley","family":"","inputs":[{"default":null,"description":"URL of the video to generate synchronized audio for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional text prompt describing the desired audio. When combined with the video it provides text-controlled video-to-audio (TC-V2A) generation; leave empty for pure video-to-audio (V2A).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"Negative text prompt — describe audio characteristics to avoid.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Optional URL to a 2-4 second reference audio clip whose timbre should be transferred to the generated audio (AC-V2A mode). Audio shorter than 2s is zero-padded; longer is truncated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"reference_audio_url","required":false,"type":"string"},{"default":8,"description":"Target audio duration in seconds. Truncated to source video length when shorter.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":25,"description":"Number of flow-matching ODE steps.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4.5,"description":"Classifier-free guidance strength.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"When True, disables the CLIP visual stream (text-driven mode).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mask_away_clip","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If null, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["seed","audio","video"],"pricing":"Your request will cost $0.002 per second of generated audio.","published_at":"2026-05-05T21:07:18.484000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9908e8/x9i4LkzQ7DMsVA9iePCb2_cc9817ab721c496ca27270816c63462d.jpg","title":"Controlfoley"},{"category":"text-to-video","description":"Generate video from text and videos using NVIDIA's 2B Cosmos Distilled Model","endpoint_id":"fal-ai/cosmos-predict-2.5/distilled/text-to-video","family":"Cosmos","inputs":[{"default":null,"description":"The text prompt describing the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality.","description":"A negative prompt to guide generation away from undesired content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":93,"description":"Number of frames to generate. Must be between 9 and 93.","enum":null,"is_list":false,"max":93,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":10,"description":"Number of denoising steps. Distilled model works well with fewer steps.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"X264 (.mp4)","description":"The format of the output video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"}],"lab":"NVIDIA","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.08 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)","published_at":"2026-02-24T20:05:10.049000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8fcd34/55UUeIF8a-m4smQXoKCjL_fd4ca83217174939851697df18067550.jpg","title":"Cosmos Predict 2.5 2B Distilled"},{"category":"image-to-video","description":"Generate video from text and images using NVIDIA's 2B Cosmos Post-Trained Model","endpoint_id":"fal-ai/cosmos-predict-2.5/image-to-video","family":"Cosmos","inputs":[{"default":null,"description":"The text prompt describing the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality.","description":"A negative prompt to guide generation away from undesired content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":93,"description":"Number of frames to generate. Must be between 9 and 93.","enum":null,"is_list":false,"max":93,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":35,"description":"Number of denoising steps. More steps yield higher quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values increase prompt adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"X264 (.mp4)","description":"The format of the output video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":null,"description":"URL of the input image to use as first frame.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"NVIDIA","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)","published_at":"2026-02-24T20:00:23.313000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8fcd1d/bqbrB-KoKCNBQG4jEOeZm_ee4d331bf9504f38b7d2ebd823275578.jpg","title":"Cosmos Predict 2.5 2B"},{"category":"text-to-video","description":"Generate video from text using NVIDIA's 2B Cosmos Post-Trained Model","endpoint_id":"fal-ai/cosmos-predict-2.5/text-to-video","family":"Cosmos","inputs":[{"default":null,"description":"The text prompt describing the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality.","description":"A negative prompt to guide generation away from undesired content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":93,"description":"Number of frames to generate. Must be between 9 and 93.","enum":null,"is_list":false,"max":93,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":35,"description":"Number of denoising steps. More steps yield higher quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values increase prompt adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"X264 (.mp4)","description":"The format of the output video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"}],"lab":"NVIDIA","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)","published_at":"2026-02-24T19:58:26.642000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8fccfa/eYc-U5ezUgUhzx9Bw5rTM_8167b40fbaa04a2594d281b7fffcea68.jpg","title":"Cosmos Predict 2.5 2B"},{"category":"video-to-video","description":"Generate video from text and videos using NVIDIA's 2B Cosmos Post-Trained Model","endpoint_id":"fal-ai/cosmos-predict-2.5/video-to-video","family":"","inputs":[{"default":null,"description":"The text prompt describing the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality.","description":"A negative prompt to guide generation away from undesired content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":93,"description":"Number of frames to generate. Must be between 9 and 93.","enum":null,"is_list":false,"max":93,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":35,"description":"Number of denoising steps. More steps yield higher quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values increase prompt adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"X264 (.mp4)","description":"The format of the output video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":null,"description":"URL of the input video to use as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)","published_at":"2026-02-24T20:02:15.958000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8fcd29/hO5Q0Al6eZQGB85t9HxHH_5ee646070ef94b74a8fa8a3f8d4164c2.jpg","title":"Cosmos Predict 2.5 2B"},{"category":"image-to-video","description":"Generate high fidelity, studio quality videos of your avatar speaking or singing using the Aurora from Creatify team!","endpoint_id":"fal-ai/creatify/aurora","family":"Aurora","inputs":[{"default":null,"description":"The URL of the image file to be used for video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file to be used for video generation.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"A text prompt to guide the video generation process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"Guidance scale to be used for text prompt adherence.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"Guidance scale to be used for audio adherence.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"audio_guidance_scale","required":false,"type":"number"},{"default":"720p","description":"The resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"Creatify AI","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.07 per video second for 480p, $0.14 per video second for 720p generation. Video seconds will be rounded upwards, meaning that a generation with an output video of 9.4 seconds will be billed as a 10 second video.","published_at":"2025-12-11T16:16:44.429000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85dac5/xLlxwj9XXOpVjGF9iUvla_d44dd53425ac4f94911ec73fa6119fc8.jpg","title":"Creatify Aurora"},{"category":"image-to-image","description":"Create creative upscaled images.","endpoint_id":"fal-ai/creative-upscaler","family":"","inputs":[{"default":"SD_1_5","description":"The type of model to use for the upscaling. Default is SD_1_5","enum":["SD_1_5","SDXL"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":false,"type":"enum"},{"default":null,"description":"The image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results. If no prompt is provide BLIP2 will be used to generate a prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":2,"description":"The scale of the output image. The higher the scale, the bigger the output image will be.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":1,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":0.5,"description":"How much the output can deviate from the original","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"creativity","required":false,"type":"number"},{"default":1,"description":"How much detail to add","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"detail","required":false,"type":"number"},{"default":0.25,"description":"How much to preserve the shape of the original image","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"shape_preservation","required":false,"type":"number"},{"default":" high quality, highly detailed, high resolution, sharp","description":"The suffix to add to the prompt. This is useful to add a common ending to all prompts such as 'high quality' etc or embedding tokens.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt_suffix","required":false,"type":"string"},{"default":"blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":20,"description":"The number of inference steps to use for generating the image. The more steps\n            the better the image will be but it will also take longer to generate.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"If set to true, the resulting image will be checked whether it includes any\n            potentially unsafe content. If it does, it will be replaced with a black\n            image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checks","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the image will not be processed by the CCSR model before\n            being processed by the creativity model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"skip_ccsr","required":false,"type":"boolean"},{"default":false,"description":"Allow for large uploads that could take a very long time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"override_size_limits","required":false,"type":"boolean"},{"default":null,"description":"The URL to the base model to use for the upscaling","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"base_model_url","required":false,"type":"string"},{"default":null,"description":"The URL to the additional LORA model to use for the upscaling. Default is None","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"additional_lora_url","required":false,"type":"string"},{"default":1,"description":"The scale of the additional LORA model to use for the upscaling. Default is 1.0","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"additional_lora_scale","required":false,"type":"number"},{"default":null,"description":"The URL to the additional embeddings to use for the upscaling. Default is None","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"additional_embedding_url","required":false,"type":"string"}],"lab":"","output_kind":"image","output_props":["image","seed"],"pricing":"","published_at":"2024-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/creative-upscaler.webp?v=3","title":"Creative Upscaler"},{"category":"text-to-audio","description":"CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.","endpoint_id":"fal-ai/csm-1b","family":"","inputs":[{"default":null,"description":"The text to generate an audio from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scene","required":true,"type":"json"},{"default":null,"description":"The context to generate an audio from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"context","required":false,"type":"json"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-03-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/csm.jpeg","title":"CSM-1B"},{"category":"image-to-video","description":"Expressive facial performance, natural speech-expression coordination, realistic body motion, and accurate audio-video synchronization with DaVinci-MagiHuman model","endpoint_id":"fal-ai/davinci-magihuman","family":"","inputs":[{"default":null,"description":"Text prompt describing the desired video content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the reference image for image-to-video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of the driving audio for lipsync mode. If omitted, audio is generated from the prompt.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":5,"description":"Duration of the generated video in seconds.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"256p","description":"Output resolution. '256p' uses the official base-model 448x256 path. '1080p' uses the official base + 1080p super-resolution pipeline. '540p' and '720p' reuse that sharper 1080p SR path and downsample to the requested output size.","enum":["256p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Number of denoising steps. Defaults to 8 for 256p and 32 for 540p/720p/1080p (base + SR).","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If enabled, runs safety checks on the prompt and input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2026-03-25T22:25:33.378000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a93a33a/pmKu_XIgnIr5iks3pT5-8_4843332a93674340ab52144e2d533c1e.jpg","title":"Davinci Magihuman"},{"category":"image-to-image","description":"Bring colors into old or new black and white photos with DDColor.","endpoint_id":"fal-ai/ddcolor","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"seed to be used for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-02-26T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ddcolor.webp","title":"DDColor"},{"category":"audio-to-audio","description":"Enhance speech audio by removing background noise and upsampling to 48KHz","endpoint_id":"fal-ai/deepfilternet3","family":"","inputs":[{"default":null,"description":"The URL of the audio to enhance.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"mp3","description":"The format for the output audio.","enum":["mp3","aac","m4a","ogg","opus","flac","wav"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_format","required":false,"type":"enum"},{"default":"192k","description":"The bitrate of the output audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bitrate","required":false,"type":"string"}],"lab":"","output_kind":"json","output_props":["timings","audio_file"],"pricing":"","published_at":"2026-01-07T23:34:22.008000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a897e1b/SwkqYGPNn2Yyk6Cc-BBvO_a988f255be3a41c0a47b5cdc3568453c.jpg","title":"DeepFilterNet 3"},{"category":"audio-to-audio","description":"SOTA stemming model for voice, drums, bass, guitar and more.","endpoint_id":"fal-ai/demucs","family":"","inputs":[{"default":null,"description":"URL of the audio file to separate into stems","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"htdemucs_6s","description":"Demucs model to use for separation","enum":["htdemucs","htdemucs_ft","htdemucs_6s","hdemucs_mmi","mdx","mdx_extra","mdx_q","mdx_extra_q"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":["vocals","drums","bass","other","guitar","piano"],"description":"Specific stems to extract. If None, extracts all available stems. Available stems depend on model: vocals, drums, bass, other, guitar, piano (for 6s model)","enum":["vocals","drums","bass","other","guitar","piano"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"stems","required":false,"type":"enum"},{"default":null,"description":"Length in seconds of each segment for processing. Smaller values use less memory but may reduce quality. Default is model-specific.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segment_length","required":false,"type":"integer"},{"default":1,"description":"Number of random shifts for equivariant stabilization. Higher values improve quality but increase processing time.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shifts","required":false,"type":"integer"},{"default":0.25,"description":"Overlap between segments (0.0 to 1.0). Higher values may improve quality but increase processing time.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"overlap","required":false,"type":"number"},{"default":"mp3","description":"Output audio format for the separated stems","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"json","output_props":["vocals","bass","piano","drums","other","guitar"],"pricing":"","published_at":"2025-10-27T21:40:53.677000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/WAcACXLL5-atiw1MGvH4g_7cb10ff246844b9c9298bbe98e431df7.jpg","title":"Demucs"},{"category":"video-to-video","description":"Generates depth maps from video using Video Depth Anything (CVPR 2025). Produces per-frame depth estimation with temporal consistency across frames. Supports 3 model sizes (Small, Base, Large), 5 colormaps including grayscale, side-by-side comparison with the original video, and raw depth export as .npz. Useful for 3D reconstruction, video effects, compositing, and scene understanding.","endpoint_id":"fal-ai/depth-anything-video","family":"","inputs":[{"default":null,"description":"URL of the input video to estimate depth for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"VDA-Large","description":"Depth estimation model size. VDA-Large = best quality, VDA-Small = fastest.","enum":["VDA-Small","VDA-Base","VDA-Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":"grayscale","description":"Colormap for depth visualization. 'turbo' (recommended) shows near=warm, far=cool. 'grayscale' for raw normalized depth. 'inferno'/'magma' for perceptually uniform. 'viridis' for colorblind-friendly.","enum":["grayscale","turbo","inferno","magma","viridis"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colormap","required":false,"type":"enum"},{"default":"auto","description":"Output resolution. 'auto' preserves input (max 1080p). Options: 'auto', '360p', '480p', '720p', '1080p'.","enum":["auto","360p","480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Max frames to process (max 1800). None = up to 1800.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"max_frames","required":false,"type":"integer"},{"default":null,"description":"Output video FPS. None = same as input.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"output_fps","required":false,"type":"number"},{"default":false,"description":"Output original | depth comparison video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"side_by_side","required":false,"type":"boolean"},{"default":false,"description":"Export raw float32 depths as .npz file with: 'depths' [N,H,W], 'min_depth', 'max_depth', 'fps', 'model', 'shape'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_raw_depths","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","raw_depths"],"pricing":"Your request will cost $0.04 per second of video.","published_at":"2026-03-02T20:46:14.255000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9098ac/VPiI1T3l10kKkmCWxcNSH_e3a99777f1b84afbaf4f7147a24a8221.jpg","title":"Depth Anything Video"},{"category":"text-to-speech","description":"Dia directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing.","endpoint_id":"fal-ai/dia-tts","family":"","inputs":[{"default":null,"description":"The text to be converted to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-04-22T17:25:11.601000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound.jpg","title":"Dia"},{"category":"audio-to-audio","description":"Clone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/dia-tts/voice-clone","family":"","inputs":[{"default":null,"description":"The text to be converted to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-04-22T23:43:19.478000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-4.jpg","title":"Dia Tts"},{"category":"text-to-audio","description":"DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.","endpoint_id":"fal-ai/diffrhythm","family":"","inputs":[{"default":null,"description":"The prompt to generate the song from. Must have two sections. Sections start with either [chorus] or a [verse].","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"lyrics","required":true,"type":"string"},{"default":null,"description":"The URL of the reference audio to use for the music generation.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"reference_audio_url","required":false,"type":"string"},{"default":null,"description":"The style prompt to use for the music generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_prompt","required":false,"type":"string"},{"default":"95s","description":"The duration of the music to generate.","enum":["95s","285s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"music_duration","required":false,"type":"enum"},{"default":4,"description":"The CFG strength to use for the music generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"cfg_strength","required":false,"type":"number"},{"default":"euler","description":"The scheduler to use for the music generation.","enum":["euler","midpoint","rk4","implicit_adams"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":32,"description":"The number of inference steps to use for the music generation.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.01 per 10 second of generated audio. For $1 you can run generate 1000s of music from lyrics.","published_at":"2025-03-04T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d5/RI4o31rYekV5K2GHIYOeI_4bbU0wiJ.png","title":"DiffRhythm: Lyrics to Song"},{"category":"image-to-image","description":"Enhance low-resolution, blur, shadowed documents with the superior quality of docres for sharper, clearer results.","endpoint_id":"fal-ai/docres","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Task to perform","enum":["deshadowing","appearance","deblurring","binarization"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"task","required":true,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-03-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/docres.webp","title":"DocRes"},{"category":"image-to-image","description":"Enhance wraped, folded documents with the superior quality of docres for sharper, clearer results.","endpoint_id":"fal-ai/docres/dewarp","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-03-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/docres.webp","title":"DocRes-dewarp"},{"category":"image-to-image","description":"Upscale your images with DRCT-Super-Resolution.","endpoint_id":"fal-ai/drct-super-resolution","family":"","inputs":[{"default":null,"description":"URL of the image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":4,"description":"Upscaling factor.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_factor","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-02-24T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/drct.webp","title":"DRCT-Super-Resolution"},{"category":"image-to-image","description":"DreamOmni2 is a unified multimodal model for text and image guided image editing.","endpoint_id":"fal-ai/dreamomni2/edit","family":"","inputs":[{"default":null,"description":"List of URLs of input images for editing.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.05 per image. For $1.00, you can run this model 20 times.","published_at":"2025-10-10T22:13:05.899000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/c4tQDAqMyMQ_6-LNFzCyj_13c4f35481fc4ebaaf4fddf9a5d86ddc.jpg","title":"DreamOmni2"},{"category":"text-to-image","description":"Dreamshaper model.","endpoint_id":"fal-ai/dreamshaper","family":"","inputs":[{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D ,3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)","description":"The negative prompt to use. Use it to address details that you don't want in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":{"height":1024,"width":1024},"description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-04-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/dreamshaper.jpeg","title":"Dreamshaper"},{"category":"image-to-image","description":"Predict poses from images.","endpoint_id":"fal-ai/dwpose","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"body-pose","description":"Mode of drawing the pose on the image. Options are: 'full-pose', 'body-pose', 'face-pose', 'hand-pose', 'face-hand-mask', 'face-mask', 'hand-mask'.","enum":["full-pose","body-pose","face-pose","hand-pose","face-hand-mask","face-mask","hand-mask"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"draw_mode","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.0006 per compute second.","published_at":"2024-06-01T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/dwpose.jpeg","title":"DWPose Pose Prediction"},{"category":"video-to-video","description":"Predict poses from videos.","endpoint_id":"fal-ai/dwpose/video","family":"","inputs":[{"default":null,"description":"URL of video to be used for pose estimation","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"body-pose","description":"Mode of drawing the pose on the video. Options are: 'full-pose', 'body-pose', 'face-pose', 'hand-pose', 'face-hand-mask', 'face-mask', 'hand-mask'.","enum":["full-pose","body-pose","face-pose","hand-pose","face-hand-mask","face-mask","hand-mask"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"draw_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.0006 per compute second.","published_at":"2025-06-15T05:20:30.597000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/dwpose.jpeg","title":"DWPose Pose Prediction"},{"category":"audio-to-video","description":"EchoMimic V3 generates a talking avatar model from a picture, audio and text prompt.","endpoint_id":"fal-ai/echomimic-v3","family":"","inputs":[{"default":null,"description":"The URL of the image to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate at once.","enum":null,"is_list":false,"max":161,"media_kind":null,"min":49,"multiline":false,"name":"num_frames_per_generation","required":false,"type":"integer"},{"default":4.5,"description":"The guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2.5,"description":"The audio guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.20 per generated second of video, based on the length of the input audio. For example, a 5-second video will cost $1.00.","published_at":"2025-08-13T02:36:00.352000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939d/aOd4Sf7zAVzMB2Q_Qndja_9W8NytiM.png","title":"EchoMimic V3"},{"category":"video-to-video","description":"Edit videos using instruction-based prompting using Editto model!","endpoint_id":"fal-ai/editto","family":"","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed","frames_zip","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-11-12T11:40:08.233000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/W64UaJMRRXDKIQKOyArBO_27c8587eded040778cd5c777b9f71035.jpg","title":"Editto"},{"category":"audio-to-audio","description":"Isolate audio tracks using ElevenLabs advanced audio isolation technology.","endpoint_id":"fal-ai/elevenlabs/audio-isolation","family":"","inputs":[{"default":null,"description":"URL of the audio file to isolate voice from","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"Video file to use for audio isolation. Either `audio_url` or `video_url` must be provided.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":false,"type":"string"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio","timestamps"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","title":"ElevenLabs Audio Isolation"},{"category":"audio-to-video","description":"Generate dubbed videos or audios using ElevenLabs Dubbing feature!","endpoint_id":"fal-ai/elevenlabs/dubbing","family":"","inputs":[{"default":null,"description":"URL of the audio file to dub. Either audio_url or video_url must be provided.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"URL of the video file to dub. Either audio_url or video_url must be provided. If both are provided, video_url takes priority.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":false,"type":"string"},{"default":null,"description":"Target language code for dubbing (ISO 639-1)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_lang","required":true,"type":"string"},{"default":null,"description":"Source language code. If not provided, will be auto-detected.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"source_lang","required":false,"type":"string"},{"default":null,"description":"Number of speakers in the audio. If not provided, will be auto-detected.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_speakers","required":false,"type":"integer"},{"default":true,"description":"Whether to use the highest resolution for dubbing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"highest_resolution","required":false,"type":"boolean"}],"lab":"ElevenLabs","output_kind":"video","output_props":["video","target_lang"],"pricing":"Your request will cost $0.9 per minute. The calculation will be based on the closest minute after rounding upwards.","published_at":"2026-01-14T14:41:55.680000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a5dca/J7G08QXS3XtfD7m-9dY4g_f57272f4c9cc4b0fa9363b581808c559.jpg","title":"ElevenLabs Dubbing"},{"category":"text-to-audio","description":"Generate high quality, realistic music with fine controls using Elevenlabs Music!","endpoint_id":"fal-ai/elevenlabs/music","family":"","inputs":[{"default":null,"description":"The text prompt describing the music to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The composition plan for the music","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"composition_plan","required":false,"type":"json"},{"default":null,"description":"The length of the song to generate in milliseconds. Used only in conjunction with prompt. Must be between 3000ms and 600000ms. Optional - if not provided, the model will choose a length based on the prompt.","enum":null,"is_list":false,"max":600000,"media_kind":null,"min":3000,"multiline":false,"name":"music_length_ms","required":false,"type":"integer"},{"default":false,"description":"If true, guarantees that the generated song will be instrumental. If false, the song may or may not be instrumental depending on the prompt. Can only be used with prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"force_instrumental","required":false,"type":"boolean"},{"default":true,"description":"Controls how strictly section durations in the composition_plan are enforced. It will only have an effect if it is used with composition_plan. When set to true, the model will precisely respect each section's duration_ms from the plan. When set to false, the model may adjust individual section durations which will generally lead to better generation quality and improved latency, while always preserving the total song duration from the plan.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"respect_sections_durations","required":false,"type":"boolean"},{"default":"mp3_44100_128","description":"Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.","enum":["mp3_22050_32","mp3_44100_32","mp3_44100_64","mp3_44100_96","mp3_44100_128","mp3_44100_192","pcm_8000","pcm_16000","pcm_22050","pcm_24000","pcm_44100","pcm_48000","ulaw_8000","alaw_8000","opus_48000_32","opus_48000_64","opus_48000_96","opus_48000_128","opus_48000_192"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.8 per output audio minute. The audio will be rounded up to the closest minute. For instance, a generation with 30 seconds output will be billed as 1 minute.","published_at":"2025-12-22T15:22:56.999000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875694/SZffdb8layV90JxfN5fkP_d2048a658d9e4dc9973598f3542833a0.jpg","title":"Elevenlabs Music"},{"category":"text-to-audio","description":"Generate sound effects using ElevenLabs advanced sound effects model.","endpoint_id":"fal-ai/elevenlabs/sound-effects/v2","family":"","inputs":[{"default":null,"description":"The text describing the sound effect to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Duration in seconds (0.5-22). If None, optimal duration will be determined from prompt.","enum":null,"is_list":false,"max":22,"media_kind":null,"min":0.5,"multiline":false,"name":"duration_seconds","required":false,"type":"number"},{"default":0.3,"description":"How closely to follow the prompt (0-1). Higher values mean less variation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"prompt_influence","required":false,"type":"number"},{"default":"mp3_44100_128","description":"Output format of the generated audio. Formatted as codec_sample_rate_bitrate.","enum":["mp3_22050_32","mp3_44100_32","mp3_44100_64","mp3_44100_96","mp3_44100_128","mp3_44100_192","pcm_8000","pcm_16000","pcm_22050","pcm_24000","pcm_44100","pcm_48000","ulaw_8000","alaw_8000","opus_48000_32","opus_48000_64","opus_48000_96","opus_48000_128","opus_48000_192"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Whether to create a sound effect that loops smoothly.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-09-02T20:11:50.270000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","title":"Elevenlabs Sound Effects V2"},{"category":"speech-to-text","description":"Generate text from speech using ElevenLabs advanced speech-to-text model.","endpoint_id":"fal-ai/elevenlabs/speech-to-text","family":"","inputs":[{"default":null,"description":"URL of the audio file to transcribe","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Language code of the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_code","required":false,"type":"string"},{"default":true,"description":"Tag audio events like laughter, applause, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tag_audio_events","required":false,"type":"boolean"},{"default":true,"description":"Whether to annotate who is speaking","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"diarize","required":false,"type":"boolean"}],"lab":"ElevenLabs","output_kind":"json","output_props":["words","text","language_code","language_probability"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","title":"ElevenLabs Speech to Text"},{"category":"speech-to-text","description":"Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!","endpoint_id":"fal-ai/elevenlabs/speech-to-text/scribe-v2","family":"","inputs":[{"default":null,"description":"URL of the audio file to transcribe","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Language code of the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_code","required":false,"type":"string"},{"default":true,"description":"Tag audio events like laughter, applause, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tag_audio_events","required":false,"type":"boolean"},{"default":true,"description":"Whether to annotate who is speaking","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"diarize","required":false,"type":"boolean"},{"default":[],"description":"Words or sentences to bias the model towards transcribing. Up to 100 keyterms, max 50 characters each. Adds 30% premium over base transcription price.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"keyterms","required":false,"type":"string"}],"lab":"ElevenLabs","output_kind":"json","output_props":["words","text","language_code","language_probability"],"pricing":"Your request will cost $0.008 per input audio minutes. If keyterm is used, you request will cost %30 more.","published_at":"2026-01-14T14:30:10.342000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a5d77/3XtHpcC46Sg0ItPRjB6Uk_82a3a831177745b38f925d35a7b5ed66.jpg","title":"ElevenLabs Speech to Text - Scribe V2"},{"category":"text-to-audio","description":"Generate realistic audio dialogues using Eleven-v3 from ElevenLabs.","endpoint_id":"fal-ai/elevenlabs/text-to-dialogue/eleven-v3","family":"","inputs":[{"default":null,"description":"A list of dialogue inputs, each containing text and a voice ID which will be converted into speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inputs","required":true,"type":"json"},{"default":null,"description":"Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. Must be one of 0.0, 0.5, 1.0, else it will be rounded to the nearest value.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"stability","required":false,"type":"number"},{"default":null,"description":"This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_speaker_boost","required":false,"type":"boolean"},{"default":"[]","description":"A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dictionary_locators","required":false,"type":"json"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"language_code","required":false,"type":"string"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio","seed"],"pricing":"","published_at":"2025-09-09T12:30:10.005000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922b/QjrjK2Y_vUdOMv3wbQutK_lvizVaD6.png","title":"Elevenlabs"},{"category":"text-to-audio","description":"Generate text-to-speech audio using Eleven-v3 from ElevenLabs.","endpoint_id":"fal-ai/elevenlabs/tts/eleven-v3","family":"","inputs":[{"default":null,"description":"The text to convert to speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"Rachel","description":"The voice to use for speech generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"string"},{"default":0.5,"description":"Voice stability (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"stability","required":false,"type":"number"},{"default":false,"description":"Whether to return timestamps for each word in the generated speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"timestamps","required":false,"type":"boolean"},{"default":null,"description":"Language code (ISO 639-1) used to enforce a language for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_code","required":false,"type":"string"},{"default":"auto","description":"This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.","enum":["auto","on","off"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_text_normalization","required":false,"type":"enum"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio","timestamps"],"pricing":"","published_at":"2025-08-20T19:22:36.745000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91a8/oTkavdBnqhpPaT65B3FG8_euEcQphX.png","title":"Elevenlabs Tts Eleven V3"},{"category":"text-to-audio","description":"Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.","endpoint_id":"fal-ai/elevenlabs/tts/multilingual-v2","family":"","inputs":[{"default":null,"description":"The text to convert to speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"Rachel","description":"The voice to use for speech generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"string"},{"default":0.5,"description":"Voice stability (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"stability","required":false,"type":"number"},{"default":0.75,"description":"Similarity boost (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"similarity_boost","required":false,"type":"number"},{"default":0,"description":"Style exaggeration (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"style","required":false,"type":"number"},{"default":1,"description":"Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality.","enum":null,"is_list":false,"max":1.2,"media_kind":null,"min":0.7,"multiline":false,"name":"speed","required":false,"type":"number"},{"default":false,"description":"Whether to return timestamps for each word in the generated speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"timestamps","required":false,"type":"boolean"},{"default":null,"description":"The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"previous_text","required":false,"type":"string"},{"default":null,"description":"The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"next_text","required":false,"type":"string"},{"default":null,"description":"Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"language_code","required":false,"type":"string"},{"default":"auto","description":"This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.","enum":["auto","on","off"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_text_normalization","required":false,"type":"enum"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio","timestamps"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b4/QzoZAeoc-h1TLhttOaE7K_jZHvV4ZG.png","title":"ElevenLabs TTS Multilingual v2"},{"category":"text-to-speech","description":"Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.","endpoint_id":"fal-ai/elevenlabs/tts/turbo-v2.5","family":"","inputs":[{"default":null,"description":"The text to convert to speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"Rachel","description":"The voice to use for speech generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"string"},{"default":0.5,"description":"Voice stability (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"stability","required":false,"type":"number"},{"default":0.75,"description":"Similarity boost (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"similarity_boost","required":false,"type":"number"},{"default":0,"description":"Style exaggeration (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"style","required":false,"type":"number"},{"default":1,"description":"Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality.","enum":null,"is_list":false,"max":1.2,"media_kind":null,"min":0.7,"multiline":false,"name":"speed","required":false,"type":"number"},{"default":false,"description":"Whether to return timestamps for each word in the generated speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"timestamps","required":false,"type":"boolean"},{"default":null,"description":"The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"previous_text","required":false,"type":"string"},{"default":null,"description":"The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"next_text","required":false,"type":"string"},{"default":null,"description":"Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"language_code","required":false,"type":"string"},{"default":"auto","description":"This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.","enum":["auto","on","off"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_text_normalization","required":false,"type":"enum"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio","timestamps"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","title":"ElevenLabs TTS Turbo v2.5"},{"category":"audio-to-audio","description":"Change the voices in your audios with voices in ElevenLabs!","endpoint_id":"fal-ai/elevenlabs/voice-changer","family":"","inputs":[{"default":null,"description":"The input audio file","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"Rachel","description":"The voice to use for speech generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"string"},{"default":false,"description":"If set, will remove the background noise from your audio input using our audio isolation model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_background_noise","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"mp3_44100_128","description":"Output format of the generated audio. Formatted as codec_sample_rate_bitrate.","enum":["mp3_22050_32","mp3_44100_32","mp3_44100_64","mp3_44100_96","mp3_44100_128","mp3_44100_192","pcm_8000","pcm_16000","pcm_22050","pcm_24000","pcm_44100","pcm_48000","ulaw_8000","alaw_8000","opus_48000_32","opus_48000_64","opus_48000_96","opus_48000_128","opus_48000_192"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"ElevenLabs","output_kind":"audio","output_props":["audio","seed"],"pricing":"","published_at":"2026-01-14T14:50:03.869000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a5e18/wKI4AAR-ugj6qdI9HH2P5_7696a622ff46451bb8fa7f0a4e54be13.jpg","title":"ElevenLabs Voice Changer"},{"category":"image-to-image","description":"Edit images with a text prompt using Emu 3.5 Image","endpoint_id":"fal-ai/emu-3.5-image/edit-image","family":"","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the output image.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the output image.","enum":["auto","21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The seed for the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"png","description":"The format of the output image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["seed","images"],"pricing":"Your request will cost $0.15 for 480p or $0.30 for 720p.","published_at":"2025-11-01T02:35:16.884000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/tQyERUtskH6UgoJDqvDof_a8481b37918840948487c1ae79050bab.jpg","title":"Emu 3.5 Image"},{"category":"text-to-image","description":"Generate images from text using Emu 3.5 Image","endpoint_id":"fal-ai/emu-3.5-image/text-to-image","family":"","inputs":[{"default":null,"description":"The prompt to create the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the output image.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio of the output image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The seed for the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"png","description":"The format of the output image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","images"],"pricing":"Your request will cost $0.15 for 480p or $0.30 for 720p.","published_at":"2025-11-01T02:28:53.205000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/vIz3smWaozr97-oRkQBRu_de31d4d13d5d47d99814d2afe57cde1f.jpg","title":"Emu 3.5 Image"},{"category":"text-to-image","description":"High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.","endpoint_id":"fal-ai/ernie-image","family":"ERNIE","inputs":[{"default":null,"description":"Text prompt for image generation. Supports English, Chinese, and Japanese.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to guide what should not be in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","square_uhd","portrait_3_2","landscape_3_2","portrait_hd","landscape_hd","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If True, the prompt will be enhanced using an LLM for more detailed results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW safety checking on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Baidu","output_kind":"images","output_props":["prompt","seed","images","timings"],"pricing":"Your request will cost $0.03 per megapixel.","published_at":"2026-04-14T17:01:00.242000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a95b471/zvbvEozhYoL2qgMX2iBvU_e73b2118bfcf46b687ce1983a00479ec.jpg","title":"Ernie Image"},{"category":"training","description":"LoRA trainer for ERNIE-Image, Baidu's powerful 8B-parameter text-to-image model.","endpoint_id":"fal-ai/ernie-image-trainer","family":"ERNIE","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n        The zip should contain pairs of images and corresponding captions.\n\n        The images should be named: ROOT.EXT. For example: 001.jpg\n\n        The corresponding captions should be named: ROOT.txt. For example: 001.txt\n\n        If no text file is provided for an image, the default_caption will be used.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"images_data_url","required":true,"type":"string"},{"default":2000,"description":"Number of steps to train for","enum":null,"is_list":false,"max":40000,"media_kind":null,"min":10,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":0.0005,"description":"Learning rate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"}],"lab":"Baidu","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"Your request will cost $1.2 per 1000-step training run. It scales per step, so a 2000-step training run will cost $2.4.","published_at":"2026-04-15T22:52:57.158000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a966681/ejGe7iNYje2r5ByKNfXQ6_875f9ce867f34603ace1208e9c3ad4fc.jpg","title":"ERNIE-Image Trainer"},{"category":"text-to-image","description":"High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.","endpoint_id":"fal-ai/ernie-image/lora","family":"ERNIE","inputs":[{"default":null,"description":"Text prompt for image generation. Supports English, Chinese, and Japanese.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to guide what should not be in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","square_uhd","portrait_3_2","landscape_3_2","portrait_hd","landscape_hd","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If True, the prompt will be enhanced using an LLM for more detailed results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW safety checking on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Baidu","output_kind":"images","output_props":["prompt","seed","images","timings"],"pricing":"","published_at":"2026-04-16T20:15:03.727000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9686af/VNuveFoGyRlJug1rMRpo5_c43ff9aa0f4f4bce986e7f57209d5750.jpg","title":"Ernie Image Lora"},{"category":"text-to-image","description":"High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.","endpoint_id":"fal-ai/ernie-image/lora/turbo","family":"ERNIE","inputs":[{"default":null,"description":"Text prompt for image generation. Supports English, Chinese, and Japanese.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to guide what should not be in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","square_uhd","portrait_3_2","landscape_3_2","portrait_hd","landscape_hd","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"Number of denoising steps. Turbo model is optimized for 8 steps.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If True, the prompt will be enhanced using an LLM for more detailed results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW safety checking on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Baidu","output_kind":"images","output_props":["prompt","seed","images","timings"],"pricing":"","published_at":"2026-04-16T20:17:14.518000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9686c2/rSdSnH8HzFMhAu06rFVvB_d73cdb88ba4f4f07898b41e75310450a.jpg","title":"Ernie Image Lora Turbo"},{"category":"text-to-image","description":"High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.","endpoint_id":"fal-ai/ernie-image/turbo","family":"ERNIE","inputs":[{"default":null,"description":"Text prompt for image generation. Supports English, Chinese, and Japanese.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to guide what should not be in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","square_uhd","portrait_3_2","landscape_3_2","portrait_hd","landscape_hd","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"Number of denoising steps. Turbo model is optimized for 8 steps.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If True, the prompt will be enhanced using an LLM for more detailed results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW safety checking on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Baidu","output_kind":"images","output_props":["prompt","seed","images","timings"],"pricing":"Your request will cost $0.01 per megapixel.","published_at":"2026-04-14T17:00:39.191000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a96230d/XwYFqTEmEgk-moh6OCFhE_6e06f8f187564c2b952b6d0e058a9203.jpg","title":"Ernie Image Turbo"},{"category":"image-to-image","description":"Upscale images by a given factor.","endpoint_id":"fal-ai/esrgan","family":"Esrgan","inputs":[{"default":null,"description":"Url to input image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":2,"description":"Rescaling factor","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":0,"description":"Tile size. Default is 0, that is no tile. When encountering the out-of-GPU-memory issue, please specify it, e.g., 400 or 200","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tile","required":false,"type":"integer"},{"default":false,"description":"Upscaling a face","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face","required":false,"type":"boolean"},{"default":"RealESRGAN_x4plus","description":"Model to use for upscaling","enum":["RealESRGAN_x4plus","RealESRGAN_x2plus","RealESRGAN_x4plus_anime_6B","RealESRGAN_x4_v3","RealESRGAN_x4_wdn_v3","RealESRGAN_x4_anime_v3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":"png","description":"Output image format (png or jpeg)","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.00111 per compute second","published_at":"2023-10-30T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/esrgan.webp?v=2","title":"Upscale Images"},{"category":"image-to-image","description":"EVF-SAM2 combines natural language understanding with advanced segmentation capabilities, allowing you to precisely mask image regions using intuitive positive and negative text prompts.","endpoint_id":"fal-ai/evf-sam","family":"","inputs":[{"default":null,"description":"The prompt to generate segmentation from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Areas to exclude from segmentation (will be subtracted from prompt results)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"Enable semantic level segmentation for body parts, background or multi objects","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"semantic_type","required":false,"type":"boolean"},{"default":null,"description":"URL of the input image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":true,"description":"Output only the binary mask instead of masked image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mask_only","required":false,"type":"boolean"},{"default":false,"description":"Use GroundingDINO instead of SAM for segmentation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_grounding_dino","required":false,"type":"boolean"},{"default":false,"description":"Invert the mask (background becomes foreground and vice versa)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"revert_mask","required":false,"type":"boolean"},{"default":0,"description":"Apply Gaussian blur to the mask. Value determines kernel size (must be odd number)","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"blur_mask","required":false,"type":"integer"},{"default":0,"description":"Expand/dilate the mask by specified pixels","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"expand_mask","required":false,"type":"integer"},{"default":false,"description":"Fill holes in the mask using morphological operations","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_holes","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-02-26T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/evf-sam2/evf-sam2.webp","title":"EVF-SAM2 Segmentation"},{"category":"text-to-audio","description":"F5 TTS","endpoint_id":"fal-ai/f5-tts","family":"","inputs":[{"default":null,"description":"The text to be converted to speech. Maximum 5000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"gen_text","required":true,"type":"string"},{"default":null,"description":"The URL of the reference audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"ref_audio_url","required":true,"type":"string"},{"default":"","description":"The reference text to be used for TTS. If not provided, an ASR (Automatic Speech Recognition) model will be used to generate the reference text.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"ref_text","required":false,"type":"string"},{"default":null,"description":"The name of the model to be used for TTS.","enum":["F5-TTS","E2-TTS"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":true,"type":"enum"},{"default":true,"description":"Whether to remove the silence from the audio file.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_silence","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["audio_url"],"pricing":"","published_at":"2024-10-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/f5-tts.jpeg","title":"F5 TTS"},{"category":"image-to-image","description":"FASHN v1.5 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.","endpoint_id":"fal-ai/fashn/tryon/v1.5","family":"Tryon 1.5","inputs":[{"default":null,"description":"URL or base64 of the model image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"model_image","required":true,"type":"string"},{"default":null,"description":"URL or base64 of the garment image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"garment_image","required":true,"type":"string"},{"default":"auto","description":"Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment.","enum":["tops","bottoms","one-pieces","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"category","required":false,"type":"enum"},{"default":"balanced","description":"Specifies the mode of operation. 'performance' mode is faster but may sacrifice quality, 'balanced' mode is a balance between speed and quality, and 'quality' mode is slower but produces higher quality results.","enum":["performance","balanced","quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":"auto","description":"Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type.","enum":["auto","model","flat-lay"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"garment_photo_type","required":false,"type":"enum"},{"default":"permissive","description":"Content moderation level for garment images. 'none' disables moderation, 'permissive' blocks only explicit content, 'conservative' also blocks underwear and swimwear.","enum":["none","permissive","conservative"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"moderation_level","required":false,"type":"enum"},{"default":null,"description":"Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":true,"description":"Disables human parsing on the model image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segmentation_free","required":false,"type":"boolean"},{"default":"png","description":"Output format of the generated images. 'png' is highest quality, while 'jpeg' is faster","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Fashn","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-04-21T12:52:40.889000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fashn_wide.webp","title":"FASHN Virtual Try-On V1.5"},{"category":"image-to-image","description":"FASHN v1.6 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 864x1296 resolution from both on-model and flat-lay photo references.","endpoint_id":"fal-ai/fashn/tryon/v1.6","family":"Tryon 1.6","inputs":[{"default":null,"description":"URL or base64 of the model image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"model_image","required":true,"type":"string"},{"default":null,"description":"URL or base64 of the garment image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"garment_image","required":true,"type":"string"},{"default":"auto","description":"Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment.","enum":["tops","bottoms","one-pieces","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"category","required":false,"type":"enum"},{"default":"balanced","description":"Specifies the mode of operation. 'performance' mode is faster but may sacrifice quality, 'balanced' mode is a balance between speed and quality, and 'quality' mode is slower but produces higher quality results.","enum":["performance","balanced","quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":"auto","description":"Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type.","enum":["auto","model","flat-lay"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"garment_photo_type","required":false,"type":"enum"},{"default":"permissive","description":"Content moderation level for garment images. 'none' disables moderation, 'permissive' blocks only explicit content, 'conservative' also blocks underwear and swimwear.","enum":["none","permissive","conservative"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"moderation_level","required":false,"type":"enum"},{"default":null,"description":"Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":true,"description":"Disables human parsing on the model image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segmentation_free","required":false,"type":"boolean"},{"default":"png","description":"Output format of the generated images. 'png' is highest quality, while 'jpeg' is faster","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Fashn","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-06-24T20:58:43.252000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fashn_wide.webp","title":"FASHN Virtual Try-On V1.6"},{"category":"text-to-video","description":"Animate your ideas!","endpoint_id":"fal-ai/fast-animatediff/text-to-video","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the video. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"(bad quality, worst quality:1.2), ugly faces, bad anime","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":16,"description":"The number of frames to generate for the video.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":8,"description":"Number of frames per second to extract from the video.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The motions to apply to the video.","enum":["zoom-out","zoom-in","pan-left","pan-right","tilt-up","tilt-down"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"motions","required":false,"type":"enum"},{"default":"square","description":"The size of the video to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-animatediff-t2v.webp","title":"AnimateDiff"},{"category":"text-to-video","description":"Animate your ideas in lightning speed!","endpoint_id":"fal-ai/fast-animatediff/turbo/text-to-video","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the video. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"(bad quality, worst quality:1.2), ugly faces, bad anime","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":16,"description":"The number of frames to generate for the video.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"The number of inference steps to perform. 4-12 is recommended for turbo mode.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":2,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":8,"description":"Number of frames per second to extract from the video.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":"square","description":"The size of the video to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-animatediff-t2v-turbo.webp","title":"AnimateDiff Turbo"},{"category":"video-to-video","description":"Re-animate your videos in lightning speed!","endpoint_id":"fal-ai/fast-animatediff/turbo/video-to-video","family":"","inputs":[{"default":null,"description":"URL of the video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":3,"description":"The first N number of seconds of video to animate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":2,"multiline":false,"name":"first_n_seconds","required":false,"type":"integer"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"(bad quality, worst quality:1.2), ugly faces, bad anime","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":12,"description":"The number of inference steps to perform. 4-12 is recommended for turbo mode.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":0.7,"description":"The strength of the input video in the final output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":2,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":8,"description":"Number of frames per second to extract from the video.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/animatediff-v2v.gif","title":"AnimateDiff Turbo"},{"category":"video-to-video","description":"Re-animate your videos!","endpoint_id":"fal-ai/fast-animatediff/video-to-video","family":"","inputs":[{"default":null,"description":"URL of the video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":3,"description":"The first N number of seconds of video to animate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":2,"multiline":false,"name":"first_n_seconds","required":false,"type":"integer"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"(bad quality, worst quality:1.2), ugly faces, bad anime","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":0.7,"description":"The strength of the input video in the final output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":8,"description":"Number of frames per second to extract from the video.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The motions to apply to the video.","enum":["zoom-out","zoom-in","pan-left","pan-right","tilt-up","tilt-down"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"motions","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/animatediff-v2v.gif","title":"AnimateDiff"},{"category":"text-to-image","description":"Fooocus extreme speed mode as a standalone app.","endpoint_id":"fal-ai/fast-fooocus-sdxl/image-to-image","family":"","inputs":[{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the prompt image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":true,"description":"If set to true, a smaller model will try to refine the output after it was processed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_refiner","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-03-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/fooocus/fal_ai_fooocus_cyberpunk-city.jpeg","title":"Fooocus"},{"category":"text-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-lcm-diffusion","family":"","inputs":[{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":1.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","prompt","seed"],"pricing":"","published_at":"2024-02-19T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/k0FmsDMVF8mBxb_Xo0Mbv_bHXC3jIr.png","title":"Latent Consistency Models (v1.5/XL)"},{"category":"image-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-lcm-diffusion/image-to-image","family":"","inputs":[{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","prompt","seed"],"pricing":"","published_at":"2024-02-19T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/AcYBaLCnLoACaInPk9cSg_TSGirHMU.png","title":"Latent Consistency Models (v1.5/XL)"},{"category":"image-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-lcm-diffusion/inpainting","family":"","inputs":[{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the mask to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","prompt","seed"],"pricing":"","published_at":"2024-02-19T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9398/yYlp9W2roAtM9J0nx7E3A_Qb77sB1s.png","title":"Latent Consistency Models (v1.5/XL)"},{"category":"text-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-lightning-sdxl","family":"","inputs":[{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"4","description":"The number of inference steps to perform.","enum":["1","2","4","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_inference_steps","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["prompt","seed","has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2024-04-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/stable-diffusion-xl-lightning.webp","title":"Stable Diffusion XL Lightning"},{"category":"image-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-lightning-sdxl/image-to-image","family":"","inputs":[{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"4","description":"The number of inference steps to perform.","enum":["1","2","4","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_inference_steps","required":false,"type":"enum"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["prompt","seed","has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2024-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/stable-diffusion-xl-lightning.webp","title":"Stable Diffusion XL Lightning"},{"category":"image-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-lightning-sdxl/inpainting","family":"","inputs":[{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"4","description":"The number of inference steps to perform.","enum":["1","2","4","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_inference_steps","required":false,"type":"enum"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["prompt","seed","has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2024-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/stable-diffusion-xl-lightning.webp","title":"Stable Diffusion XL Lightning"},{"category":"text-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-sdxl","family":"","inputs":[{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","prompt","images","timings","has_nsfw_concepts"],"pricing":"","published_at":"2024-06-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-sdxl.jpeg","title":"Stable Diffusion XL"},{"category":"text-to-image","description":"Generate Images with ControlNet.","endpoint_id":"fal-ai/fast-sdxl-controlnet-canny","family":"","inputs":[{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_image_url","required":true,"type":"string"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the control image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","images","timings","seed"],"pricing":"","published_at":"2024-02-28T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d6/coPReDaI9jEr370VyHNOZ_bL67e1a4.png","title":"ControlNet SDXL"},{"category":"image-to-image","description":"Generate Images with ControlNet.","endpoint_id":"fal-ai/fast-sdxl-controlnet-canny/image-to-image","family":"","inputs":[{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_image_url","required":true,"type":"string"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the control image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","images","timings","seed"],"pricing":"","published_at":"2023-12-01T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92e1/zLc8X8J0c0VU5-UHthfDf_ZplspoJQ.png","title":"ControlNet SDXL"},{"category":"image-to-image","description":"Generate Images with ControlNet.","endpoint_id":"fal-ai/fast-sdxl-controlnet-canny/inpainting","family":"","inputs":[{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_image_url","required":true,"type":"string"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The URL of the mask to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the control image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","images","timings","seed"],"pricing":"","published_at":"2023-12-01T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939e/qDBDvcUlHPz_jSFS4evMH_uqajLLYT.png","title":"ControlNet SDXL"},{"category":"image-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-sdxl/image-to-image","family":"","inputs":[{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":65,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","prompt","images","timings","has_nsfw_concepts"],"pricing":"","published_at":"2024-04-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-sdxl.jpeg","title":"Stable Diffusion XL"},{"category":"image-to-image","description":"Run SDXL at the speed of light","endpoint_id":"fal-ai/fast-sdxl/inpainting","family":"","inputs":[{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":65,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the mask to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","prompt","images","timings","has_nsfw_concepts"],"pricing":"","published_at":"2024-04-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-sdxl.jpeg","title":"Stable Diffusion XL"},{"category":"image-to-video","description":"Generate short video clips from your images using SVD v1.1 at Lightning Speed","endpoint_id":"fal-ai/fast-svd-lcm","family":"","inputs":[{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":127,"description":"The motion bucket id determines the motion of the generated video. The\n            higher the number, the more motion there will be.","enum":null,"is_list":false,"max":255,"media_kind":null,"min":1,"multiline":false,"name":"motion_bucket_id","required":false,"type":"integer"},{"default":0.02,"description":"The conditoning augmentation determines the amount of noise that will be\n            added to the conditioning frame. The higher the number, the more noise\n            there will be, and the less the video will look like the initial image.\n            Increase it for more motion.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"cond_aug","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of steps to run the model for. The higher the number the better\n            the quality and longer it will take to generate.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":10,"description":"The FPS of the generated video. The higher the number, the faster the video will\n            play. Total video length is 25 frames.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-svd-turbo.webp","title":"Stable Video Diffusion Turbo"},{"category":"text-to-video","description":"Generate short video clips from your images using SVD v1.1 at Lightning Speed","endpoint_id":"fal-ai/fast-svd-lcm/text-to-video","family":"","inputs":[{"default":null,"description":"The prompt to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":127,"description":"The motion bucket id determines the motion of the generated video. The\n            higher the number, the more motion there will be.","enum":null,"is_list":false,"max":255,"media_kind":null,"min":1,"multiline":false,"name":"motion_bucket_id","required":false,"type":"integer"},{"default":0.02,"description":"The conditoning augmentation determines the amount of noise that will be\n            added to the conditioning frame. The higher the number, the more noise\n            there will be, and the less the video will look like the initial image.\n            Increase it for more motion.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"cond_aug","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of steps to run the model for. The higher the number the better\n            the quality and longer it will take to generate.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":10,"description":"The FPS of the generated video. The higher the number, the faster the video will\n            play. Total video length is 25 frames.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2024-06-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-svd-turbo.gif","title":"Stable Video Diffusion Turbo"},{"category":"text-to-video","description":"Generate short video clips from your prompts using SVD v1.1","endpoint_id":"fal-ai/fast-svd/text-to-video","family":"","inputs":[{"default":null,"description":"The prompt to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":127,"description":"The motion bucket id determines the motion of the generated video. The\n            higher the number, the more motion there will be.","enum":null,"is_list":false,"max":255,"media_kind":null,"min":1,"multiline":false,"name":"motion_bucket_id","required":false,"type":"integer"},{"default":0.02,"description":"The conditoning augmentation determines the amount of noise that will be\n            added to the conditioning frame. The higher the number, the more noise\n            there will be, and the less the video will look like the initial image.\n            Increase it for more motion.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"cond_aug","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":20,"description":"The number of steps to run the model for. The higher the number the better\n            the quality and longer it will take to generate.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":"none","description":"This parameter is deprecated and has no effect. It is kept for backwards\n            compatibility.","enum":["none","minimum","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"deep_cache","required":false,"type":"enum"},{"default":10,"description":"The FPS of the generated video. The higher the number, the faster the video will\n            play. Total video length is 25 frames.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":"unrealistic, saturated, high contrast, big nose, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label","description":"The negative prompt to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/svd_rocket.gif","title":"Stable Video Diffusion"},{"category":"video-to-video","description":"Compose videos from multiple media sources using FFmpeg API.","endpoint_id":"fal-ai/ffmpeg-api/compose","family":"","inputs":[{"default":null,"description":"List of tracks to be combined into the final media","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tracks","required":true,"type":"json"}],"lab":"","output_kind":"text","output_props":["thumbnail_url","video_url"],"pricing":"","published_at":"2025-01-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ffmpeg-api-compose.webp","title":"FFmpeg API Compose"},{"category":"image-to-image","description":"ffmpeg endpoint for first, middle and last frame extraction from videos","endpoint_id":"fal-ai/ffmpeg-api/extract-frame","family":"","inputs":[{"default":null,"description":"URL of the video file to use as the video track","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"first","description":"Type of frame to extract: first, middle, or last frame of the video","enum":["first","middle","last"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"frame_type","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-06-09T10:55:21.156000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ffmpeg-api-compose.webp","title":"Ffmpeg Api"},{"category":"image-to-video","description":"A fal.ai endpoint that stitches an ordered list of images into an MP4 video by holding each image for a specified number of frames at a configurable frame rate","endpoint_id":"fal-ai/ffmpeg-api/images-to-video","family":"","inputs":[{"default":null,"description":"Ordered list of images to play as video frames. Each image is held for its specified number of frames before cutting to the next image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"images","required":true,"type":"json"},{"default":24,"description":"Frames per second of the output video.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-05-05T21:08:00.388000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a99021f/66-TU4tuGYUlScYEZCwkp_f2989ba3ae084e379f0a4362f6f54e9c.jpg","title":"Ffmpeg Api Images to Video"},{"category":"json","description":"Get EBU R128 loudness normalization from audio files using FFmpeg API.","endpoint_id":"fal-ai/ffmpeg-api/loudnorm","family":"","inputs":[{"default":null,"description":"URL of the audio file to normalize","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":-18,"description":"Integrated loudness target in LUFS.","enum":null,"is_list":false,"max":-5,"media_kind":null,"min":-70,"multiline":false,"name":"integrated_loudness","required":false,"type":"number"},{"default":-0.1,"description":"Maximum true peak in dBTP.","enum":null,"is_list":false,"max":0,"media_kind":null,"min":-9,"multiline":false,"name":"true_peak","required":false,"type":"number"},{"default":7,"description":"Loudness range target in LU","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"loudness_range","required":false,"type":"number"},{"default":0,"description":"Offset gain in dB applied before the true-peak limiter","enum":null,"is_list":false,"max":99,"media_kind":null,"min":-99,"multiline":false,"name":"offset","required":false,"type":"number"},{"default":false,"description":"Use linear normalization mode (single-pass). If false, uses dynamic mode (two-pass for better quality).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"linear","required":false,"type":"boolean"},{"default":false,"description":"Treat mono input files as dual-mono for correct EBU R128 measurement on stereo systems","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dual_mono","required":false,"type":"boolean"},{"default":false,"description":"Return loudness measurement summary with the normalized audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"print_summary","required":false,"type":"boolean"},{"default":null,"description":"Measured integrated loudness of input file in LUFS. Required for linear mode.","enum":null,"is_list":false,"max":0,"media_kind":null,"min":-99,"multiline":false,"name":"measured_i","required":false,"type":"number"},{"default":null,"description":"Measured loudness range of input file in LU. Required for linear mode.","enum":null,"is_list":false,"max":99,"media_kind":null,"min":0,"multiline":false,"name":"measured_lra","required":false,"type":"number"},{"default":null,"description":"Measured true peak of input file in dBTP. Required for linear mode.","enum":null,"is_list":false,"max":99,"media_kind":null,"min":-99,"multiline":false,"name":"measured_tp","required":false,"type":"number"},{"default":null,"description":"Measured threshold of input file in LUFS. Required for linear mode.","enum":null,"is_list":false,"max":0,"media_kind":null,"min":-99,"multiline":false,"name":"measured_thresh","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["summary","audio"],"pricing":"","published_at":"2025-07-08T19:13:13.775000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ffmpeg-api-waveform.webp","title":"Ffmpeg Api"},{"category":"video-to-video","description":"Merge videos with standalone audio files or audio from video files.","endpoint_id":"fal-ai/ffmpeg-api/merge-audio-video","family":"","inputs":[{"default":null,"description":"URL of the video file to use as the video track","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the audio file to use as the audio track","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Offset in seconds for when the audio should start relative to the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_offset","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-06-09T06:04:14.299000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-5.jpg","title":"Ffmpeg Api Merge Audio-Video"},{"category":"audio-to-audio","description":"Merge audios into a single audio using FFmpeg API!","endpoint_id":"fal-ai/ffmpeg-api/merge-audios","family":"","inputs":[{"default":null,"description":"List of audio URLs to merge in order. The 0th stream of the audio will be considered as the merge candidate.","enum":null,"is_list":true,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_urls","required":true,"type":"string"},{"default":null,"description":"Output format of the combined audio. If not used, will be determined automatically using FFMPEG. Formatted as codec_sample_rate_bitrate.","enum":["mp3_22050_32","mp3_44100_32","mp3_44100_64","mp3_44100_96","mp3_44100_128","mp3_44100_192","pcm_8000","pcm_16000","pcm_22050","pcm_24000","pcm_44100","pcm_48000","ulaw_8000","alaw_8000","opus_48000_32","opus_48000_64","opus_48000_96","opus_48000_128","opus_48000_192"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-12-23T21:51:58.875000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a878178/GTLJRXgGY24Y-lyirlsfm_c01912199a8c41298f64c5201337120a.jpg","title":"FFmpeg API [Merge Audios]"},{"category":"video-to-video","description":"Use ffmpeg capabilities to merge 2 or more videos.","endpoint_id":"fal-ai/ffmpeg-api/merge-videos","family":"","inputs":[{"default":null,"description":"List of video URLs to merge in order","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_urls","required":true,"type":"string"},{"default":null,"description":"Target FPS for the output video. If not provided, uses the lowest FPS from input videos.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"target_fps","required":false,"type":"number"},{"default":null,"description":"Resolution of the final video. Width and height must be between 512 and 2048.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Zero-based index of the input video whose aspect ratio should be used when resolution is not provided. If omitted, preserves the default behavior of using the minimum width and minimum height across input videos.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"resolution_aspect_ratio_video_index","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video","metadata"],"pricing":"","published_at":"2025-08-12T14:10:10.402000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b5/NrTcEEKFIBtR9irMXXIMh_y4h72cLd.png","title":"Ffmpeg Api"},{"category":"json","description":"Get encoding metadata from video and audio files using FFmpeg API.","endpoint_id":"fal-ai/ffmpeg-api/metadata","family":"","inputs":[{"default":null,"description":"URL of the media file (video or audio) to analyze","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"media_url","required":true,"type":"string"},{"default":false,"description":"Whether to extract the start and end frames for videos. Note that when true the request will be slower.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extract_frames","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["media"],"pricing":"","published_at":"2025-01-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ffmpeg-api-metadata.webp","title":"FFmpeg API Metadata"},{"category":"json","description":"Get waveform data from audio files using FFmpeg API.","endpoint_id":"fal-ai/ffmpeg-api/waveform","family":"","inputs":[{"default":null,"description":"URL of the audio file to analyze","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"media_url","required":true,"type":"string"},{"default":4,"description":"Controls how many points are sampled per second of audio. Lower values (e.g. 1-2) create a coarser waveform, higher values (e.g. 4-10) create a more detailed one.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"points_per_second","required":false,"type":"number"},{"default":2,"description":"Number of decimal places for the waveform values. Higher values provide more precision but increase payload size.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"precision","required":false,"type":"integer"},{"default":3,"description":"Size of the smoothing window. Higher values create a smoother waveform. Must be an odd number.","enum":null,"is_list":false,"max":21,"media_kind":null,"min":1,"multiline":false,"name":"smoothing_window","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["waveform","precision","points","duration"],"pricing":"","published_at":"2025-01-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ffmpeg-api-waveform.webp","title":"FFmpeg API Waveform"},{"category":"image-to-image","description":"Interpolate images with FILM - Frame Interpolation for Large Motion","endpoint_id":"fal-ai/film","family":"","inputs":[{"default":null,"description":"The URL of the first image to use as the starting point for interpolation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the second image to use as the ending point for interpolation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"},{"default":"images","description":"The type of output to generate; either individual images or a video.","enum":["images","video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_type","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the output images. Only applicable if output_type is 'images'.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video. Only applicable if output_type is 'video'.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Only applicable if output_type is 'video'.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":1,"description":"The number of frames to generate between the input images.","enum":null,"is_list":false,"max":64,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"Whether to include the start image in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_start","required":false,"type":"boolean"},{"default":false,"description":"Whether to include the end image in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_end","required":false,"type":"boolean"},{"default":8,"description":"Frames per second for the output video. Only applicable if output_type is 'video'.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","video"],"pricing":"Your request will cost $0.0013 per compute second.","published_at":"2025-07-22T20:06:32.726000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos.jpg","title":"FILM"},{"category":"video-to-video","description":"Interpolate videos with FILM - Frame Interpolation for Large Motion","endpoint_id":"fal-ai/film/video","family":"","inputs":[{"default":null,"description":"The URL of the video to use for interpolation.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":1,"description":"The number of frames to generate between the input video frames.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If True, the input video will be split into scenes before interpolation. This removes smear frames between scenes, but can result in false positives if the scene detection is not accurate. If False, the entire video will be treated as a single scene.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_scene_detection","required":false,"type":"boolean"},{"default":true,"description":"If True, the function will use the calculated FPS of the input video multiplied by the number of frames to determine the output FPS. If False, the passed FPS will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_calculated_fps","required":false,"type":"boolean"},{"default":8,"description":"Frames per second for the output video. Only applicable if use_calculated_fps is False.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":false,"description":"If True, the final frame will be looped back to the first frame to create a seamless loop. If False, the final frame will not loop back.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Only applicable if output_type is 'video'.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Only applicable if output_type is 'video'.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.0013 per compute second.","published_at":"2025-07-22T20:08:28.407000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos.jpg","title":"FILM"},{"category":"image-to-image","description":"Finegrain Eraser removes objects—along with their shadows, reflections, and lighting artifacts—using only natural language, seamlessly filling the scene with contextually accurate content.","endpoint_id":"fal-ai/finegrain-eraser","family":"","inputs":[{"default":null,"description":"URL of the image to edit","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text description of what to erase","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"standard","description":"Erase quality mode","enum":["express","standard","premium"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation","enum":null,"is_list":false,"max":999,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Finegrain","output_kind":"image","output_props":["image","used_seed"],"pricing":"Your request will cost $0.18 with Express, $0.27 with Standard, and $0.36 with Premium.","published_at":"2025-04-09T19:56:33.112000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-3.jpg","title":"Finegrain Eraser"},{"category":"image-to-image","description":"Finegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.","endpoint_id":"fal-ai/finegrain-eraser/bbox","family":"","inputs":[{"default":null,"description":"URL of the image to edit","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"List of bounding box coordinates to erase (only one box prompt is supported)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":true,"type":"json"},{"default":"standard","description":"Erase quality mode","enum":["express","standard","premium"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation","enum":null,"is_list":false,"max":999,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Finegrain","output_kind":"image","output_props":["image","used_seed"],"pricing":"Your request will cost $0.09 with Express, $0.18 with Standard, and $0.27 with Premium.","published_at":"2025-04-09T19:57:48.361000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-3.jpg","title":"Finegrain Eraser Bbox"},{"category":"image-to-image","description":"Finegrain Eraser removes any object selected with a mask—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.","endpoint_id":"fal-ai/finegrain-eraser/mask","family":"","inputs":[{"default":null,"description":"URL of the image to edit","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the mask image. Should be a binary mask where white (255) indicates areas to erase","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":"standard","description":"Erase quality mode","enum":["express","standard","premium"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation","enum":null,"is_list":false,"max":999,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Finegrain","output_kind":"image","output_props":["image","used_seed"],"pricing":"Your request will cost $0.04 with Express, $0.13 with Standard, and $0.22 with Premium.","published_at":"2025-04-10T17:18:31.479000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-3.jpg","title":"Finegrain Eraser Mask"},{"category":"image-to-image","description":"FireRed Image Edit is FireRed's state of the art open source editing model, re-trained from Qwen Image Edit 2509.","endpoint_id":"fal-ai/firered-image-edit","family":"","inputs":[{"default":null,"description":"The editing instruction describing what changes to make to the image. Supports both English and Chinese instructions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If None, uses the input image dimensions.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform. More steps generally produce higher quality results.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Classifier-free guidance scale. Higher values make the model follow the prompt more closely.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit. Supports single image editing and multi-image references (e.g., virtual try-on, style transfer from reference).","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"The negative prompt for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"The acceleration level to use for inference speed optimization.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","prompt","seed"],"pricing":"Your request will cost $0.0325 per output megapixel, rounded up to the nearest megapixel.","published_at":"2026-02-19T07:08:10.392000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f1239/wp41i0Uc6S7_a2LBEiNbL_1baaf9f1d4c54f79992b9a95b1bd4331.jpg","title":"Firered Image Edit"},{"category":"image-to-image","description":"FireRed Image Edit v1.1 is an updated version of FireRed Image Edit, with improved image editing capabilities.","endpoint_id":"fal-ai/firered-image-edit-v1.1","family":"","inputs":[{"default":null,"description":"The editing instruction describing what changes to make to the image. Supports both English and Chinese instructions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If None, uses the input image dimensions.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform. More steps generally produce higher quality results.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Classifier-free guidance scale. Higher values make the model follow the prompt more closely.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit. Supports single image editing and multi-image references (e.g., virtual try-on, style transfer from reference, portrait makeup).","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"The negative prompt for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"The acceleration level to use for inference speed optimization.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"FireRed","output_kind":"images","output_props":["prompt","seed","has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2026-03-05T15:29:32.237000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90f675/Gmp2KQoCOF63GQxC9cBc2_93137963f6d14fa3accada3e97b74871.jpg","title":"Firered Image Edit V1.1"},{"category":"image-to-video","description":"SoulX-FlashHead is a unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.","endpoint_id":"fal-ai/flashhead","family":"Flashhead","inputs":[{"default":null,"description":"URL of the face reference image. Portrait recommended.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text to speak. Converted to speech via ElevenLabs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"Aria","description":"ElevenLabs voice name.","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":0.5,"description":"Voice stability (0-1).","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"stability","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Soul AI Lab","output_kind":"video","output_props":["video","timings","duration","seed"],"pricing":"","published_at":"2026-04-30T16:37:09.369000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94db4d/aMNytcPYimW1YyGVRoxH3_2b4f538f1c174926a2183f0a7da66c7a.jpg","title":"Flashhead"},{"category":"audio-to-video","description":"Audio-driven talking avatar generation powered by the SoulX-FlashTalk 14B model.","endpoint_id":"fal-ai/flashtalk","family":"SoulX FlashTalk","inputs":[{"default":null,"description":"URL of the face reference image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the speech audio file (WAV, MP3, etc).","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Soul AI Lab","output_kind":"video","output_props":["video","timings","seed","duration"],"pricing":"","published_at":"2026-04-16T14:46:43.334000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94de6d/L1EyyKgRIeS1fWUVXyF9g_b3b3ab1dbd4146879c94613f56624649.jpg","title":"Flashtalk"},{"category":"video-to-video","description":"Upscale your videos using FlashVSR with the fastest speeds!","endpoint_id":"fal-ai/flashvsr/upscale/video","family":"","inputs":[{"default":2,"description":"Upscaling factor to be used.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":null,"description":"The random seed used for the generation process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The input video to be upscaled","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"regular","description":"Acceleration mode for VAE decoding. Options: regular (best quality), high (balanced), full (fastest). More accerleation means longer duration videos can be processed too.","enum":["regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"Color correction enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_fix","required":false,"type":"boolean"},{"default":70,"description":"Quality level for tile blending (0-100). Controls overlap between tiles to prevent grid artifacts. Higher values provide better quality with more overlap. Recommended: 70-85 for high-res videos, 50-70 for faster processing.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":0,"multiline":false,"name":"quality","required":false,"type":"integer"},{"default":false,"description":"Copy the original audio tracks into the upscaled video using FFmpeg when possible.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_audio","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The format of the output video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.0005 per megapixel of video data (width × height × frames).\nFor example, if your upscaled video is 1920×1080 with 121 frames, the total cost will be $0.125.","published_at":"2025-11-11T01:52:01.139000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/bj0FLRnM-ZgEQvTLXgax5_2c719e57677a4a05992eb71173b5d28f.jpg","title":"Flashvsr"},{"category":"vision","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/caption","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"text","output_props":["results"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence 2 Large Caption"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/caption-to-phrase-grounding","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text input for the task","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_input","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/dense-region-caption","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"vision","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/detailed-caption","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"text","output_props":["results"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence 2 Large Detailed Caption"},{"category":"vision","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/more-detailed-caption","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"text","output_props":["results"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/object-detection","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"vision","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/ocr","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"text","output_props":["results"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence 2 Large OCR"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/ocr-with-region","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/open-vocabulary-detection","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text input for the task","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_input","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/referring-expression-segmentation","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text input for the task","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_input","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/region-proposal","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"vision","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/region-to-category","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The user input coordinates","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"region","required":true,"type":"json"}],"lab":"","output_kind":"text","output_props":["results"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence 2 Large Region To Category"},{"category":"vision","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/region-to-description","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The user input coordinates","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"region","required":true,"type":"json"}],"lab":"","output_kind":"text","output_props":["results"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks","endpoint_id":"fal-ai/florence-2-large/region-to-segmentation","family":"","inputs":[{"default":null,"description":"The URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The user input coordinates","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"region","required":true,"type":"json"}],"lab":"","output_kind":"image","output_props":["results","image"],"pricing":"","published_at":"2024-06-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Florence-2 Large"},{"category":"image-to-image","description":"The model provides you high quality image editing capabilities.","endpoint_id":"fal-ai/flowedit","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt of the image to be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"source_prompt","required":true,"type":"string"},{"default":null,"description":"Prompt of the image to be made.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation. If set none, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"Steps for which the model should run.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1.5,"description":"Guidance scale for the source.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"src_guidance_scale","required":false,"type":"number"},{"default":5.5,"description":"Guidance scale for target.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"tar_guidance_scale","required":false,"type":"number"},{"default":1,"description":"Average step count","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"n_avg","required":false,"type":"integer"},{"default":23,"description":"Control the strength of the edit","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"n_max","required":false,"type":"integer"},{"default":0,"description":"Minimum step for improved style edits","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"n_min","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image","seed"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939e/WafAxBIDmm3djJb8ywXDf_8gs6raC2.png","title":"Flow-Edit"},{"category":"text-to-image","description":"FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux-1/dev","family":"Flux 1 Dev","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-06-02T18:12:26.276000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","title":"FLUX.1 [dev]"},{"category":"image-to-image","description":"FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux-1/dev/image-to-image","family":"Flux 1 Dev","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-06-02T18:28:08.120000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"FLUX.1 [dev]"},{"category":"image-to-image","description":"FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-1/dev/redux","family":"Flux 1 Krea","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-06-02T18:29:41.412000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","title":"FLUX.1 [dev] Redux"},{"category":"text-to-image","description":"FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux-1/krea","family":"Flux 1 Krea","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-07-30T13:15:37.175000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-5.jpg","title":"FLUX.1 Krea [dev]"},{"category":"image-to-image","description":"FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux-1/krea/image-to-image","family":"Flux 1 Krea","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-07-30T13:49:39.470000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-5.jpg","title":"FLUX.1 Krea [dev]"},{"category":"image-to-image","description":"FLUX.1 Krea [dev] Redux is a high-performance endpoint for the FLUX.1 Krea [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-1/krea/redux","family":"Flux 1 Krea","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-07-30T13:43:13.554000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale.jpg","title":"FLUX.1 Krea [dev] Redux"},{"category":"text-to-image","description":"Fastest inference in the world for the 12 billion parameter FLUX.1 [schnell] text-to-image model.","endpoint_id":"fal-ai/flux-1/schnell","family":"Flux 1 Schnell","inputs":[{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-06-02T18:15:06.266000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"FLUX.1 [schnell]"},{"category":"image-to-image","description":"FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-1/schnell/redux","family":"Flux 1 Schnell","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-06-02T18:30:38.654000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-5.jpeg","title":"FLUX.1 [schnell] Redux"},{"category":"text-to-image","description":"FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux-1/srpo","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-09-15T22:03:08.956000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d3/YI0vlnMufwkKs0eTTXmM7_UVyjAsaK.png","title":"FLUX.1 SRPO [dev]"},{"category":"image-to-image","description":"FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux-1/srpo/image-to-image","family":"","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-09-15T22:05:45.744000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/QmXPvyNcBu58l_Yb8ug72_8g3SvKdJ.png","title":"FLUX.1 SRPO [dev]"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","endpoint_id":"fal-ai/flux-2","family":"Flux 2","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"","published_at":"2025-11-23T00:15:07.672000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/zSBCJtPpeIQwR5AC_IamX_b1e1137961754e4d851907c21f8c20cd.jpg","title":"FLUX 2"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [flex] from Black Forest Labs. Features adjustable inference steps and guidance scale for fine-tuned control. Enhanced typography and text rendering capabilities.","endpoint_id":"fal-ai/flux-2-flex","family":"Flux 2 Flex","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":3.5,"description":"The guidance scale to use for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1.5,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"Your request will cost $0.05 per megapixel on both input and output side, rounded up to the nearest megapixel. For example, a 1024x1024 image will cost $0.05, and a 1920x1080 image will cost $0.10 ($0.06 × 2 megapixels). Similarly, a 512x512 output will cost $0.05 ($0.05 for 0.26 megapixels, rounded to 1 megapixel).","published_at":"2025-11-25T02:35:27.724000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/LqyVE8NElm_vf-t27Yfkz_6c1dd3323df343e4a3ec968d8f67024c.jpg","title":"Flux 2 Flex"},{"category":"image-to-image","description":"Image editing with FLUX.2 [flex] from Black Forest Labs. Supports multi-reference editing with customizable inference steps and enhanced text rendering.","endpoint_id":"fal-ai/flux-2-flex/edit","family":"Flux 2 Flex","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image. If `auto`, the size will be determined by the model.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"List of URLs of input images for editing","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":3.5,"description":"The guidance scale to use for the generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1.5,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"Your request will cost $0.05 per megapixel on both input and output side, rounded up to the nearest megapixel. For example, a 1024x1024 image will cost $0.05, and a 1920x1080 image will cost $0.10 ($0.05 × 2 megapixels). Similarly, a 512x512 output will cost $0.06 ($0.05 for 0.26 megapixels, rounded to 1 megapixel).","published_at":"2025-11-25T02:36:00.176000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/NXNJkZllyE8XTyMrtEALf_90206edd3ddb4ba793758a26bde823c7.jpg","title":"Flux 2 Flex"},{"category":"training","description":"Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.","endpoint_id":"fal-ai/flux-2-klein-9b-base-trainer","family":"Flux 2 Klein","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images, although more is better.\n\n    The zip can also contain a text file for each image. The text file should be named:\n    ROOT.txt\n    For example:\n    photo.txt\n\n    This text file can be used to specify the edit instructions for the image pair.\n\n    If no text file is provided, the default_caption will be used.\n\n    If no default_caption is provided, the training will fail.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":5e-05,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0043 * steps. With 1000 steps, your request will cost $4.3.","published_at":"2026-01-17T00:10:10.940000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b082b/4dsf0LE8NoXuk9Pz0Ziue_d7c1c380c4d04e03b820d06500a5749f.jpg","title":"FLUX 2 [klein] 9b Base Trainer"},{"category":"training","description":"Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.","endpoint_id":"fal-ai/flux-2-klein-9b-base-trainer/edit","family":"Flux 2 Klein","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n    The zip should contain pairs of images. The images should be named:\n\n    ROOT_start.EXT and ROOT_end.EXT\n    For example:\n    photo_start.jpg and photo_end.jpg\n\n    The zip can also contain up to four reference image for each image pair. The reference images should be named:\n    ROOT_start.EXT, ROOT_start2.EXT, ROOT_start3.EXT, ROOT_start4.EXT, ROOT_end.EXT\n    For example:\n    photo_start.jpg, photo_start2.jpg, photo_end.jpg\n\n    The zip can also contain ","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":5e-05,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps and the reference images. The formula is: 0.002 * steps * reference_multiplier. The reference multiplier for 1, 2, 3 and 4 images is 2.11, 3.44, 5.09, and 6.95 respectively. With 1 reference image and 1000 steps, your request will cost $4.22.","published_at":"2026-01-17T00:12:09.074000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b0825/dvng2ddAgvgcH9WxFOxF7_b324e03aec15473c998151bb6fa0453c.jpg","title":"Flux 2 Klein 9B Base Trainer"},{"category":"image-to-image","description":"Add a background to images with white/clean background","endpoint_id":"fal-ai/flux-2-lora-gallery/add-background","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The URLs of the images. Provide an image with a white or clean background.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"Add Background forest","description":"The prompt describing the background to add. Must start with 'Add Background' followed by your description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the add background effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:25:11.715000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/-soa1BLI68gem3r7qatcf_ec7fab33b28040238c41b8f80546e89b.jpg","title":"Flux 2 Lora Gallery"},{"category":"image-to-image","description":"Virtually furnishes an empty apartment","endpoint_id":"fal-ai/flux-2-lora-gallery/apartment-staging","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The URL of the empty room image to furnish.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The prompt to generate a furnished room. Use 'furnish this room' for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the apartment staging effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:29:04.658000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/B8oJR3Fdg-dqVxbhAJsa1_c6599007f202434b8bda0349f863ebfc.jpg","title":"Flux 2 Lora Gallery"},{"category":"text-to-image","description":"Ballpoint pen sketch drawing style","endpoint_id":"fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate a ballpoint pen sketch style image. Use 'b4llp01nt' trigger word for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the ballpoint pen sketch effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:30:43.105000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/G7xRP2MFaynDxvtM3tDIf_8f3d89b67c234182bd704e3349162883.jpg","title":"Flux 2 Lora Gallery"},{"category":"text-to-image","description":"Transforms images into comic book style","endpoint_id":"fal-ai/flux-2-lora-gallery/digital-comic-art","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate a digital comic art style image. Use 'd1g1t4l' trigger word for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the digital comic art effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:32:21.201000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/-C_LrtBKqv1kuA3PkybTA_60142c0dc6da4ba8905165de61daacaf.jpg","title":"Flux 2 Lora Gallery"},{"category":"image-to-image","description":"Extends a face into a full body portrait","endpoint_id":"fal-ai/flux-2-lora-gallery/face-to-full-portrait","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The URL of the cropped face image.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"Face to full portrait","description":"The prompt describing the full portrait to generate from the face.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the face to full portrait effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:37:05.640000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/S6rY_7j8Q-hCTWtn0Wb4k_99665a8ac4584b36b382565ef1ba20e3.jpg","title":"Flux 2 Lora Gallery"},{"category":"text-to-image","description":"HDR surrealistic effect with intense colors","endpoint_id":"fal-ai/flux-2-lora-gallery/hdr-style","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate an HDR style image. The trigger word 'Hyp3rRe4list1c' will be automatically prepended.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the HDR style effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:38:44.387000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/XhRCpnCkio1p3CnaNTQyQ_839690f21013420f8d0bb5d101fd329d.jpg","title":"FLUX 2 Lora Gallery Hdr Style"},{"category":"image-to-image","description":"Generates same object from different angles (azimuth/elevation)","endpoint_id":"fal-ai/flux-2-lora-gallery/multiple-angles","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The URL of the image to adjust camera angle for.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":0,"description":"Horizontal rotation angle around the object in degrees. 0°=front view, 90°=right side, 180°=back view, 270°=left side, 360°=front view again.","enum":null,"is_list":false,"max":360,"media_kind":null,"min":0,"multiline":false,"name":"horizontal_angle","required":false,"type":"number"},{"default":0,"description":"Vertical camera angle in degrees. 0°=eye-level shot, 30°=elevated shot, 60°=high-angle shot (looking down from above).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0,"multiline":false,"name":"vertical_angle","required":false,"type":"number"},{"default":5,"description":"Camera zoom/distance. 0=wide shot (far away), 5=medium shot (normal), 10=close-up (very close).","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"zoom","required":false,"type":"number"},{"default":null,"description":"The size of the generated image. If not provided, the size of the input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image.","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the multiple angles effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:41:48.103000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/uGB7v3AfMfHnqXp04NAzY_c730bfb4d81848338df88c8b6db41927.jpg","title":"Flux 2 Lora Gallery"},{"category":"text-to-image","description":"Makes images more photorealistic and natural","endpoint_id":"fal-ai/flux-2-lora-gallery/realism","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate a realistic image with natural lighting and authentic details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the realism effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:45:02.910000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/HJMvMFtI3pbgP7xP7L995_81e2ec28da9b49f9badb58560cb70088.jpg","title":"FLUX 2 Lora Gallery Realism"},{"category":"text-to-image","description":"Generates satellite/aerial view style images","endpoint_id":"fal-ai/flux-2-lora-gallery/satellite-view-style","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate a satellite/aerial view style image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the satellite view style effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:47:02.458000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/BPMCo8jjOVngBxqYDK7sK_9b09e8f629d74207bcb6cab302cff659.jpg","title":"Flux 2 Lora Gallery"},{"category":"text-to-image","description":"Applies sepia vintage effect to images","endpoint_id":"fal-ai/flux-2-lora-gallery/sepia-vintage","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate a sepia vintage photography style image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the sepia vintage photography effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:58:53.285000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/qyhINx709mN5xIBjraXXQ_af4667229d1d44b2912f6becc366d6d9.jpg","title":"Flux 2 Lora Gallery"},{"category":"image-to-image","description":"Virtual clothing try-on (2 images: person + garment)","endpoint_id":"fal-ai/flux-2-lora-gallery/virtual-tryon","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The URLs of the images for virtual try-on. Provide person image and clothing image.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The prompt to generate a virtual try-on image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The strength of the virtual try-on effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","seed"],"pricing":"","published_at":"2025-11-25T19:50:48.195000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/l4pNPFFxYpTn4dDetQB3H_0e3817198ad1498db78841fba7eefff9.jpg","title":"Flux 2 Lora Gallery"},{"category":"text-to-image","description":"FLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.","endpoint_id":"fal-ai/flux-2-max","family":"Flux 2 Max","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"The first processed megapixel will cost $0.07. Each additional megapixel will cost 0.03","published_at":"2025-12-16T13:55:00.993000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a868a0f/zL7LNUIqnPPhZNy_PtHJq_330f66115240460788092cb9523b6aba.jpg","title":"Flux 2 Max"},{"category":"image-to-image","description":"FLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.","endpoint_id":"fal-ai/flux-2-max/edit","family":"Flux 2 Max","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image. If `auto`, the size will be determined by the model.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"List of URLs of input images for editing","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"The first processed megapixel will cost $0.07. Each additional megapixel will cost 0.03. Input images counted as processed megapixel.","published_at":"2025-12-16T13:47:03.184000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8689a8/bbcmo6U5xg_RxDXijtxNA_55df705e1b1b4535a90bccd70887680e.jpg","title":"Flux 2 Max"},{"category":"text-to-image","description":"Image editing with FLUX.2 [pro] from Black Forest Labs. Ideal for high-quality image manipulation, style transfer, and sequential editing workflows","endpoint_id":"fal-ai/flux-2-pro","family":"Flux 2 Pro","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"Your request will cost $0.03 for the first megapixel of output, plus $0.015 per extra megapixel of input and output, rounded up to the nearest megapixel. For example, a 1024x1024 image will cost $0.03, and a 1920x1080 image will cost $0.045 ($0.03 for first megapixel + $0.015 for the second megapixel). Similarly, a 512x512 output will cost $0.03 ($0.03 for 0.25 megapixels, rounded to 1 megapixel)","published_at":"2025-11-23T00:14:31.608000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/UfryXXm9my6IM8HsoP9FL_054c2c2953dc491996904114c6e04836.jpg","title":"Flux 2 Pro"},{"category":"image-to-image","description":"Text-to-image generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images.","endpoint_id":"fal-ai/flux-2-pro/edit","family":"Flux 2 Pro","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image. If `auto`, the size will be determined by the model.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The seed to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"List of URLs of input images for editing","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"Your request will cost $0.03 for the first megapixel of output, plus $0.015 per extra megapixel of input and output, rounded up to the nearest megapixel. For example, a 1024x1024 image will cost $0.03, and a 1920x1080 image will cost $0.045 ($0.03 for first megapixel + $0.015 for the second megapixel). Similarly, a 512x512 output will cost $0.03 ($0.03 for0.25 megapixels, rounded to 1 megapixel)","published_at":"2025-11-23T00:13:41.404000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/eZetcrsZI6AQLCD3f5gaI_b173ae004bdd4108bd1be54eb6e49c7a.jpg","title":"FLUX 2 Pro Edit"},{"category":"image-to-image","description":"Outpainting generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images.","endpoint_id":"fal-ai/flux-2-pro/outpaint","family":"Flux 2 Pro","inputs":[{"default":null,"description":"The image URL to expand using outpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0,"description":"Pixels to expand at the top of the image.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":0,"multiline":false,"name":"expand_top","required":false,"type":"integer"},{"default":0,"description":"Pixels to expand at the bottom of the image.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":0,"multiline":false,"name":"expand_bottom","required":false,"type":"integer"},{"default":0,"description":"Pixels to expand on the left of the image.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":0,"multiline":false,"name":"expand_left","required":false,"type":"integer"},{"default":0,"description":"Pixels to expand on the right of the image.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":0,"multiline":false,"name":"expand_right","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically crop the reference image when the expanded canvas does not fully contain it.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_crop","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.03 for the first megapixel of output, plus $0.015 per extra megapixel of input and output, rounded up to the nearest megapixel. For example, a 1024x1024 image will cost $0.03, and a 1920x1080 image will cost $0.045 ($0.03 for first megapixel + $0.015 for the second megapixel). Similarly, a 512x512 output will cost $0.03 ($0.03 for 0.25 megapixels, rounded to 1 megapixel).","published_at":"2026-05-14T23:54:45.441000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a3cce/-REF_qGgpSuwSJ0NGjEYo_d68ad106f4174e0d8fb68c3551e6bc86.jpg","title":"FLUX 2 Pro Outpaint"},{"category":"training","description":"Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.","endpoint_id":"fal-ai/flux-2-trainer","family":"Flux 2 Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images, although more is better.\n\n    The zip can also contain a text file for each image. The text file should be named:\n    ROOT.txt\n    For example:\n    photo.txt\n\n    This text file can be used to specify the edit instructions for the image pair.\n\n    If no text file is provided, the default_caption will be used.\n\n    If no default_caption is provided, the training will fail.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":5e-05,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0064 * steps. With 1000 steps, your request will cost $6.40.","published_at":"2025-11-25T04:33:24.920000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/nYv87OHdt503yjlNUk1P3_2551388f5f4e4537b67e8ed436333bca.jpg","title":"FLUX 2 Trainer"},{"category":"training","description":"Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.","endpoint_id":"fal-ai/flux-2-trainer-v2","family":"Flux 2 Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images, although more is better.\n\n    The zip can also contain a text file for each image. The text file should be named:\n    ROOT.txt\n    For example:\n    photo.txt\n\n    This text file can be used to specify the edit instructions for the image pair.\n\n    If no text file is provided, the default_caption will be used.\n\n    If no default_caption is provided, the training will fail.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":5e-05,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0064 * steps. With 1000 steps, your request will cost $6.40.","published_at":"2026-01-10T00:59:39.928000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/nYv87OHdt503yjlNUk1P3_2551388f5f4e4537b67e8ed436333bca.jpg","title":"FLUX 2 Trainer V2"},{"category":"training","description":"Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.","endpoint_id":"fal-ai/flux-2-trainer-v2/edit","family":"Flux 2 Trainer","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n    The zip should contain pairs of images. The images should be named:\n\n    ROOT_start.EXT and ROOT_end.EXT\n    For example:\n    photo_start.jpg and photo_end.jpg\n\n    The zip can also contain up to four reference image for each image pair. The reference images should be named:\n    ROOT_start.EXT, ROOT_start2.EXT, ROOT_start3.EXT, ROOT_start4.EXT, ROOT_end.EXT\n    For example:\n    photo_start.jpg, photo_start2.jpg, photo_end.jpg\n\n    The zip can also contain ","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":5e-05,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps, reference images. The formula is: 0.0056 * steps * reference_multiplier. The reference multiplier for 1, 2, 3 and 4 images is 2.11, 3.44, 5.09, and 6.95 respectively. With 1 reference image and 1000 steps, your request will cost $11.82.","published_at":"2026-01-10T01:08:01.647000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/QQxycBXjY75hch-HBAQKZ_4af8ba3ddb9d457ba5fc51fcd428e720.jpg","title":"FLUX 2 Trainer V2 Edit"},{"category":"training","description":"Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.","endpoint_id":"fal-ai/flux-2-trainer/edit","family":"Flux 2 Trainer","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n    The zip should contain pairs of images. The images should be named:\n\n    ROOT_start.EXT and ROOT_end.EXT\n    For example:\n    photo_start.jpg and photo_end.jpg\n\n    The zip can also contain up to four reference image for each image pair. The reference images should be named:\n    ROOT_start.EXT, ROOT_start2.EXT, ROOT_start3.EXT, ROOT_start4.EXT, ROOT_end.EXT\n    For example:\n    photo_start.jpg, photo_start2.jpg, photo_end.jpg\n\n    The zip can also contain ","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":5e-05,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps, reference images. The formula is: 0.0056 * steps * reference_multiplier. The reference multiplier for 1, 2, 3 and 4 images is 2.11, 3.44, 5.09, and 6.95 respectively. With 1 reference image and 1000 steps, your request will cost $11.82.","published_at":"2025-11-25T04:36:01.280000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/QQxycBXjY75hch-HBAQKZ_4af8ba3ddb9d457ba5fc51fcd428e720.jpg","title":"FLUX 2 Trainer Edit"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/edit","family":"Flux 2","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"Requests cost $0.012 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.024 (1 MP input + 1 MP output, each costing 0.012).","published_at":"2025-11-23T00:15:40.781000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/zYjw3YqOcfDQymX7cvMBl_3d76809c48f74eb9abe3e17e1bdd5d2d.jpg","title":"FLUX 2 Edit"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities— in a flash.","endpoint_id":"fal-ai/flux-2/flash","family":"Flux 2 Flash","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"","published_at":"2025-12-16T20:07:20.209000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a871486/tX7YdfQViGtCE7ZjxOCph_5f5262a21e9e426e8981ea9513d11999.jpg","title":"FLUX 2 Flash"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—in a flash.","endpoint_id":"fal-ai/flux-2/flash/edit","family":"Flux 2 Flash","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"Requests cost $0.005 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.010 (1 MP input + 1 MP output, each costing 0.005).","published_at":"2025-12-16T20:10:11.517000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a871484/fjLSktGKoWIGQWm-GRaUM_87cd94bbbff7400b830e73b8f6f075d4.jpg","title":"FLUX 2 Flash Edit"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 4B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","endpoint_id":"fal-ai/flux-2/klein/4b","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-15T12:20:58.031000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f30/UwGq5qBE9zqd4r6QI7En0_082c2d0376a646378870218b6c0589f9.jpg","title":"FLUX.2 [klein] 4B"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 4B Base from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","endpoint_id":"fal-ai/flux-2/klein/4b/base","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-15T18:57:56.846000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f36/bYUAh_nzYUAUa_yCBkrP1_2dd84022eeda49e99db95e13fc588e47.jpg","title":"FLUX.2 [klein] 4B Base"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [klein] 4B Base from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/klein/4b/base/edit","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.009 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024×1024 generation with a 512×512 input image will cost $0.018 (1 MP input + 1 MP output, each costing $0.009).","published_at":"2026-01-15T20:55:54.156000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f49/nKsGN6UMAi6IjaYdkmILC_e20d2097bb984ad589518cf915fe54b4.jpg","title":"FLUX.2 [klein] 4B Base"},{"category":"image-to-image","description":"Image-to-image editing with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs. Specialized style transfer and domain-specific modifications.","endpoint_id":"fal-ai/flux-2/klein/4b/base/edit/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.016 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.032 (1 MP input + 1 MP output, each costing 0.016).","published_at":"2026-01-19T16:30:59.857000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b09b3/ck_nRVKlUom4-4_5qfG7t_117a3ccf9f9541aeb83e5ffa75564e6d.jpg","title":"FLUX.2 [klein] 4B Base LoRA"},{"category":"text-to-image","description":"Text-to-image generation with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs. Custom style adaptation and fine-tuned model variations.","endpoint_id":"fal-ai/flux-2/klein/4b/base/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-19T16:24:56.142000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b09ad/V8uFhTiTNXdAgvt1tbJmB_1335a918cf5542539d5954c13b7d0fef.jpg","title":"FLUX.2 [klein] 4B Base LoRA"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [klein] 4B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/klein/4b/edit","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-15T12:26:00.554000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f40/-9rbLPCsz36IFb-4t3J2L_76750002c0db4ce899b77e98321ffe30.jpg","title":"FLUX.2 [klein] 4B"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [klein] 4B from Black Forest Labs and custom LoRA. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/klein/4b/edit/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.01 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.02 (1 MP input + 1 MP output, each costing 0.01).","published_at":"2026-03-17T17:08:43.804000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a928e1f/c62zNs4MhBXgm-5w7n0C5_90bad8837ecc451e96f91da93b78f564.jpg","title":"FLUX.2 [klein] 4B LoRA"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 4B from Black Forest Labs and custom LoRA. Enhanced realism, crisper text generation, and native editing capabilities.","endpoint_id":"fal-ai/flux-2/klein/4b/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.01 per megapixel","published_at":"2026-03-17T17:01:51.649000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a928da0/57Gi1qonPRBT6XhWAvMAH_ac391991cfe0414199ae74f054947eef.jpg","title":"FLUX.2 [klein] 4B LoRA"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","endpoint_id":"fal-ai/flux-2/klein/9b","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-15T12:24:18.909000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f3c/90FKDpwtSCZTqOu0jUI-V_64c1a6ec0f9343908d9efa61b7f2444b.jpg","title":"FLUX.2 [klein] 9B"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 9B Base from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","endpoint_id":"fal-ai/flux-2/klein/9b/base","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-15T20:51:04.479000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f3c/90FKDpwtSCZTqOu0jUI-V_64c1a6ec0f9343908d9efa61b7f2444b.jpg","title":"FLUX.2 [klein] 9B Base"},{"category":"image-to-image","description":"Image-to-image editing with Flux 2 [klein] 9B Base from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/klein/9b/base/edit","family":"FLUX.2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.011 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024×1024 generation with a 512×512 input image will cost  $0.022 (1 MP input + 1 MP output, each costing  $0.011).","published_at":"2026-01-15T20:47:31.793000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f50/X8ffS5h55gcigsNZoNC7O_52e6b383ac214d2abe0a2e023f03de88.jpg","title":"FLUX.2 [klein] 9B Base"},{"category":"image-to-image","description":"Image-to-image editing with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs. Specialized style transfer and domain-specific modifications.","endpoint_id":"fal-ai/flux-2/klein/9b/base/edit/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.02 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.04 (1 MP input + 1 MP output, each costing 0.02).","published_at":"2026-01-19T16:36:11.015000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b09b1/1lRmcLX6NOxTZp285RGPN_85a165d7a3cd4fbfba4c6302d341f0aa.jpg","title":"FLUX.2 [klein] 9B Base LoRA"},{"category":"text-to-image","description":"Text-to-image generation with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs. Custom style adaptation and fine-tuned model variations.","endpoint_id":"fal-ai/flux-2/klein/9b/base/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for classifier-free guidance. Describes what to avoid in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"Guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2026-01-19T16:34:00.337000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b09ab/3my7lbot7weIdE03-d5xc_2da235d3c4d14924b2c7a03f47e1bd65.jpg","title":"FLUX.2 [klein] 9B Base LoRA"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/klein/9b/edit","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.011 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024×1024 generation with a 512×512 input image will cost  $0.022 (1 MP input + 1 MP output, each costing  $0.011).","published_at":"2026-01-15T12:25:09.939000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a7f50/X8ffS5h55gcigsNZoNC7O_52e6b383ac214d2abe0a2e023f03de88.jpg","title":"FLUX.2 [klein] 9B"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs and custom LoRA. Precise modifications using natural language descriptions and hex color control.","endpoint_id":"fal-ai/flux-2/klein/9b/edit/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image. If not provided, uses the input image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.015 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.03 (1 MP input + 1 MP output, each costing 0.015).","published_at":"2026-03-17T17:25:59.132000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a928dd2/yFNW07YLHtp5zuE4eJAW1_e2f89915a1b740559b3c652b0b028296.jpg","title":"FLUX.2 [klein] 9B LoRA"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs and custom LoRA.","endpoint_id":"fal-ai/flux-2/klein/9b/lora","family":"Flux 2 Klein","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"Requests cost $0.015 per megapixel","published_at":"2026-03-17T17:22:48.946000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a928e3b/sIC-Ne9BMwZZtBvR3FwKN_9a724704a550471a9df59999e9e1017f.jpg","title":"FLUX.2 [klein] 9B LoRA"},{"category":"image-to-image","description":"Realtime generation with FLUX.2 [klein] from Black Forest Labs.","endpoint_id":"fal-ai/flux-2/klein/realtime","family":"Flux 2 Klein","inputs":[{"default":3,"description":"Num Inference Steps","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"Enable RIFE frame interpolation between consecutive frames (doubles output frames).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_interpolation","required":false,"type":"boolean"},{"default":"Turn this into \"Living oil painting, melting gold and sapphire\"","description":"The prompt to guide image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":35,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Output feedback loop. 1.0 = pure noise (no feedback), 0.9 = 90% noise + 10% previous output latent.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"output_feedback_strength","required":false,"type":"number"},{"default":"square","description":"The size of the generated image. square=768x768, square_hd=1024x1024.","enum":["square","square_hd"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2.3,"description":"Schedule mu for time shift. 2.3=default, lower=more even denoising, 0.3=nearly linear.","enum":null,"is_list":false,"max":2.5,"media_kind":null,"min":0.3,"multiline":false,"name":"schedule_mu","required":false,"type":"number"},{"default":null,"description":"Base64-encoded image data URI for editing. CDN URLs are not supported for realtime. For optimal performance, use 704x704 JPEG images with 50% quality. Other sizes will be resized automatically.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2026-02-05T23:20:48.413000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d5092/vaTm5if3zW-sNx3VgjI2T_2b97424cac3e4f62bebb30ddf1aa1d4b.jpg","title":"Flux 2 [klein] Realtime"},{"category":"text-to-image","description":"Text-to-image generation with LoRA support for FLUX.2 [dev] from Black Forest Labs. Custom style adaptation and fine-tuned model variations.","endpoint_id":"fal-ai/flux-2/lora","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3). Each LoRA can be a URL, HuggingFace repo ID, or local path.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"Your request will cost $0.021 per megapixel. LoRAs over 2GB in size will accrue an extra 50% charge per GB (2-3GB total lora size will multiply the price by 1.5x, 3-4GB total lora size by 2x, 4-5GB total lora size by 2.5x. The max limit is now 5GB from the older 2GB.","published_at":"2025-11-23T00:16:11.639000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/tOKnFZKepFeCNbgp6-ndM_7aba1231214a4c0e9446a7c2e02a9289.jpg","title":"FLUX 2 Lora"},{"category":"image-to-image","description":"Image-to-image editing with LoRA support for FLUX.2 [dev] from Black Forest Labs. Specialized style transfer and domain-specific modifications.","endpoint_id":"fal-ai/flux-2/lora/edit","family":"Flux 2 Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for the image generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URsL of the images for editing. A maximum of 3 images are allowed, if more are provided, only the first 3 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3). Each LoRA can be a URL, HuggingFace repo ID, or local path.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"Requests cost $0.021 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.042 (1 MP input + 1 MP output, each costing 0.021). LoRAs over 2GB in size will accrue an extra 50% charge per GB (2-3GB total lora size will multiply the price by 1.5x, 3-4GB total lora size by 2x, 4-5GB total lora size by 2.5x. The max limit is now 5GB from the older 2GB.","published_at":"2025-11-23T00:16:39.018000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/yUqMpmIEFNYAjtwP3j5VH_5a4980d4efa9484c9ad6a85f88d7563d.jpg","title":"FLUX 2 Lora Edit"},{"category":"text-to-image","description":"Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities—all at turbo speed.","endpoint_id":"fal-ai/flux-2/turbo","family":"Flux 2 Turbo","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"","published_at":"2025-12-16T14:02:30.209000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a871494/j8F-tmy_dz4TyImvIHj19_510cc93373ef451386734b7e05711de1.jpg","title":"FLUX 2 Turbo"},{"category":"image-to-image","description":"Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—all at turbo speed.","endpoint_id":"fal-ai/flux-2/turbo/edit","family":"Flux 2 Turbo","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2.5,"description":"Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The seed to use for the generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the image to generate. The width and height must be between 512 and 2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images for editing. A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","prompt","has_nsfw_concepts","seed","timings"],"pricing":"Requests cost $0.008 per megapixel of input and output. Input images will be resized to 1MP. For example, a 1024x1024 generation with 512*512 size image input will cost 0.016 (1 MP input + 1 MP output, each costing 0.008).","published_at":"2025-12-16T14:07:03.662000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87149a/-KWY7GOfhbNA3tLkPSJ8w_b8d48adf037e42038ecf0595281ffaac.jpg","title":"FLUX 2 Turbo Edit"},{"category":"text-to-image","description":"FLUX Control LoRA Canny is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a Canny edge map.","endpoint_id":"fal-ai/flux-control-lora-canny","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of image to use for image-to-image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The image to use for control lora. This is used to control the style of the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_lora_image_url","required":true,"type":"string"},{"default":1,"description":"The strength of the control lora.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"control_lora_strength","required":false,"type":"number"},{"default":true,"description":"If set to true, the input image will be preprocessed to extract depth information.\n            This is useful for generating depth maps from images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_depth","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/control-lora-canny.jpeg","title":"FLUX.1 [dev] Control LoRA Canny"},{"category":"image-to-image","description":"FLUX Control LoRA Canny is a high-performance endpoint that uses a control image using a Canny edge map to transfer structure to the generated image and another initial image to guide color.","endpoint_id":"fal-ai/flux-control-lora-canny/image-to-image","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The image to use for control lora. This is used to control the style of the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_lora_image_url","required":true,"type":"string"},{"default":1,"description":"The strength of the control lora.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"control_lora_strength","required":false,"type":"number"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/control-lora-canny.jpeg","title":"FLUX.1 [dev] Control LoRA Canny"},{"category":"text-to-image","description":"FLUX Control LoRA Depth is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a depth map.","endpoint_id":"fal-ai/flux-control-lora-depth","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of image to use for image-to-image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The image to use for control lora. This is used to control the style of the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_lora_image_url","required":true,"type":"string"},{"default":1,"description":"The strength of the control lora.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"control_lora_strength","required":false,"type":"number"},{"default":true,"description":"If set to true, the input image will be preprocessed to extract depth information.\n            This is useful for generating depth maps from images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_depth","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["has_nsfw_concepts","images","prompt","timings","seed"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/control-lora-depth.jpeg","title":"FLUX.1 [dev] Control LoRA Depth"},{"category":"image-to-image","description":"FLUX Control LoRA Depth is a high-performance endpoint that uses a control image using a depth map to transfer structure to the generated image and another initial image to guide color.","endpoint_id":"fal-ai/flux-control-lora-depth/image-to-image","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The image to use for control lora. This is used to control the style of the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_lora_image_url","required":true,"type":"string"},{"default":1,"description":"The strength of the control lora.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"control_lora_strength","required":false,"type":"number"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["has_nsfw_concepts","images","prompt","timings","seed"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/control-lora-depth.jpeg","title":"FLUX.1 [dev] Control LoRA Depth"},{"category":"text-to-image","description":"A versatile endpoint for the FLUX.1 [dev] model that supports multiple AI extensions including LoRA, ControlNet conditioning, and IP-Adapter integration, enabling comprehensive control over image generation through various guidance methods.","endpoint_id":"fal-ai/flux-general","family":"Flux General","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"control_loras","required":false,"type":"json"},{"default":"[]","description":"The controlnets to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":"[]","description":"The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_unions","required":false,"type":"json"},{"default":"[]","description":"IP-Adapter to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapters","required":false,"type":"json"},{"default":"[]","description":"EasyControl Inputs to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"easycontrols","required":false,"type":"json"},{"default":null,"description":"Use an image input to influence the generation. Can be used to fill images in masked areas.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_image","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"real_cfg_scale","required":false,"type":"number"},{"default":false,"description":"Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true.\n            If using XLabs IP-Adapter v1, this will be turned on!.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_real_cfg","required":false,"type":"boolean"},{"default":false,"description":"Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_cfg_zero","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Reference-Only","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":0.65,"description":"Strength of reference_only generation. Only used if a reference image is provided.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":-3,"multiline":false,"name":"reference_strength","required":false,"type":"number"},{"default":0,"description":"The percentage of the total timesteps when the reference guidance is to bestarted.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_start","required":false,"type":"number"},{"default":1,"description":"The percentage of the total timesteps when the reference guidance is to be ended.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_end","required":false,"type":"number"},{"default":0.5,"description":"Base shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"base_shift","required":false,"type":"number"},{"default":1.15,"description":"Max shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"max_shift","required":false,"type":"number"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Specifies whether beta sigmas ought to be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_beta_schedule","required":false,"type":"boolean"},{"default":null,"description":"Sigmas schedule for the denoising process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigma_schedule","required":false,"type":"string"},{"default":"euler","description":"Scheduler for the denoising process.","enum":["euler","dpmpp_2m"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"","description":"Negative prompt to steer the image generation away from unwanted features.\n            By default, we will be using NAG for processing the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":3,"description":"The scale for NAG. Higher values will result in a image that is more distant\n            to the negative prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"nag_scale","required":false,"type":"number"},{"default":2.5,"description":"The tau for NAG. Controls the normalization of the hidden state.\n            Higher values will result in a less aggressive normalization,\n            but may also lead to unexpected changes with respect to the original image.\n            Not recommended to change this value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"nag_tau","required":false,"type":"number"},{"default":0.25,"description":"The alpha value for NAG. This value is used as a final weighting\n            factor for steering the normalized guidance (positive and negative prompts)\n            in the direction of the positive prompt. Higher values will result in less\n            steering on the normalized guidance where lower values will result in\n            considering the positive prompt guidance more.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_alpha","required":false,"type":"number"},{"default":0.25,"description":"The proportion of steps to apply NAG. After the specified proportion\n            of steps has been iterated, the remaining steps will use original\n            attention processors in FLUX.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_end","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-08-21T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b2/bbpu6j6ryq35Wu6-WHkpA_2mmO6mnS.png","title":"FLUX.1 [dev] with Controlnets and Loras"},{"category":"image-to-image","description":"A specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.","endpoint_id":"fal-ai/flux-general/differential-diffusion","family":"Flux General","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"control_loras","required":false,"type":"json"},{"default":"[]","description":"The controlnets to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":"[]","description":"The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_unions","required":false,"type":"json"},{"default":"[]","description":"IP-Adapter to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapters","required":false,"type":"json"},{"default":"[]","description":"EasyControl Inputs to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"easycontrols","required":false,"type":"json"},{"default":null,"description":"Use an image input to influence the generation. Can be used to fill images in masked areas.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_image","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"real_cfg_scale","required":false,"type":"number"},{"default":false,"description":"Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true.\n            If using XLabs IP-Adapter v1, this will be turned on!.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_real_cfg","required":false,"type":"boolean"},{"default":false,"description":"Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_cfg_zero","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Reference-Only","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":0.65,"description":"Strength of reference_only generation. Only used if a reference image is provided.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":-3,"multiline":false,"name":"reference_strength","required":false,"type":"number"},{"default":0,"description":"The percentage of the total timesteps when the reference guidance is to bestarted.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_start","required":false,"type":"number"},{"default":1,"description":"The percentage of the total timesteps when the reference guidance is to be ended.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_end","required":false,"type":"number"},{"default":0.5,"description":"Base shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"base_shift","required":false,"type":"number"},{"default":1.15,"description":"Max shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"max_shift","required":false,"type":"number"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Specifies whether beta sigmas ought to be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_beta_schedule","required":false,"type":"boolean"},{"default":null,"description":"Sigmas schedule for the denoising process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigma_schedule","required":false,"type":"string"},{"default":"euler","description":"Scheduler for the denoising process.","enum":["euler","dpmpp_2m"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"","description":"Negative prompt to steer the image generation away from unwanted features.\n            By default, we will be using NAG for processing the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":3,"description":"The scale for NAG. Higher values will result in a image that is more distant\n            to the negative prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"nag_scale","required":false,"type":"number"},{"default":2.5,"description":"The tau for NAG. Controls the normalization of the hidden state.\n            Higher values will result in a less aggressive normalization,\n            but may also lead to unexpected changes with respect to the original image.\n            Not recommended to change this value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"nag_tau","required":false,"type":"number"},{"default":0.25,"description":"The alpha value for NAG. This value is used as a final weighting\n            factor for steering the normalized guidance (positive and negative prompts)\n            in the direction of the positive prompt. Higher values will result in less\n            steering on the normalized guidance where lower values will result in\n            considering the positive prompt guidance more.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_alpha","required":false,"type":"number"},{"default":0.25,"description":"The proportion of steps to apply NAG. After the specified proportion\n            of steps has been iterated, the remaining steps will use original\n            attention processors in FLUX.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_end","required":false,"type":"number"},{"default":null,"description":"URL of image to use as initial image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of change map.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"change_map_image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for differential diffusion. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-08-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/flux-lora/flux_general.png","title":"FLUX.1 [dev] with Controlnets and Loras"},{"category":"image-to-image","description":"FLUX General Image-to-Image is a versatile endpoint that transforms existing images with support for LoRA, ControlNet, and IP-Adapter extensions, enabling precise control over style transfer, modifications, and artistic variations through multiple guidance methods.","endpoint_id":"fal-ai/flux-general/image-to-image","family":"Flux General","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"control_loras","required":false,"type":"json"},{"default":"[]","description":"The controlnets to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":"[]","description":"The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_unions","required":false,"type":"json"},{"default":"[]","description":"IP-Adapter to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapters","required":false,"type":"json"},{"default":"[]","description":"EasyControl Inputs to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"easycontrols","required":false,"type":"json"},{"default":null,"description":"Use an image input to influence the generation. Can be used to fill images in masked areas.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_image","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"real_cfg_scale","required":false,"type":"number"},{"default":false,"description":"Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true.\n            If using XLabs IP-Adapter v1, this will be turned on!.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_real_cfg","required":false,"type":"boolean"},{"default":false,"description":"Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_cfg_zero","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Reference-Only","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":0.65,"description":"Strength of reference_only generation. Only used if a reference image is provided.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":-3,"multiline":false,"name":"reference_strength","required":false,"type":"number"},{"default":0,"description":"The percentage of the total timesteps when the reference guidance is to bestarted.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_start","required":false,"type":"number"},{"default":1,"description":"The percentage of the total timesteps when the reference guidance is to be ended.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_end","required":false,"type":"number"},{"default":0.5,"description":"Base shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"base_shift","required":false,"type":"number"},{"default":1.15,"description":"Max shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"max_shift","required":false,"type":"number"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Specifies whether beta sigmas ought to be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_beta_schedule","required":false,"type":"boolean"},{"default":null,"description":"Sigmas schedule for the denoising process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigma_schedule","required":false,"type":"string"},{"default":"euler","description":"Scheduler for the denoising process.","enum":["euler","dpmpp_2m"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"","description":"Negative prompt to steer the image generation away from unwanted features.\n            By default, we will be using NAG for processing the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":3,"description":"The scale for NAG. Higher values will result in a image that is more distant\n            to the negative prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"nag_scale","required":false,"type":"number"},{"default":2.5,"description":"The tau for NAG. Controls the normalization of the hidden state.\n            Higher values will result in a less aggressive normalization,\n            but may also lead to unexpected changes with respect to the original image.\n            Not recommended to change this value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"nag_tau","required":false,"type":"number"},{"default":0.25,"description":"The alpha value for NAG. This value is used as a final weighting\n            factor for steering the normalized guidance (positive and negative prompts)\n            in the direction of the positive prompt. Higher values will result in less\n            steering on the normalized guidance where lower values will result in\n            considering the positive prompt guidance more.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_alpha","required":false,"type":"number"},{"default":0.25,"description":"The proportion of steps to apply NAG. After the specified proportion\n            of steps has been iterated, the remaining steps will use original\n            attention processors in FLUX.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_end","required":false,"type":"number"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-08-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/flux-lora/flux_general.png","title":"FLUX.1 [dev] with Controlnets and Loras"},{"category":"image-to-image","description":"FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.","endpoint_id":"fal-ai/flux-general/inpainting","family":"Flux General","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"control_loras","required":false,"type":"json"},{"default":"[]","description":"The controlnets to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":"[]","description":"The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_unions","required":false,"type":"json"},{"default":"[]","description":"IP-Adapter to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapters","required":false,"type":"json"},{"default":"[]","description":"EasyControl Inputs to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"easycontrols","required":false,"type":"json"},{"default":null,"description":"Use an image input to influence the generation. Can be used to fill images in masked areas.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_image","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"real_cfg_scale","required":false,"type":"number"},{"default":false,"description":"Uses classical CFG as in SD1.5, SDXL, etc. Increases generation times and price when set to be true.\n            If using XLabs IP-Adapter v1, this will be turned on!.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_real_cfg","required":false,"type":"boolean"},{"default":false,"description":"Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_cfg_zero","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Reference-Only","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":0.65,"description":"Strength of reference_only generation. Only used if a reference image is provided.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":-3,"multiline":false,"name":"reference_strength","required":false,"type":"number"},{"default":0,"description":"The percentage of the total timesteps when the reference guidance is to bestarted.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_start","required":false,"type":"number"},{"default":1,"description":"The percentage of the total timesteps when the reference guidance is to be ended.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_end","required":false,"type":"number"},{"default":0.5,"description":"Base shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"base_shift","required":false,"type":"number"},{"default":1.15,"description":"Max shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"max_shift","required":false,"type":"number"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Specifies whether beta sigmas ought to be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_beta_schedule","required":false,"type":"boolean"},{"default":null,"description":"Sigmas schedule for the denoising process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigma_schedule","required":false,"type":"string"},{"default":"euler","description":"Scheduler for the denoising process.","enum":["euler","dpmpp_2m"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"","description":"Negative prompt to steer the image generation away from unwanted features.\n            By default, we will be using NAG for processing the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":3,"description":"The scale for NAG. Higher values will result in a image that is more distant\n            to the negative prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"nag_scale","required":false,"type":"number"},{"default":2.5,"description":"The tau for NAG. Controls the normalization of the hidden state.\n            Higher values will result in a less aggressive normalization,\n            but may also lead to unexpected changes with respect to the original image.\n            Not recommended to change this value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"nag_tau","required":false,"type":"number"},{"default":0.25,"description":"The alpha value for NAG. This value is used as a final weighting\n            factor for steering the normalized guidance (positive and negative prompts)\n            in the direction of the positive prompt. Higher values will result in less\n            steering on the normalized guidance where lower values will result in\n            considering the positive prompt guidance more.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_alpha","required":false,"type":"number"},{"default":0.25,"description":"The proportion of steps to apply NAG. After the specified proportion\n            of steps has been iterated, the remaining steps will use original\n            attention processors in FLUX.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_end","required":false,"type":"number"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The mask to area to Inpaint in.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-08-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/flux-lora/flux_general.png","title":"FLUX.1 [dev] with Controlnets and Loras"},{"category":"image-to-image","description":"A general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.","endpoint_id":"fal-ai/flux-general/rf-inversion","family":"Flux General","inputs":[{"default":null,"description":"The prompt to edit the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The LoRAs to use for the image generation which use a control image. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"control_loras","required":false,"type":"json"},{"default":"[]","description":"The controlnets to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":"[]","description":"The controlnet unions to use for the image generation. Only one controlnet is supported at the moment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_unions","required":false,"type":"json"},{"default":"[]","description":"EasyControl Inputs to use for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"easycontrols","required":false,"type":"json"},{"default":null,"description":"Use an image input to influence the generation. Can be used to fill images in masked areas.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_image","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"Uses CFG-zero init sampling as in https://arxiv.org/abs/2503.18886.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_cfg_zero","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Reference-Only","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":0.65,"description":"Strength of reference_only generation. Only used if a reference image is provided.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":-3,"multiline":false,"name":"reference_strength","required":false,"type":"number"},{"default":0,"description":"The percentage of the total timesteps when the reference guidance is to bestarted.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_start","required":false,"type":"number"},{"default":1,"description":"The percentage of the total timesteps when the reference guidance is to be ended.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"reference_end","required":false,"type":"number"},{"default":0.5,"description":"Base shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"base_shift","required":false,"type":"number"},{"default":1.15,"description":"Max shift for the scheduled timesteps","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"max_shift","required":false,"type":"number"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Specifies whether beta sigmas ought to be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_beta_schedule","required":false,"type":"boolean"},{"default":null,"description":"Sigmas schedule for the denoising process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigma_schedule","required":false,"type":"string"},{"default":"euler","description":"Scheduler for the denoising process.","enum":["euler","dpmpp_2m"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"","description":"Negative prompt to steer the image generation away from unwanted features.\n            By default, we will be using NAG for processing the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":3,"description":"The scale for NAG. Higher values will result in a image that is more distant\n            to the negative prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"nag_scale","required":false,"type":"number"},{"default":2.5,"description":"The tau for NAG. Controls the normalization of the hidden state.\n            Higher values will result in a less aggressive normalization,\n            but may also lead to unexpected changes with respect to the original image.\n            Not recommended to change this value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"nag_tau","required":false,"type":"number"},{"default":0.25,"description":"The alpha value for NAG. This value is used as a final weighting\n            factor for steering the normalized guidance (positive and negative prompts)\n            in the direction of the positive prompt. Higher values will result in less\n            steering on the normalized guidance where lower values will result in\n            considering the positive prompt guidance more.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_alpha","required":false,"type":"number"},{"default":0.25,"description":"The proportion of steps to apply NAG. After the specified proportion\n            of steps has been iterated, the remaining steps will use original\n            attention processors in FLUX.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"nag_end","required":false,"type":"number"},{"default":null,"description":"URL of image to be edited","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.6,"description":"The controller guidance (gamma) used in the creation of structured noise.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0.01,"multiline":false,"name":"controller_guidance_forward","required":false,"type":"number"},{"default":0.75,"description":"The controller guidance (eta) used in the denoising process.Using values closer to 1 will result in an image closer to input.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0.01,"multiline":false,"name":"controller_guidance_reverse","required":false,"type":"number"},{"default":0,"description":"Timestep to start guidance during reverse process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_guidance_start","required":false,"type":"integer"},{"default":8,"description":"Timestep to stop guidance during reverse process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_guidance_end","required":false,"type":"integer"},{"default":"constant","description":"Scheduler for applying reverse guidance.","enum":["constant","linear_increase","linear_decrease"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_guidance_schedule","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-09-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/flux-lora/flux_general.png","title":"FLUX.1 [dev] with Controlnets and Loras"},{"category":"image-to-image","description":"Fast endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image editing using pre-trained LoRA adaptations for specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-kontext-lora","family":"Flux Kontext","inputs":[{"default":null,"description":"The URL of the image to edit.\n\nMax width: 14142px, Max height: 14142px, Timeout: 20s","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"match_input","description":"Determines how the output resolution is set for image editing.\n            - `auto`: The model selects an optimal resolution from a predefined set that best matches the input image's aspect ratio. This is the recommended setting for most use cases as it's what the model was trained on.\n            - `match_input`: The model will attempt to use the same resolution as the input image. The resolution will be adjusted to be compatible with the model's requirements (e.g. dimensions must be multiples ","enum":["auto","match_input","1:1","16:9","21:9","3:2","2:3","4:5","5:4","3:4","4:3","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution_mode","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","timings","prompt"],"pricing":"","published_at":"2025-06-25T21:13:19.794000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-3.jpeg","title":"Flux Kontext Lora"},{"category":"image-to-image","description":"Fast inpainting endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image inpainting with reference images, while using pre-trained LoRA adaptations for specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-kontext-lora/inpaint","family":"Flux Kontext","inputs":[{"default":null,"description":"The URL of the image to be inpainted.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt for the image to image task.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"The URL of the reference image for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":0.88,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","timings","prompt"],"pricing":"","published_at":"2025-07-29T16:56:50.213000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Flux Kontext Lora"},{"category":"text-to-image","description":"Super fast text-to-image endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-kontext-lora/text-to-image","family":"Flux Kontext","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","timings","prompt"],"pricing":"","published_at":"2025-06-25T21:15:54.503000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"Flux Kontext Lora"},{"category":"training","description":"LoRA trainer for FLUX.1 Kontext [dev]","endpoint_id":"fal-ai/flux-kontext-trainer","family":"Flux Kontext","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n        The zip should contain pairs of images. The images should be named:\n\n        ROOT_start.EXT and ROOT_end.EXT\n        For example:\n        photo_start.jpg and photo_end.jpg\n\n        The zip can also contain a text file for each image pair. The text file should be named:\n        ROOT.txt\n        For example:\n        photo.txt\n\n        This text file can be used to specify the edit instructions for the image pair.\n\n        If no text file is provided, the","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Number of steps to train for","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":2,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":0.0001,"description":"Learning Rate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["config_file","diffusers_lora_file"],"pricing":"Your request will cost $2.5 per 1000-step training run. It scales per step, so a 2000-step training run costs $5. Note: 500 steps is the minimum step count, which will cost $1.25.","published_at":"2025-06-26T13:55:28.583000+00:00","thumbnail":"https://v3.fal.media/files/monkey/pYXiffttc2Skv36wflufu_dec4efe0d27e4527b64acfbc0e91536a.jpg","title":"Flux Kontext Trainer"},{"category":"image-to-image","description":"Frontier image editing model.","endpoint_id":"fal-ai/flux-kontext/dev","family":"Flux Kontext","inputs":[{"default":null,"description":"The prompt to edit the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to edit.\n\nMax width: 14142px, Max height: 14142px, Timeout: 20s","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output format","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"match_input","description":"Determines how the output resolution is set for image editing.\n            - `auto`: The model selects an optimal resolution from a predefined set that best matches the input image's aspect ratio. This is the recommended setting for most use cases as it's what the model was trained on.\n            - `match_input`: The model will attempt to use the same resolution as the input image. The resolution will be adjusted to be compatible with the model's requirements (e.g. dimensions must be multiples ","enum":["auto","match_input","1:1","16:9","21:9","3:2","2:3","4:5","5:4","3:4","4:3","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution_mode","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","timings","prompt"],"pricing":"","published_at":"2025-05-28T18:38:52.637000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"FLUX.1 Kontext [dev]"},{"category":"text-to-image","description":"Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-krea-lora","family":"Flux Krea","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-08-01T23:35:24.369000+00:00","thumbnail":"https://v3.fal.media/files/tiger/fB-RsJ-BW4mrUVAH8oKF2_LOuGVDgg07U8OWbOhhMFt_d6ab08c96ab94da8b6d3e979d634af16.jpg","title":"FLUX.1 Krea [dev] with LoRAs"},{"category":"image-to-image","description":"FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.","endpoint_id":"fal-ai/flux-krea-lora/image-to-image","family":"Flux Krea","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-08-01T23:32:55.146000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound.jpg","title":"FLUX.1 Krea [dev] with LoRAs"},{"category":"image-to-image","description":"Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-krea-lora/inpainting","family":"Flux Krea","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The mask to area to Inpaint in.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-08-01T23:38:18.120000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"FLUX.1 Krea [dev] Inpainting with LoRAs"},{"category":"text-to-image","description":"Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-krea-lora/stream","family":"Flux Krea","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-08-01T23:39:51.003000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a61/T4z71gOSeWv0wALDdi2-b_qVoN8eec.png","title":"Flux Krea Lora"},{"category":"text-to-image","description":"Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-lora","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2024-08-01T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91af/UMrx6t6mc59z33d20WIQP_iBIZYKKq.png","title":"FLUX.1 [dev] with LoRAs"},{"category":"image-to-image","description":"Utilize Flux.1 [dev] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.","endpoint_id":"fal-ai/flux-lora-canny","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for canny input","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-01-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux_lora.jpg","title":"FLUX.1 [dev] Canny with LoRAs"},{"category":"image-to-image","description":"Generate high-quality images from depth maps using Flux.1 [dev] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.","endpoint_id":"fal-ai/flux-lora-depth","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for depth input","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-11-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux_lora.jpg","title":"FLUX.1 [dev] Depth with LoRAs"},{"category":"training","description":"Train styles, people and other subjects at blazing speeds.","endpoint_id":"fal-ai/flux-lora-fast-training","family":"Flux Lora","inputs":[{"default":null,"description":"URL to zip archive with images. Try to use at least 4 images in general the more the better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"images_data_url","required":true,"type":"string"},{"default":null,"description":"Trigger word to be used in the captions. If None, a trigger word will not be used.\n        If no captions are provide the trigger_word will be used instead of captions. If captions are the trigger word will not be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"trigger_word","required":false,"type":"string"},{"default":true,"description":"If True segmentation masks will be used in the weight the training loss. For people a face mask is used if possible.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"create_masks","required":false,"type":"boolean"},{"default":null,"description":"Number of steps to train the LoRA on.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":1,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":false,"description":"If True, the training will be for a style. This will deactivate segmentation, captioning and will use trigger word instead. Use the trigger word to specify the style.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_style","required":false,"type":"boolean"},{"default":false,"description":"Specifies whether the input data is already in a processed format. When set to False (default), the system expects raw input where image files and their corresponding caption files share the same name (e.g., 'photo.jpg' and 'photo.txt'). Set to True if your data is already in a preprocessed format.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_input_format_already_preprocessed","required":false,"type":"boolean"},{"default":null,"description":"The format of the archive. If not specified, the format will be inferred from the URL.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"data_archive_format","required":false,"type":"string"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file","debug_preprocessed_output"],"pricing":"Your request will cost $2 per training run (scales linearly with steps). For $2 you can run this model with approximately 1 times.","published_at":"2025-01-01T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/video-training.webp","title":"Train Flux LoRA"},{"category":"image-to-image","description":"FLUX.1 [dev] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-lora-fill","family":"Flux Lora","inputs":[{"default":"","description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":30,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":28,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for fill operation","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask to area to Inpaint in.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":true,"description":"Specifies whether to paste-back the original image onto to the non-inpainted areas of the output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"paste_back","required":false,"type":"boolean"},{"default":null,"description":"Use an image fill input to fill in particular images into the masked area.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_image","required":false,"type":"json"},{"default":false,"description":"Resizes the image back to the original size. Use when you wish to preserve the exact image size as the originally provided image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resize_to_original","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["has_nsfw_concepts","images","prompt","timings","seed"],"pricing":"","published_at":"2024-12-19T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux_lora.jpg","title":"FLUX.1 [dev] Fill with LoRAs"},{"category":"training","description":"FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.","endpoint_id":"fal-ai/flux-lora-portrait-trainer","family":"Flux Lora","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images, although more is better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image file it corresponds to.\n\n        The captions can include a special string `[trigger]`. If a trigger_word is specified, it will replace `[trigger]` in the captions.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"images_data_url","required":true,"type":"string"},{"default":null,"description":"Trigger phrase to be used in the captions. If None, a trigger word will not be used.\n        If no captions are provide the trigger_work will be used instead of captions. If captions are provided, the trigger word will replace the `[trigger]` string in the captions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"trigger_phrase","required":false,"type":"string"},{"default":9e-05,"description":"Learning rate to use for training.","enum":null,"is_list":false,"max":0.001,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":2500,"description":"Number of steps to train the LoRA on.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":1,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":true,"description":"If True, multiresolution training will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multiresolution_training","required":false,"type":"boolean"},{"default":true,"description":"If True, the subject will be cropped from the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subject_crop","required":false,"type":"boolean"},{"default":null,"description":"The format of the archive. If not specified, the format will be inferred from the URL.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"data_archive_format","required":false,"type":"string"},{"default":"","description":"URL to a checkpoint to resume training from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resume_from_checkpoint","required":false,"type":"string"},{"default":false,"description":"If True, masks will be created for the subject.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"create_masks","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["config_file","diffusers_lora_file"],"pricing":"Your request will cost $0.0024 cents per step. A minimum of 1000 steps will be billed.","published_at":"2024-11-07T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b1/vXd9M_4clrJurIFT2rpUz_CT0b31Lr.png","title":"Train Flux LoRAs For Portraits"},{"category":"image-to-image","description":"FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.","endpoint_id":"fal-ai/flux-lora/image-to-image","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2024-08-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/h2glDvCl5RvtgjNx_-5qY.jpeg","title":"FLUX.1 [dev] with LoRAs"},{"category":"text-to-image","description":"Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-lora/inpainting","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The mask to area to Inpaint in.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2024-09-18T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux_lora.jpg","title":"FLUX.1 [dev] Inpainting with LoRAs"},{"category":"text-to-image","description":"Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-lora/stream","family":"Flux Lora","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["timings","seed","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2025-05-15T22:28:51.397000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-5.jpeg","title":"Flux Lora"},{"category":"image-to-image","description":"FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.","endpoint_id":"fal-ai/flux-pro/kontext","family":"Flux Pro Kontext","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-28T18:30:52.718000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-2.jpg","title":"FLUX.1 Kontext [pro]"},{"category":"image-to-image","description":"FLUX.1 Kontext [max] is a model with greatly improved prompt adherence and typography generation meet premium consistency for editing without compromise on speed.","endpoint_id":"fal-ai/flux-pro/kontext/max","family":"Flux Pro Kontext","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-29T04:53:59.306000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ac/S_XdqqwSzXvTx90JvwNqA_74St34QO.png","title":"FLUX.1 Kontext [max]"},{"category":"image-to-image","description":"Experimental version of FLUX.1 Kontext [max] with multi image handling capabilities","endpoint_id":"fal-ai/flux-pro/kontext/max/multi","family":"Flux Pro Kontext","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-29T19:13:44.033000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ad/YTgMmEhBRGtsGx2bg21D6_tcu36I7F.png","title":"FLUX.1 Kontext [max]"},{"category":"text-to-image","description":"FLUX.1 Kontext [max] text-to-image is a new premium model brings maximum performance across all aspects – greatly improved prompt adherence.","endpoint_id":"fal-ai/flux-pro/kontext/max/text-to-image","family":"Flux Pro Kontext","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-29T04:52:29.523000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"FLUX.1 Kontext [max]"},{"category":"image-to-image","description":"Experimental version of FLUX.1 Kontext [pro] with multi image handling capabilities","endpoint_id":"fal-ai/flux-pro/kontext/multi","family":"Flux Pro Kontext","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-29T19:10:26.719000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"FLUX.1 Kontext [pro]"},{"category":"text-to-image","description":"The FLUX.1 Kontext [pro] text-to-image delivers state-of-the-art image generation results with unprecedented prompt following, photorealistic rendering, and flawless typography.","endpoint_id":"fal-ai/flux-pro/kontext/text-to-image","family":"Flux Pro Kontext","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-28T19:25:39.115000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ad/tawaEEjSMOh_9TnYUkmy0_dDkJYEiR.png","title":"FLUX.1 Kontext [pro]"},{"category":"text-to-image","description":"FLUX1.1 [pro] is an enhanced version of FLUX.1 [pro], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.","endpoint_id":"fal-ai/flux-pro/v1.1","family":"Flux Pro 1.1","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-01-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/turbo_thumbnail.jpg","title":"FLUX1.1 [pro]"},{"category":"text-to-image","description":"FLUX1.1 [pro] ultra is the newest version of FLUX1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.","endpoint_id":"fal-ai/flux-pro/v1.1-ultra","family":"Flux Pro 1.1","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The image URL to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":0.1,"description":"The strength of the image prompt, between 0 and 1.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_prompt_strength","required":false,"type":"number"},{"default":"16:9","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Generate less processed, more natural-looking images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"raw","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-12-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-pro-v1-1-ultra.webp","title":"FLUX1.1 [pro] ultra"},{"category":"text-to-image","description":"FLUX1.1 [pro] ultra fine-tuned is the newest version of FLUX1.1 [pro] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.","endpoint_id":"fal-ai/flux-pro/v1.1-ultra-finetuned","family":"Flux Pro 1.1","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The image URL to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":0.1,"description":"The strength of the image prompt, between 0 and 1.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_prompt_strength","required":false,"type":"number"},{"default":"16:9","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Generate less processed, more natural-looking images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"raw","required":false,"type":"boolean"},{"default":null,"description":"References your specific model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"finetune_id","required":true,"type":"string"},{"default":null,"description":"Controls finetune influence.\n        Increase this value if your target concept isn't showing up strongly enough.\n        The optimal setting depends on your finetune and prompt","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"finetune_strength","required":true,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-01-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-pro-11-ultra.webp","title":"FLUX1.1 [pro] ultra Fine-tuned"},{"category":"image-to-image","description":"FLUX1.1 [pro] ultra Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-pro/v1.1-ultra/redux","family":"Flux Pro 1.1","inputs":[{"default":"","description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.1,"description":"The strength of the image prompt, between 0 and 1.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_prompt_strength","required":false,"type":"number"},{"default":"16:9","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Generate less processed, more natural-looking images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"raw","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-11-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-pro-11-ultra.webp","title":"FLUX1.1 [pro] ultra Redux"},{"category":"image-to-image","description":"FLUX1.1 [pro] Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-pro/v1.1/redux","family":"Flux Pro 1.1","inputs":[{"default":"","description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-11-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/turbo_thumbnail.jpg","title":"FLUX1.1 [pro] Redux"},{"category":"image-to-image","description":"Latest object erasing model from Black Forest Labs. Remove undesired objects, texts from images.","endpoint_id":"fal-ai/flux-pro/v1/erase","family":"","inputs":[{"default":null,"description":"The URL of the input image to erase content from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of a black/white mask image where white (255) marks pixels to erase and black (0) marks pixels to keep. Needs to match the dimensions of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_url","required":true,"type":"string"},{"default":10,"description":"Number of pixels to expand the mask edges by. Higher values produce cleaner erase results around the masked region.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":0,"multiline":false,"name":"dilate_pixels","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"Your request will cost $0.03 for the first megapixel generated, then $0.004 for each subsequent megapixel. Each reference megapixel also costs $0.004 set at 3 MP minimum.","published_at":"2026-05-21T20:04:52.011000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b202c/YGjsDrgyeEZOfCM1_iVVF_afd5d6b09ebb42989964c331657d5587.jpg","title":"Flux Pro Erase"},{"category":"image-to-image","description":"FLUX.1 [pro] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-pro/v1/fill","family":"Flux Pro 1","inputs":[{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask URL to inpaint the image. Needs to match the dimensions of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-11-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fluxpro.jpg","title":"FLUX.1 [pro] Fill"},{"category":"image-to-image","description":"FLUX.1 [pro] Fill Fine-tuned is a high-performance endpoint for the FLUX.1 [pro] model with a fine-tuned LoRA that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux-pro/v1/fill-finetuned","family":"Flux Pro 1","inputs":[{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Whether to enhance the prompt for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask URL to inpaint the image. Needs to match the dimensions of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"References your specific model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"finetune_id","required":true,"type":"string"},{"default":null,"description":"Controls finetune influence.\n        Increase this value if your target concept isn't showing up strongly enough.\n        The optimal setting depends on your finetune and prompt","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"finetune_strength","required":true,"type":"number"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-01-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fluxpro.jpg","title":"FLUX.1 [pro] Fill Fine-tuned"},{"category":"image-to-image","description":"Generate virtual try-on results from a person image plus one or more garment references.","endpoint_id":"fal-ai/flux-pro/v1/vto","family":"","inputs":[{"default":null,"description":"Natural-language styling instructions describing how the garment should be worn on the person (e.g. tucked in, layered, sleeves rolled up).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the person image that the garment will be applied onto. The output keeps this image's aspect ratio. Maximum 2 megapixels; recommended under 1 MP.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"human_image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the garment reference image. Maximum 1 megapixel; recommended around 0.5 MP. Multiple garments must be merged into a single composite image before submission.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"garment_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same input will output the same image every time. If not provided, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"Your request will cost $0.0375 for the first input megapixel, plus $0.005 per extra input megapixel and $0.005 per output megapixel, rounded up to the nearest megapixel. Each input image is rounded up independently before being summed. For example, two 1024x1024 input images with a 1024x1024 output will cost $0.0475 ($0.0375 for the first input megapixel + $0.005 for the second input megapixel + $0.005 for the output megapixel).","published_at":"2026-05-28T16:46:06.236000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c03aa/mE1fcmjHXlY9mzOt47JMW_ca02b95a28d248348b29f89d5687fcaf.jpg","title":"FLUX Virtual Try-On"},{"category":"image-to-image","description":"An endpoint for personalized image generation using Flux as per given description.","endpoint_id":"fal-ai/flux-pulid","family":"Flux Pluid","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of image to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":20,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"","description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0,"description":"The number of steps to start the CFG from.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"start_step","required":false,"type":"integer"},{"default":1,"description":"The weight of the CFG loss.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"true_cfg","required":false,"type":"number"},{"default":1,"description":"The weight of the ID loss.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"id_weight","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"128","description":"The maximum sequence length for the model.","enum":["128","256","512"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"max_sequence_length","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-10-29T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-pulid.webp","title":"PuLID Flux"},{"category":"text-to-image","description":"Super fast endpoint for the FLUX.1 [schnell] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.","endpoint_id":"fal-ai/flux-subject","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of image of the subject","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["images","timings","prompt","seed","has_nsfw_concepts"],"pricing":"","published_at":"2024-08-01T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-subject.webp","title":"FLUX.1 Subject"},{"category":"image-to-image","description":"Flux Vision Upscaler for magnify/upscaling images with high fidelity and creativity.","endpoint_id":"fal-ai/flux-vision-upscaler","family":"","inputs":[{"default":null,"description":"The URL of the image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":2,"description":"The upscale factor (1-4x).","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":null,"description":"The seed to use for the upscale. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":0.3,"description":"The creativity of the model. The higher the creativity, the more the model will deviate from the original. Refers to the denoise strength of the sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"creativity","required":false,"type":"number"},{"default":1,"description":"CFG/guidance scale (1-4). Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"guidance","required":false,"type":"number"},{"default":20,"description":"Number of inference steps (4-50).","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"image","output_props":["seed","timings","image","caption"],"pricing":"","published_at":"2025-11-02T21:17:39.501000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/7DKYn-EKEd3lthAymIaZ4_54bca98af99240488e7d2fcc2a2dcad8.jpg","title":"Flux Vision Upscaler"},{"category":"text-to-image","description":"FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux/dev","family":"Flux Dev","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-04-01T18:10:42.284000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"FLUX.1 [dev]"},{"category":"image-to-image","description":"FLUX.1 Image-to-Image is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux/dev/image-to-image","family":"Flux Dev","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2024-07-11T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91a9/up8aXYeFDjcRbQZDxV7vK_Jo37PJhg.png","title":"FLUX.1 [dev]"},{"category":"image-to-image","description":"FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux/dev/redux","family":"Flux Dev","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2024-11-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-dev-thumb.webp","title":"FLUX.1 [dev] Redux"},{"category":"text-to-image","description":"FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux/krea","family":"Flux Krea","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-07-30T14:24:29.026000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"FLUX.1 Krea [dev]"},{"category":"image-to-image","description":"FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux/krea/image-to-image","family":"Flux Krea","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-07-30T14:27:21.110000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-4.jpeg","title":"FLUX.1 Krea [dev]"},{"category":"image-to-image","description":"FLUX.1 Krea [dev] Redux is a high-performance endpoint for the FLUX.1 Krea [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux/krea/redux","family":"Flux Krea","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-07-30T14:25:55.003000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale.jpg","title":"FLUX.1 Krea [dev] Redux"},{"category":"text-to-image","description":"FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use.","endpoint_id":"fal-ai/flux/schnell","family":"Flux Schnell","inputs":[{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2024-11-25T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9af64d/GxvCUPd3gO-MSYcy06g0x_1641cfe028c2429b8e12e4fc320eb0a8.jpg","title":"FLUX.1 [schnell]"},{"category":"image-to-image","description":"FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.","endpoint_id":"fal-ai/flux/schnell/redux","family":"Flux Schnell","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2024-11-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/flux-schnell-thumb.webp","title":"FLUX.1 [schnell] Redux"},{"category":"text-to-image","description":"FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux/srpo","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-09-15T23:01:28.380000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922c/6Vo52961ugiywy7MrAPfh_M5gEUDZC.png","title":"FLUX.1 SRPO [dev]"},{"category":"image-to-image","description":"FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.","endpoint_id":"fal-ai/flux/srpo/image-to-image","family":"","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n        will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n        the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"The speed of the generation. The higher the speed, the faster the generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Black Forest Labs","output_kind":"images","output_props":["seed","timings","images","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-09-15T23:04:24.590000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92e1/NW7Y_ttxvgm8Qrp0e5gu7_7qfYSZby.png","title":"FLUX.1 SRPO [dev]"},{"category":"text-to-image","description":"Default parameters with automated optimizations and quality improvements.","endpoint_id":"fal-ai/fooocus","family":"","inputs":[{"default":"","description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":["Fooocus Sharp","Fooocus Enhance","Fooocus V2"],"description":"The style to use.","enum":["Fooocus V2","Fooocus Enhance","Fooocus Sharp","Fooocus Semi Realistic","Fooocus Masterpiece","Fooocus Photograph","Fooocus Negative","Fooocus Cinematic","SAI 3D Model","SAI Analog Film","SAI Anime","SAI Cinematic","SAI Comic Book","SAI Craft Clay","SAI Digital Art","SAI Enhance","SAI Fantasy Art","SAI Isometric","SAI Line Art","SAI Lowpoly","SAI Neonpunk","SAI Origami","SAI Photographic","SAI Pixel Art","SAI Texture","MRE Cinematic Dynamic","MRE Spontaneous Picture","MRE Artistic Vision","MRE Dark Dream","MRE Gloomy Art","MRE Bad Dream","MRE Underground","MRE Surreal Painting","MRE Dynamic Illustration","MRE Undead Art","MRE Elemental Art","MRE Space Art","MRE Ancient Illustration","MRE Brave Art","MRE Heroic Fantasy","MRE Dark Cyberpunk","MRE Lyrical Geometry","MRE Sumi E Symbolic","MRE Sumi E Detailed","MRE Manga","MRE Anime","MRE Comic","Ads Advertising","Ads Automotive","Ads Corporate","Ads Fashion Editorial","Ads Food Photography","Ads Gourmet Food Photography","Ads Luxury","Ads Real Estate","Ads Retail","Artstyle Abstract","Artstyle Abstract Expressionism","Artstyle Art Deco","Artstyle Art Nouveau","Artstyle Constructivist","Artstyle Cubist","Artstyle Expressionist","Artstyle Graffiti","Artstyle Hyperrealism","Artstyle Impressionist","Artstyle Pointillism","Artstyle Pop Art","Artstyle Psychedelic","Artstyle Renaissance","Artstyle Steampunk","Artstyle Surrealist","Artstyle Typography","Artstyle Watercolor","Futuristic Biomechanical","Futuristic Biomechanical Cyberpunk","Futuristic Cybernetic","Futuristic Cybernetic Robot","Futuristic Cyberpunk Cityscape","Futuristic Futuristic","Futuristic Retro Cyberpunk","Futuristic Retro Futurism","Futuristic Sci Fi","Futuristic Vaporwave","Game Bubble Bobble","Game Cyberpunk Game","Game Fighting Game","Game Gta","Game Mario","Game Minecraft","Game Pokemon","Game Retro Arcade","Game Retro Game","Game Rpg Fantasy Game","Game Strategy Game","Game Streetfighter","Game Zelda","Misc Architectural","Misc Disco","Misc Dreamscape","Misc Dystopian","Misc Fairy Tale","Misc Gothic","Misc Grunge","Misc Horror","Misc Kawaii","Misc Lovecraftian","Misc Macabre","Misc Manga","Misc Metropolis","Misc Minimalist","Misc Monochrome","Misc Nautical","Misc Space","Misc Stained Glass","Misc Techwear Fashion","Misc Tribal","Misc Zentangle","Papercraft Collage","Papercraft Flat Papercut","Papercraft Kirigami","Papercraft Paper Mache","Papercraft Paper Quilling","Papercraft Papercut Collage","Papercraft Papercut Shadow Box","Papercraft Stacked Papercut","Papercraft Thick Layered Papercut","Photo Alien","Photo Film Noir","Photo Glamour","Photo Hdr","Photo Iphone Photographic","Photo Long Exposure","Photo Neon Noir","Photo Silhouette","Photo Tilt Shift","Cinematic Diva","Abstract Expressionism","Academia","Action Figure","Adorable 3D Character","Adorable Kawaii","Art Deco","Art Nouveau","Astral Aura","Avant Garde","Baroque","Bauhaus Style Poster","Blueprint Schematic Drawing","Caricature","Cel Shaded Art","Character Design Sheet","Classicism Art","Color Field Painting","Colored Pencil Art","Conceptual Art","Constructivism","Cubism","Dadaism","Dark Fantasy","Dark Moody Atmosphere","Dmt Art Style","Doodle Art","Double Exposure","Dripping Paint Splatter Art","Expressionism","Faded Polaroid Photo","Fauvism","Flat 2d Art","Fortnite Art Style","Futurism","Glitchcore","Glo Fi","Googie Art Style","Graffiti Art","Harlem Renaissance Art","High Fashion","Idyllic","Impressionism","Infographic Drawing","Ink Dripping Drawing","Japanese Ink Drawing","Knolling Photography","Light Cheery Atmosphere","Logo Design","Luxurious Elegance","Macro Photography","Mandola Art","Marker Drawing","Medievalism","Minimalism","Neo Baroque","Neo Byzantine","Neo Futurism","Neo Impressionism","Neo Rococo","Neoclassicism","Op Art","Ornate And Intricate","Pencil Sketch Drawing","Pop Art 2","Rococo","Silhouette Art","Simple Vector Art","Sketchup","Steampunk 2","Surrealism","Suprematism","Terragen","Tranquil Relaxing Atmosphere","Sticker Designs","Vibrant Rim Light","Volumetric Lighting","Watercolor 2","Whimsical And Playful","Mk Chromolithography","Mk Cross Processing Print","Mk Dufaycolor Photograph","Mk Herbarium","Mk Punk Collage","Mk Mosaic","Mk Van Gogh","Mk Coloring Book","Mk Singer Sargent","Mk Pollock","Mk Basquiat","Mk Andy Warhol","Mk Halftone Print","Mk Gond Painting","Mk Albumen Print","Mk Aquatint Print","Mk Anthotype Print","Mk Inuit Carving","Mk Bromoil Print","Mk Calotype Print","Mk Color Sketchnote","Mk Cibulak Porcelain","Mk Alcohol Ink Art","Mk One Line Art","Mk Blacklight Paint","Mk Carnival Glass","Mk Cyanotype Print","Mk Cross Stitching","Mk Encaustic Paint","Mk Embroidery","Mk Gyotaku","Mk Luminogram","Mk Lite Brite Art","Mk Mokume Gane","Pebble Art","Mk Palekh","Mk Suminagashi","Mk Scrimshaw","Mk Shibori","Mk Vitreous Enamel","Mk Ukiyo E","Mk Vintage Airline Poster","Mk Vintage Travel Poster","Mk Bauhaus Style","Mk Afrofuturism","Mk Atompunk","Mk Constructivism","Mk Chicano Art","Mk De Stijl","Mk Dayak Art","Mk Fayum Portrait","Mk Illuminated Manuscript","Mk Kalighat Painting","Mk Madhubani Painting","Mk Pictorialism","Mk Pichwai Painting","Mk Patachitra Painting","Mk Samoan Art Inspired","Mk Tlingit Art","Mk Adnate Style","Mk Ron English Style","Mk Shepard Fairey Style"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"enum"},{"default":"Extreme Speed","description":"You can choose Speed or Quality","enum":["Speed","Quality","Extreme Speed","Lightning"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"performance","required":false,"type":"enum"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"The sharpness of the generated image. Use it to control how sharp the generated\n            image should be. Higher value means image and texture are sharper.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"sharpness","required":false,"type":"number"},{"default":"1024x1024","description":"The size of the generated image. You can choose between some presets or\n            custom height and width that **must be multiples of 8**.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"aspect_ratio","required":false,"type":"string"},{"default":1,"description":"Number of images to generate in one request","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"[{\"path\": \"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors\", \"scale\": 0.1}]","description":"The LoRAs to use for the image generation. You can use up to 5 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"None","description":"Refiner (SDXL or SD 1.5)","enum":["None","realisticVisionV60B1_v51VAE.safetensors"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refiner_model","required":false,"type":"enum"},{"default":0.8,"description":"Use 0.4 for SD1.5 realistic models; 0.667 for SD1.5 anime models\n            0.8 for XL-refiners; or any value for switching two SDXL models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"refiner_switch","required":false,"type":"number"},{"default":"jpeg","description":"The format of the generated image.","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The image to use as a reference for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"control_image_url","required":false,"type":"string"},{"default":"PyraCanny","description":"The type of image control","enum":["ImagePrompt","PyraCanny","CPDS","FaceSwap"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"control_type","required":false,"type":"enum"},{"default":1,"description":"The strength of the control image. Use it to control how much the generated image\n            should look like the control image.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"control_image_weight","required":false,"type":"number"},{"default":1,"description":"The stop at value of the control image. Use it to control how much the generated image\n            should look like the control image.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_image_stop_at","required":false,"type":"number"},{"default":null,"description":"The image to use as a reference for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"inpaint_image_url","required":false,"type":"string"},{"default":null,"description":"The image to use as a mask for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"},{"default":false,"description":"Mixing Image Prompt And Inpaint","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mixing_image_prompt_and_inpaint","required":false,"type":"boolean"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2023-11-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/fooocus/fal_ai_fooocus_cyberpunk-city.jpeg","title":"Fooocus"},{"category":"text-to-image","description":"Default parameters with automated optimizations and quality improvements.","endpoint_id":"fal-ai/fooocus/image-prompt","family":"","inputs":[{"default":"","description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":["Fooocus Sharp","Fooocus Enhance","Fooocus V2"],"description":"The style to use.","enum":["Fooocus V2","Fooocus Enhance","Fooocus Sharp","Fooocus Semi Realistic","Fooocus Masterpiece","Fooocus Photograph","Fooocus Negative","Fooocus Cinematic","SAI 3D Model","SAI Analog Film","SAI Anime","SAI Cinematic","SAI Comic Book","SAI Craft Clay","SAI Digital Art","SAI Enhance","SAI Fantasy Art","SAI Isometric","SAI Line Art","SAI Lowpoly","SAI Neonpunk","SAI Origami","SAI Photographic","SAI Pixel Art","SAI Texture","MRE Cinematic Dynamic","MRE Spontaneous Picture","MRE Artistic Vision","MRE Dark Dream","MRE Gloomy Art","MRE Bad Dream","MRE Underground","MRE Surreal Painting","MRE Dynamic Illustration","MRE Undead Art","MRE Elemental Art","MRE Space Art","MRE Ancient Illustration","MRE Brave Art","MRE Heroic Fantasy","MRE Dark Cyberpunk","MRE Lyrical Geometry","MRE Sumi E Symbolic","MRE Sumi E Detailed","MRE Manga","MRE Anime","MRE Comic","Ads Advertising","Ads Automotive","Ads Corporate","Ads Fashion Editorial","Ads Food Photography","Ads Gourmet Food Photography","Ads Luxury","Ads Real Estate","Ads Retail","Artstyle Abstract","Artstyle Abstract Expressionism","Artstyle Art Deco","Artstyle Art Nouveau","Artstyle Constructivist","Artstyle Cubist","Artstyle Expressionist","Artstyle Graffiti","Artstyle Hyperrealism","Artstyle Impressionist","Artstyle Pointillism","Artstyle Pop Art","Artstyle Psychedelic","Artstyle Renaissance","Artstyle Steampunk","Artstyle Surrealist","Artstyle Typography","Artstyle Watercolor","Futuristic Biomechanical","Futuristic Biomechanical Cyberpunk","Futuristic Cybernetic","Futuristic Cybernetic Robot","Futuristic Cyberpunk Cityscape","Futuristic Futuristic","Futuristic Retro Cyberpunk","Futuristic Retro Futurism","Futuristic Sci Fi","Futuristic Vaporwave","Game Bubble Bobble","Game Cyberpunk Game","Game Fighting Game","Game Gta","Game Mario","Game Minecraft","Game Pokemon","Game Retro Arcade","Game Retro Game","Game Rpg Fantasy Game","Game Strategy Game","Game Streetfighter","Game Zelda","Misc Architectural","Misc Disco","Misc Dreamscape","Misc Dystopian","Misc Fairy Tale","Misc Gothic","Misc Grunge","Misc Horror","Misc Kawaii","Misc Lovecraftian","Misc Macabre","Misc Manga","Misc Metropolis","Misc Minimalist","Misc Monochrome","Misc Nautical","Misc Space","Misc Stained Glass","Misc Techwear Fashion","Misc Tribal","Misc Zentangle","Papercraft Collage","Papercraft Flat Papercut","Papercraft Kirigami","Papercraft Paper Mache","Papercraft Paper Quilling","Papercraft Papercut Collage","Papercraft Papercut Shadow Box","Papercraft Stacked Papercut","Papercraft Thick Layered Papercut","Photo Alien","Photo Film Noir","Photo Glamour","Photo Hdr","Photo Iphone Photographic","Photo Long Exposure","Photo Neon Noir","Photo Silhouette","Photo Tilt Shift","Cinematic Diva","Abstract Expressionism","Academia","Action Figure","Adorable 3D Character","Adorable Kawaii","Art Deco","Art Nouveau","Astral Aura","Avant Garde","Baroque","Bauhaus Style Poster","Blueprint Schematic Drawing","Caricature","Cel Shaded Art","Character Design Sheet","Classicism Art","Color Field Painting","Colored Pencil Art","Conceptual Art","Constructivism","Cubism","Dadaism","Dark Fantasy","Dark Moody Atmosphere","Dmt Art Style","Doodle Art","Double Exposure","Dripping Paint Splatter Art","Expressionism","Faded Polaroid Photo","Fauvism","Flat 2d Art","Fortnite Art Style","Futurism","Glitchcore","Glo Fi","Googie Art Style","Graffiti Art","Harlem Renaissance Art","High Fashion","Idyllic","Impressionism","Infographic Drawing","Ink Dripping Drawing","Japanese Ink Drawing","Knolling Photography","Light Cheery Atmosphere","Logo Design","Luxurious Elegance","Macro Photography","Mandola Art","Marker Drawing","Medievalism","Minimalism","Neo Baroque","Neo Byzantine","Neo Futurism","Neo Impressionism","Neo Rococo","Neoclassicism","Op Art","Ornate And Intricate","Pencil Sketch Drawing","Pop Art 2","Rococo","Silhouette Art","Simple Vector Art","Sketchup","Steampunk 2","Surrealism","Suprematism","Terragen","Tranquil Relaxing Atmosphere","Sticker Designs","Vibrant Rim Light","Volumetric Lighting","Watercolor 2","Whimsical And Playful","Mk Chromolithography","Mk Cross Processing Print","Mk Dufaycolor Photograph","Mk Herbarium","Mk Punk Collage","Mk Mosaic","Mk Van Gogh","Mk Coloring Book","Mk Singer Sargent","Mk Pollock","Mk Basquiat","Mk Andy Warhol","Mk Halftone Print","Mk Gond Painting","Mk Albumen Print","Mk Aquatint Print","Mk Anthotype Print","Mk Inuit Carving","Mk Bromoil Print","Mk Calotype Print","Mk Color Sketchnote","Mk Cibulak Porcelain","Mk Alcohol Ink Art","Mk One Line Art","Mk Blacklight Paint","Mk Carnival Glass","Mk Cyanotype Print","Mk Cross Stitching","Mk Encaustic Paint","Mk Embroidery","Mk Gyotaku","Mk Luminogram","Mk Lite Brite Art","Mk Mokume Gane","Pebble Art","Mk Palekh","Mk Suminagashi","Mk Scrimshaw","Mk Shibori","Mk Vitreous Enamel","Mk Ukiyo E","Mk Vintage Airline Poster","Mk Vintage Travel Poster","Mk Bauhaus Style","Mk Afrofuturism","Mk Atompunk","Mk Constructivism","Mk Chicano Art","Mk De Stijl","Mk Dayak Art","Mk Fayum Portrait","Mk Illuminated Manuscript","Mk Kalighat Painting","Mk Madhubani Painting","Mk Pictorialism","Mk Pichwai Painting","Mk Patachitra Painting","Mk Samoan Art Inspired","Mk Tlingit Art","Mk Adnate Style","Mk Ron English Style","Mk Shepard Fairey Style"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"enum"},{"default":"Extreme Speed","description":"You can choose Speed or Quality","enum":["Speed","Quality","Extreme Speed","Lightning"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"performance","required":false,"type":"enum"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"The sharpness of the generated image. Use it to control how sharp the generated\n            image should be. Higher value means image and texture are sharper.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"sharpness","required":false,"type":"number"},{"default":"1024x1024","description":"The size of the generated image. You can choose between some presets or\n            custom height and width that **must be multiples of 8**.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"aspect_ratio","required":false,"type":"string"},{"default":1,"description":"Number of images to generate in one request","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"[{\"path\": \"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors\", \"scale\": 0.1}]","description":"The LoRAs to use for the image generation. You can use up to 5 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"None","description":"Refiner (SDXL or SD 1.5)","enum":["None","realisticVisionV60B1_v51VAE.safetensors"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refiner_model","required":false,"type":"enum"},{"default":0.8,"description":"Use 0.4 for SD1.5 realistic models; 0.667 for SD1.5 anime models\n            0.8 for XL-refiners; or any value for switching two SDXL models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"refiner_switch","required":false,"type":"number"},{"default":"jpeg","description":"The format of the generated image.","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_1","required":true,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_2","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_3","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_4","required":false,"type":"json"},{"default":null,"description":"The image to use as a reference for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"inpaint_image_url","required":false,"type":"string"},{"default":null,"description":"The image to use as a mask for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"},{"default":"Inpaint or Outpaint (default)","description":"The mode to use for inpainting.","enum":["Inpaint or Outpaint (default)","Improve Detail (face, hand, eyes, etc.)","Modify Content (add objects, change background, etc.)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inpaint_mode","required":false,"type":"enum"},{"default":"","description":"Describe what you want to inpaint.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inpaint_additional_prompt","required":false,"type":"string"},{"default":[],"description":"The directions to outpaint.","enum":["Left","Right","Top","Bottom"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"outpaint_selections","required":false,"type":"enum"},{"default":false,"description":"Mixing Image Prompt and Inpaint","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mixing_image_prompt_and_inpaint","required":false,"type":"boolean"},{"default":null,"description":"The image to upscale or vary.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"uov_image_url","required":false,"type":"string"},{"default":"Disabled","description":"The method to use for upscaling or varying.","enum":["Disabled","Vary (Subtle)","Vary (Strong)","Upscale (1.5x)","Upscale (2x)","Upscale (Fast 2x)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"uov_method","required":false,"type":"enum"},{"default":false,"description":"Mixing Image Prompt and Vary/Upscale","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mixing_image_prompt_and_vary_upscale","required":false,"type":"boolean"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/fooocus/fal_ai_fooocus_cyberpunk-city.jpeg","title":"Fooocus Image Prompt"},{"category":"text-to-image","description":"Default parameters with automated optimizations and quality improvements.","endpoint_id":"fal-ai/fooocus/inpaint","family":"","inputs":[{"default":"","description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":["Fooocus Sharp","Fooocus Enhance","Fooocus V2"],"description":"The style to use.","enum":["Fooocus V2","Fooocus Enhance","Fooocus Sharp","Fooocus Semi Realistic","Fooocus Masterpiece","Fooocus Photograph","Fooocus Negative","Fooocus Cinematic","SAI 3D Model","SAI Analog Film","SAI Anime","SAI Cinematic","SAI Comic Book","SAI Craft Clay","SAI Digital Art","SAI Enhance","SAI Fantasy Art","SAI Isometric","SAI Line Art","SAI Lowpoly","SAI Neonpunk","SAI Origami","SAI Photographic","SAI Pixel Art","SAI Texture","MRE Cinematic Dynamic","MRE Spontaneous Picture","MRE Artistic Vision","MRE Dark Dream","MRE Gloomy Art","MRE Bad Dream","MRE Underground","MRE Surreal Painting","MRE Dynamic Illustration","MRE Undead Art","MRE Elemental Art","MRE Space Art","MRE Ancient Illustration","MRE Brave Art","MRE Heroic Fantasy","MRE Dark Cyberpunk","MRE Lyrical Geometry","MRE Sumi E Symbolic","MRE Sumi E Detailed","MRE Manga","MRE Anime","MRE Comic","Ads Advertising","Ads Automotive","Ads Corporate","Ads Fashion Editorial","Ads Food Photography","Ads Gourmet Food Photography","Ads Luxury","Ads Real Estate","Ads Retail","Artstyle Abstract","Artstyle Abstract Expressionism","Artstyle Art Deco","Artstyle Art Nouveau","Artstyle Constructivist","Artstyle Cubist","Artstyle Expressionist","Artstyle Graffiti","Artstyle Hyperrealism","Artstyle Impressionist","Artstyle Pointillism","Artstyle Pop Art","Artstyle Psychedelic","Artstyle Renaissance","Artstyle Steampunk","Artstyle Surrealist","Artstyle Typography","Artstyle Watercolor","Futuristic Biomechanical","Futuristic Biomechanical Cyberpunk","Futuristic Cybernetic","Futuristic Cybernetic Robot","Futuristic Cyberpunk Cityscape","Futuristic Futuristic","Futuristic Retro Cyberpunk","Futuristic Retro Futurism","Futuristic Sci Fi","Futuristic Vaporwave","Game Bubble Bobble","Game Cyberpunk Game","Game Fighting Game","Game Gta","Game Mario","Game Minecraft","Game Pokemon","Game Retro Arcade","Game Retro Game","Game Rpg Fantasy Game","Game Strategy Game","Game Streetfighter","Game Zelda","Misc Architectural","Misc Disco","Misc Dreamscape","Misc Dystopian","Misc Fairy Tale","Misc Gothic","Misc Grunge","Misc Horror","Misc Kawaii","Misc Lovecraftian","Misc Macabre","Misc Manga","Misc Metropolis","Misc Minimalist","Misc Monochrome","Misc Nautical","Misc Space","Misc Stained Glass","Misc Techwear Fashion","Misc Tribal","Misc Zentangle","Papercraft Collage","Papercraft Flat Papercut","Papercraft Kirigami","Papercraft Paper Mache","Papercraft Paper Quilling","Papercraft Papercut Collage","Papercraft Papercut Shadow Box","Papercraft Stacked Papercut","Papercraft Thick Layered Papercut","Photo Alien","Photo Film Noir","Photo Glamour","Photo Hdr","Photo Iphone Photographic","Photo Long Exposure","Photo Neon Noir","Photo Silhouette","Photo Tilt Shift","Cinematic Diva","Abstract Expressionism","Academia","Action Figure","Adorable 3D Character","Adorable Kawaii","Art Deco","Art Nouveau","Astral Aura","Avant Garde","Baroque","Bauhaus Style Poster","Blueprint Schematic Drawing","Caricature","Cel Shaded Art","Character Design Sheet","Classicism Art","Color Field Painting","Colored Pencil Art","Conceptual Art","Constructivism","Cubism","Dadaism","Dark Fantasy","Dark Moody Atmosphere","Dmt Art Style","Doodle Art","Double Exposure","Dripping Paint Splatter Art","Expressionism","Faded Polaroid Photo","Fauvism","Flat 2d Art","Fortnite Art Style","Futurism","Glitchcore","Glo Fi","Googie Art Style","Graffiti Art","Harlem Renaissance Art","High Fashion","Idyllic","Impressionism","Infographic Drawing","Ink Dripping Drawing","Japanese Ink Drawing","Knolling Photography","Light Cheery Atmosphere","Logo Design","Luxurious Elegance","Macro Photography","Mandola Art","Marker Drawing","Medievalism","Minimalism","Neo Baroque","Neo Byzantine","Neo Futurism","Neo Impressionism","Neo Rococo","Neoclassicism","Op Art","Ornate And Intricate","Pencil Sketch Drawing","Pop Art 2","Rococo","Silhouette Art","Simple Vector Art","Sketchup","Steampunk 2","Surrealism","Suprematism","Terragen","Tranquil Relaxing Atmosphere","Sticker Designs","Vibrant Rim Light","Volumetric Lighting","Watercolor 2","Whimsical And Playful","Mk Chromolithography","Mk Cross Processing Print","Mk Dufaycolor Photograph","Mk Herbarium","Mk Punk Collage","Mk Mosaic","Mk Van Gogh","Mk Coloring Book","Mk Singer Sargent","Mk Pollock","Mk Basquiat","Mk Andy Warhol","Mk Halftone Print","Mk Gond Painting","Mk Albumen Print","Mk Aquatint Print","Mk Anthotype Print","Mk Inuit Carving","Mk Bromoil Print","Mk Calotype Print","Mk Color Sketchnote","Mk Cibulak Porcelain","Mk Alcohol Ink Art","Mk One Line Art","Mk Blacklight Paint","Mk Carnival Glass","Mk Cyanotype Print","Mk Cross Stitching","Mk Encaustic Paint","Mk Embroidery","Mk Gyotaku","Mk Luminogram","Mk Lite Brite Art","Mk Mokume Gane","Pebble Art","Mk Palekh","Mk Suminagashi","Mk Scrimshaw","Mk Shibori","Mk Vitreous Enamel","Mk Ukiyo E","Mk Vintage Airline Poster","Mk Vintage Travel Poster","Mk Bauhaus Style","Mk Afrofuturism","Mk Atompunk","Mk Constructivism","Mk Chicano Art","Mk De Stijl","Mk Dayak Art","Mk Fayum Portrait","Mk Illuminated Manuscript","Mk Kalighat Painting","Mk Madhubani Painting","Mk Pictorialism","Mk Pichwai Painting","Mk Patachitra Painting","Mk Samoan Art Inspired","Mk Tlingit Art","Mk Adnate Style","Mk Ron English Style","Mk Shepard Fairey Style"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"enum"},{"default":"Extreme Speed","description":"You can choose Speed or Quality","enum":["Speed","Quality","Extreme Speed","Lightning"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"performance","required":false,"type":"enum"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"The sharpness of the generated image. Use it to control how sharp the generated\n            image should be. Higher value means image and texture are sharper.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"sharpness","required":false,"type":"number"},{"default":"1024x1024","description":"The size of the generated image. You can choose between some presets or\n            custom height and width that **must be multiples of 8**.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"aspect_ratio","required":false,"type":"string"},{"default":1,"description":"Number of images to generate in one request","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"[{\"path\": \"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors\", \"scale\": 0.1}]","description":"The LoRAs to use for the image generation. You can use up to 5 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"None","description":"Refiner (SDXL or SD 1.5)","enum":["None","realisticVisionV60B1_v51VAE.safetensors"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refiner_model","required":false,"type":"enum"},{"default":0.8,"description":"Use 0.4 for SD1.5 realistic models; 0.667 for SD1.5 anime models\n            0.8 for XL-refiners; or any value for switching two SDXL models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"refiner_switch","required":false,"type":"number"},{"default":"jpeg","description":"The format of the generated image.","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The image to use as a reference for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"inpaint_image_url","required":true,"type":"string"},{"default":null,"description":"The image to use as a mask for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"},{"default":"Inpaint or Outpaint (default)","description":"The mode to use for inpainting.","enum":["Inpaint or Outpaint (default)","Improve Detail (face, hand, eyes, etc.)","Modify Content (add objects, change background, etc.)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inpaint_mode","required":false,"type":"enum"},{"default":"","description":"Describe what you want to inpaint.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inpaint_additional_prompt","required":false,"type":"string"},{"default":[],"description":"The directions to outpaint.","enum":["Left","Right","Top","Bottom"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"outpaint_selections","required":false,"type":"enum"},{"default":false,"description":"If set to true, the advanced inpaint options ('inpaint_disable_initial_latent',\n            'inpaint_engine', 'inpaint_strength', 'inpaint_respective_field',\n            'inpaint_erode_or_dilate') will be overridden.\n            Otherwise, the default values will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"override_inpaint_options","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the initial preprocessing will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inpaint_disable_initial_latent","required":false,"type":"boolean"},{"default":"v2.6","description":"Version of Fooocus inpaint model","enum":["None","v1","v2.5","v2.6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inpaint_engine","required":false,"type":"enum"},{"default":1,"description":"Same as the denoising strength in A1111 inpaint. Only used in inpaint, not\n            used in outpaint. (Outpaint always use 1.0)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"inpaint_strength","required":false,"type":"number"},{"default":0.618,"description":"The area to inpaint. Value 0 is same as \"Only Masked\" in A1111. Value 1 is\n            same as \"Whole Image\" in A1111. Only used in inpaint, not used in outpaint.\n            (Outpaint always use 1.0)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"inpaint_respective_field","required":false,"type":"number"},{"default":0,"description":"Positive value will make white area in the mask larger, negative value will\n            make white area smaller. (default is 0, always process before any mask\n            invert)","enum":null,"is_list":false,"max":64,"media_kind":null,"min":-64,"multiline":false,"name":"inpaint_erode_or_dilate","required":false,"type":"number"},{"default":false,"description":"If set to true, the mask will be inverted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"invert_mask","required":false,"type":"boolean"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_1","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_2","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_3","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_4","required":false,"type":"json"},{"default":false,"description":"Mixing Image Prompt and Inpaint","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mixing_image_prompt_and_inpaint","required":false,"type":"boolean"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/fooocus/fal_ai_fooocus_cyberpunk-city.jpeg","title":"Fooocus Inpainting"},{"category":"text-to-image","description":"Default parameters with automated optimizations and quality improvements.","endpoint_id":"fal-ai/fooocus/upscale-or-vary","family":"","inputs":[{"default":"","description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":["Fooocus Sharp","Fooocus Enhance","Fooocus V2"],"description":"The style to use.","enum":["Fooocus V2","Fooocus Enhance","Fooocus Sharp","Fooocus Semi Realistic","Fooocus Masterpiece","Fooocus Photograph","Fooocus Negative","Fooocus Cinematic","SAI 3D Model","SAI Analog Film","SAI Anime","SAI Cinematic","SAI Comic Book","SAI Craft Clay","SAI Digital Art","SAI Enhance","SAI Fantasy Art","SAI Isometric","SAI Line Art","SAI Lowpoly","SAI Neonpunk","SAI Origami","SAI Photographic","SAI Pixel Art","SAI Texture","MRE Cinematic Dynamic","MRE Spontaneous Picture","MRE Artistic Vision","MRE Dark Dream","MRE Gloomy Art","MRE Bad Dream","MRE Underground","MRE Surreal Painting","MRE Dynamic Illustration","MRE Undead Art","MRE Elemental Art","MRE Space Art","MRE Ancient Illustration","MRE Brave Art","MRE Heroic Fantasy","MRE Dark Cyberpunk","MRE Lyrical Geometry","MRE Sumi E Symbolic","MRE Sumi E Detailed","MRE Manga","MRE Anime","MRE Comic","Ads Advertising","Ads Automotive","Ads Corporate","Ads Fashion Editorial","Ads Food Photography","Ads Gourmet Food Photography","Ads Luxury","Ads Real Estate","Ads Retail","Artstyle Abstract","Artstyle Abstract Expressionism","Artstyle Art Deco","Artstyle Art Nouveau","Artstyle Constructivist","Artstyle Cubist","Artstyle Expressionist","Artstyle Graffiti","Artstyle Hyperrealism","Artstyle Impressionist","Artstyle Pointillism","Artstyle Pop Art","Artstyle Psychedelic","Artstyle Renaissance","Artstyle Steampunk","Artstyle Surrealist","Artstyle Typography","Artstyle Watercolor","Futuristic Biomechanical","Futuristic Biomechanical Cyberpunk","Futuristic Cybernetic","Futuristic Cybernetic Robot","Futuristic Cyberpunk Cityscape","Futuristic Futuristic","Futuristic Retro Cyberpunk","Futuristic Retro Futurism","Futuristic Sci Fi","Futuristic Vaporwave","Game Bubble Bobble","Game Cyberpunk Game","Game Fighting Game","Game Gta","Game Mario","Game Minecraft","Game Pokemon","Game Retro Arcade","Game Retro Game","Game Rpg Fantasy Game","Game Strategy Game","Game Streetfighter","Game Zelda","Misc Architectural","Misc Disco","Misc Dreamscape","Misc Dystopian","Misc Fairy Tale","Misc Gothic","Misc Grunge","Misc Horror","Misc Kawaii","Misc Lovecraftian","Misc Macabre","Misc Manga","Misc Metropolis","Misc Minimalist","Misc Monochrome","Misc Nautical","Misc Space","Misc Stained Glass","Misc Techwear Fashion","Misc Tribal","Misc Zentangle","Papercraft Collage","Papercraft Flat Papercut","Papercraft Kirigami","Papercraft Paper Mache","Papercraft Paper Quilling","Papercraft Papercut Collage","Papercraft Papercut Shadow Box","Papercraft Stacked Papercut","Papercraft Thick Layered Papercut","Photo Alien","Photo Film Noir","Photo Glamour","Photo Hdr","Photo Iphone Photographic","Photo Long Exposure","Photo Neon Noir","Photo Silhouette","Photo Tilt Shift","Cinematic Diva","Abstract Expressionism","Academia","Action Figure","Adorable 3D Character","Adorable Kawaii","Art Deco","Art Nouveau","Astral Aura","Avant Garde","Baroque","Bauhaus Style Poster","Blueprint Schematic Drawing","Caricature","Cel Shaded Art","Character Design Sheet","Classicism Art","Color Field Painting","Colored Pencil Art","Conceptual Art","Constructivism","Cubism","Dadaism","Dark Fantasy","Dark Moody Atmosphere","Dmt Art Style","Doodle Art","Double Exposure","Dripping Paint Splatter Art","Expressionism","Faded Polaroid Photo","Fauvism","Flat 2d Art","Fortnite Art Style","Futurism","Glitchcore","Glo Fi","Googie Art Style","Graffiti Art","Harlem Renaissance Art","High Fashion","Idyllic","Impressionism","Infographic Drawing","Ink Dripping Drawing","Japanese Ink Drawing","Knolling Photography","Light Cheery Atmosphere","Logo Design","Luxurious Elegance","Macro Photography","Mandola Art","Marker Drawing","Medievalism","Minimalism","Neo Baroque","Neo Byzantine","Neo Futurism","Neo Impressionism","Neo Rococo","Neoclassicism","Op Art","Ornate And Intricate","Pencil Sketch Drawing","Pop Art 2","Rococo","Silhouette Art","Simple Vector Art","Sketchup","Steampunk 2","Surrealism","Suprematism","Terragen","Tranquil Relaxing Atmosphere","Sticker Designs","Vibrant Rim Light","Volumetric Lighting","Watercolor 2","Whimsical And Playful","Mk Chromolithography","Mk Cross Processing Print","Mk Dufaycolor Photograph","Mk Herbarium","Mk Punk Collage","Mk Mosaic","Mk Van Gogh","Mk Coloring Book","Mk Singer Sargent","Mk Pollock","Mk Basquiat","Mk Andy Warhol","Mk Halftone Print","Mk Gond Painting","Mk Albumen Print","Mk Aquatint Print","Mk Anthotype Print","Mk Inuit Carving","Mk Bromoil Print","Mk Calotype Print","Mk Color Sketchnote","Mk Cibulak Porcelain","Mk Alcohol Ink Art","Mk One Line Art","Mk Blacklight Paint","Mk Carnival Glass","Mk Cyanotype Print","Mk Cross Stitching","Mk Encaustic Paint","Mk Embroidery","Mk Gyotaku","Mk Luminogram","Mk Lite Brite Art","Mk Mokume Gane","Pebble Art","Mk Palekh","Mk Suminagashi","Mk Scrimshaw","Mk Shibori","Mk Vitreous Enamel","Mk Ukiyo E","Mk Vintage Airline Poster","Mk Vintage Travel Poster","Mk Bauhaus Style","Mk Afrofuturism","Mk Atompunk","Mk Constructivism","Mk Chicano Art","Mk De Stijl","Mk Dayak Art","Mk Fayum Portrait","Mk Illuminated Manuscript","Mk Kalighat Painting","Mk Madhubani Painting","Mk Pictorialism","Mk Pichwai Painting","Mk Patachitra Painting","Mk Samoan Art Inspired","Mk Tlingit Art","Mk Adnate Style","Mk Ron English Style","Mk Shepard Fairey Style"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"enum"},{"default":"Extreme Speed","description":"You can choose Speed or Quality","enum":["Speed","Quality","Extreme Speed","Lightning"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"performance","required":false,"type":"enum"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"The sharpness of the generated image. Use it to control how sharp the generated\n            image should be. Higher value means image and texture are sharper.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"sharpness","required":false,"type":"number"},{"default":"1024x1024","description":"The size of the generated image. You can choose between some presets or\n            custom height and width that **must be multiples of 8**.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"aspect_ratio","required":false,"type":"string"},{"default":1,"description":"Number of images to generate in one request","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"[{\"path\": \"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_offset_example-lora_1.0.safetensors\", \"scale\": 0.1}]","description":"The LoRAs to use for the image generation. You can use up to 5 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"None","description":"Refiner (SDXL or SD 1.5)","enum":["None","realisticVisionV60B1_v51VAE.safetensors"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refiner_model","required":false,"type":"enum"},{"default":0.8,"description":"Use 0.4 for SD1.5 realistic models; 0.667 for SD1.5 anime models\n            0.8 for XL-refiners; or any value for switching two SDXL models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"refiner_switch","required":false,"type":"number"},{"default":"jpeg","description":"The format of the generated image.","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The image to upscale or vary.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"uov_image_url","required":true,"type":"string"},{"default":"Vary (Strong)","description":"The method to use for upscaling or varying.","enum":["Disabled","Vary (Subtle)","Vary (Strong)","Upscale (1.5x)","Upscale (2x)","Upscale (Fast 2x)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"uov_method","required":false,"type":"enum"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_1","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_2","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_3","required":false,"type":"json"},{"default":null,"description":"ImagePrompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_prompt_4","required":false,"type":"json"},{"default":false,"description":"Mixing Image Prompt and Vary/Upscale","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mixing_image_prompt_and_vary_upscale","required":false,"type":"boolean"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","timings","images"],"pricing":"","published_at":"2024-08-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/fooocus/fal_ai_fooocus_cyberpunk-city.jpeg","title":"Fooocus Upscale or Vary"},{"category":"image-to-video","description":"Framepack is an efficient Image-to-video model that autoregressively generates videos.","endpoint_id":"fal-ai/framepack","family":"","inputs":[{"default":null,"description":"Text prompt for video generation (max 500 characters).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of the image input.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the video to generate.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"480p","description":"The resolution of the video to generate. 720p generations cost 1.5x more than 480p generations.","enum":["720p","480p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Classifier-Free Guidance scale for the generation.","enum":null,"is_list":false,"max":7,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":10,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":180,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":900,"media_kind":null,"min":30,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-04-17T17:10:10.829000+00:00","thumbnail":"https://v3.fal.media/files/koala/dUfFd9Z7aSX06gL2_qXn0_image.webp","title":"Framepack"},{"category":"image-to-video","description":"Framepack is an efficient Image-to-video model that autoregressively generates videos.","endpoint_id":"fal-ai/framepack/f1","family":"","inputs":[{"default":null,"description":"Text prompt for video generation (max 500 characters).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of the image input.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the video to generate.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"480p","description":"The resolution of the video to generate. 720p generations cost 1.5x more than 480p generations.","enum":["720p","480p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Classifier-Free Guidance scale for the generation.","enum":null,"is_list":false,"max":7,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":10,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":180,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":900,"media_kind":null,"min":30,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-05-13T22:19:18.611000+00:00","thumbnail":"https://v3.fal.media/files/koala/dUfFd9Z7aSX06gL2_qXn0_image.webp","title":"Framepack F1"},{"category":"image-to-video","description":"Framepack is an efficient Image-to-video model that autoregressively generates videos.","endpoint_id":"fal-ai/framepack/flf2v","family":"","inputs":[{"default":null,"description":"Text prompt for video generation (max 500 characters).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of the image input.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the video to generate.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"480p","description":"The resolution of the video to generate. 720p generations cost 1.5x more than 480p generations.","enum":["720p","480p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Classifier-Free Guidance scale for the generation.","enum":null,"is_list":false,"max":7,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":10,"description":"Guidance scale for the generation.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":240,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":1800,"media_kind":null,"min":30,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of the end image input.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"},{"default":0.8,"description":"Determines the influence of the final frame on the generated video. Higher values result in the output being more heavily influenced by the last frame.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-04-22T20:06:23.895000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-5.jpg","title":"Framepack"},{"category":"text-to-image","description":"Google's famous original image generation and editing model, a.k.a Nano Banana","endpoint_id":"fal-ai/gemini-25-flash-image","family":"Nano Banana","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.039 per image. For $1.00, you can run this model 25 times.","published_at":"2025-08-26T01:20:51.897000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9146/WZGTo2gGxttSHbIOe2afs_5d4fa25649f142508bf428f2afb06262.jpg","title":"Gemini 2.5 Flash Image"},{"category":"image-to-image","description":"Google's famous original image generation and editing model, a.k.a Nano Banana","endpoint_id":"fal-ai/gemini-25-flash-image/edit","family":"Nano Banana","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.039 per image. For $1.00, you can run this model 25 times.","published_at":"2025-08-26T01:22:27.733000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91aa/DgAD0PTXm4IPy4MhNlykk_WkMVBWXT.png","title":"Gemini 2.5 Flash Image"},{"category":"text-to-image","description":"Gemini 3 Pro Image (a.k.a Nano Banana Pro) is Google's state-of-the-art high-fidelity image generation and editing model","endpoint_id":"fal-ai/gemini-3-pro-image-preview","family":"Nano Banana Pro","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.15 per image. For $1.00, you can run this model 7 times. 4K outputs will be charged at double the standard rate. Note: Pricing may change in the future.","published_at":"2025-11-20T14:28:35.485000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/Neuz3jAvI1MSVxj3tCrTU_afda4e7f4bc14945a716e864e1f609d8.jpg","title":"Gemini 3 Pro Image Preview"},{"category":"image-to-image","description":"Gemini 3 Pro Image (a.k.a Nano Banana Pro) is Google's state-of-the-art high-fidelity image generation and editing model","endpoint_id":"fal-ai/gemini-3-pro-image-preview/edit","family":"Nano Banana Pro","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.15 per image. For $1.00, you can run this model 7 times. 4K outputs will be charged at double the standard rate. Note: Pricing may change in the future.","published_at":"2025-11-20T14:29:56.085000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/Vp2KdBwHgd4Qp0ixnsOue_eb81afc63ac24064bc9d3e9ed48f9b74.jpg","title":"Gemini 3 Pro Image Preview"},{"category":"text-to-image","description":"Gemini 3.1 Flash Image (a.k.a Nano Banana 2) is Google's new state-of-the-art fast image generation and editing model","endpoint_id":"fal-ai/gemini-3.1-flash-image-preview","family":"Nano Banana 2","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use \"auto\" to let the model decide based on the prompt.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["0.5K","1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.08 per image. For $1.00, you can run this model 12 times. 2K and 4K outputs will be charged at 1.5 times and 2 times the standard rate, respectively. 512x512 resolution outputs will be charged at 0.75 times the standard rate. If web search is used, an additional $0.015 will be charged. Note: Pricing is subject to change.","published_at":"2026-02-26T04:32:59.033000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8ffadd/4fWGbdMY93hLdUwrA2-8S_5e33c8db6e0243ad8ec1164517de37d3.jpg","title":"Gemini 3.1 Flash Image Preview"},{"category":"image-to-image","description":"Gemini 3.1 Flash Image (a.k.a. Nano Banana 2) is Google's new state-of-the-art fast image generation and editing model","endpoint_id":"fal-ai/gemini-3.1-flash-image-preview/edit","family":"Nano Banana 2","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing. Optional when at least one of `video_url`, `audio_url`, or `pdf_url` is provided.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["0.5K","1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Optional video to use as input context. Accepts an http(s)/data URL to a video file (downloaded and sent inline, max 15MB) or a YouTube URL (passed through to the model without downloading).","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":false,"type":"string"},{"default":null,"description":"Optional audio file to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"Optional PDF document to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"pdf_url","required":false,"type":"string"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.08 per image. For $1.00, you can run this model 12 times. 2K and 4K outputs will be charged at 1.5 times and 2 times the standard rate, respectively. 512x512 resolution outputs will be charged at 0.75 times the standard rate. If web search is used, an additional $0.015 will be charged. Note: Pricing is subject to change.","published_at":"2026-02-26T04:34:19.168000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90149a/wFO334Fx1uSWISNJNiWX8_0c3e76b1c53f483397ae8a6e2f6cc383.jpg","title":"Gemini 3.1 Flash Image Preview"},{"category":"text-to-speech","description":"Newest audio model from Google introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.","endpoint_id":"fal-ai/gemini-3.1-flash-tts","family":"","inputs":[{"default":null,"description":"The text to convert to speech. Gemini 3.1 Flash TTS supports natural-language prompting for style, pace, accent, and emotional expression — include delivery instructions inline with the text (e.g. 'Say cheerfully: Have a wonderful day!'). Supports expressive audio tags like [sigh], [laughing], [whispering], [short pause] for fine-grained control over delivery. For multi-speaker synthesis, prefix lines with speaker aliases defined in the speakers field (e.g. 'Alice: Hello!\\nBob: Hi!').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional style and delivery instructions prepended to the prompt. Controls expressiveness, accent, pace, tone, and emotional expression using natural language. Use this to separate style control from the text content. Examples: 'Speak warmly and slowly', 'Read this as a dramatic newscast', 'Use a British accent with a cheerful tone', 'Whisper mysteriously'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_instructions","required":false,"type":"string"},{"default":"Kore","description":"Voice preset for single-speaker synthesis. 30 distinct voices are available. Ignored when speakers is set. Popular choices: Kore (strong, firm female), Puck (upbeat, lively male), Charon (calm, professional male), Zephyr (bright, clear female), Aoede (warm, melodic female).","enum":["Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Pulcherrima","Puck","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"Language for multilingual synthesis. When set, steers the model to speak in the specified language. If not set, the model auto-detects the language from the text.","enum":["Arabic (Egypt)","Bangla (Bangladesh)","Dutch (Netherlands)","English (India)","English (US)","French (France)","German (Germany)","Hindi (India)","Indonesian (Indonesia)","Italian (Italy)","Japanese (Japan)","Korean (South Korea)","Marathi (India)","Polish (Poland)","Portuguese (Brazil)","Romanian (Romania)","Russian (Russia)","Spanish (Spain)","Tamil (India)","Telugu (India)","Thai (Thailand)","Turkish (Turkey)","Ukrainian (Ukraine)","Vietnamese (Vietnam)","Afrikaans (South Africa)","Albanian (Albania)","Amharic (Ethiopia)","Arabic (World)","Armenian (Armenia)","Azerbaijani (Azerbaijan)","Basque (Spain)","Belarusian (Belarus)","Bulgarian (Bulgaria)","Burmese (Myanmar)","Catalan (Spain)","Cebuano (Philippines)","Chinese Mandarin (China)","Chinese Mandarin (Taiwan)","Croatian (Croatia)","Czech (Czech Republic)","Danish (Denmark)","English (Australia)","English (UK)","Estonian (Estonia)","Filipino (Philippines)","Finnish (Finland)","French (Canada)","Galician (Spain)","Georgian (Georgia)","Greek (Greece)","Gujarati (India)","Haitian Creole (Haiti)","Hebrew (Israel)","Hungarian (Hungary)","Icelandic (Iceland)","Javanese (Java)","Kannada (India)","Konkani (India)","Lao (Laos)","Latin (Vatican City)","Latvian (Latvia)","Lithuanian (Lithuania)","Luxembourgish (Luxembourg)","Macedonian (North Macedonia)","Maithili (India)","Malagasy (Madagascar)","Malay (Malaysia)","Malayalam (India)","Mongolian (Mongolia)","Nepali (Nepal)","Norwegian Bokmal (Norway)","Norwegian Nynorsk (Norway)","Odia (India)","Pashto (Afghanistan)","Persian (Iran)","Portuguese (Portugal)","Punjabi (India)","Serbian (Serbia)","Sindhi (India)","Sinhala (Sri Lanka)","Slovak (Slovakia)","Slovenian (Slovenia)","Spanish (Latin America)","Spanish (Mexico)","Swahili (Kenya)","Swedish (Sweden)","Urdu (Pakistan)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_code","required":false,"type":"enum"},{"default":null,"description":"Multi-speaker voice configuration. When set, enables multi-speaker synthesis where different parts of the text are spoken by different voices. Each speaker needs a voice and a speaker_id (alias) that matches prefixes in the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speakers","required":false,"type":"json"},{"default":1,"description":"Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":"mp3","description":"Audio output format. mp3: compressed, small file size (recommended). wav: uncompressed PCM wrapped in WAV (24 kHz, 16-bit mono). ogg_opus: Ogg container with Opus codec, good quality-to-size ratio.","enum":["wav","mp3","ogg_opus"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Google","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-04-16T14:39:44.127000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a959ab9/uM2hZiKHOALvYZA2dBlB3_fa351c0ec002415e968d93c006094bae.jpg","title":"Gemini 3.1 Flash Tts"},{"category":"text-to-audio","description":"Use Gemini TTS Models to convert your prompts to real audio.","endpoint_id":"fal-ai/gemini-tts","family":"","inputs":[{"default":null,"description":"The text to convert to speech. Gemini TTS supports natural-language prompting for style, pace, accent, and emotional expression — include delivery instructions inline with the text (e.g. 'Say cheerfully: Have a wonderful day!'). For multi-speaker synthesis, prefix lines with speaker aliases defined in the speakers field (e.g. 'Alice: Hello!\\nBob: Hi!'). Supports inline pace/style markers like [slowly], [whispering], [excited], [extremely fast].","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional style and delivery instructions prepended to the prompt. Controls expressiveness, accent, pace, tone, and emotional expression using natural language. Use this to separate style control from the text content. Examples: 'Speak warmly and slowly', 'Read this as a dramatic newscast', 'Use a British accent with a cheerful tone', 'Whisper mysteriously'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_instructions","required":false,"type":"string"},{"default":"Kore","description":"Voice preset for single-speaker synthesis. 30 distinct voices are available. Ignored when speakers is set. Popular choices: Kore (strong, firm female), Puck (upbeat, lively male), Charon (calm, professional male), Zephyr (bright, clear female), Aoede (warm, melodic female).","enum":["Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Pulcherrima","Puck","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":"gemini-2.5-flash-tts","description":"Which Gemini TTS model to use. gemini-2.5-flash-tts: low latency, cost-efficient for everyday applications (recommended). gemini-2.5-pro-tts: highest quality, best for structured workflows like podcasts, audiobooks, and customer support.","enum":["gemini-2.5-flash-tts","gemini-2.5-pro-tts"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":null,"description":"Language for multilingual synthesis. When set, steers the model to speak in the specified language. Supports 24 GA languages and 60+ Preview languages. If not set, the model auto-detects the language from the text.","enum":["Arabic (Egypt)","Bangla (Bangladesh)","Dutch (Netherlands)","English (India)","English (US)","French (France)","German (Germany)","Hindi (India)","Indonesian (Indonesia)","Italian (Italy)","Japanese (Japan)","Korean (South Korea)","Marathi (India)","Polish (Poland)","Portuguese (Brazil)","Romanian (Romania)","Russian (Russia)","Spanish (Spain)","Tamil (India)","Telugu (India)","Thai (Thailand)","Turkish (Turkey)","Ukrainian (Ukraine)","Vietnamese (Vietnam)","Afrikaans (South Africa)","Albanian (Albania)","Amharic (Ethiopia)","Arabic (World)","Armenian (Armenia)","Azerbaijani (Azerbaijan)","Basque (Spain)","Belarusian (Belarus)","Bulgarian (Bulgaria)","Burmese (Myanmar)","Catalan (Spain)","Cebuano (Philippines)","Chinese Mandarin (China)","Chinese Mandarin (Taiwan)","Croatian (Croatia)","Czech (Czech Republic)","Danish (Denmark)","English (Australia)","English (UK)","Estonian (Estonia)","Filipino (Philippines)","Finnish (Finland)","French (Canada)","Galician (Spain)","Georgian (Georgia)","Greek (Greece)","Gujarati (India)","Haitian Creole (Haiti)","Hebrew (Israel)","Hungarian (Hungary)","Icelandic (Iceland)","Javanese (Java)","Kannada (India)","Konkani (India)","Lao (Laos)","Latin (Vatican City)","Latvian (Latvia)","Lithuanian (Lithuania)","Luxembourgish (Luxembourg)","Macedonian (North Macedonia)","Maithili (India)","Malagasy (Madagascar)","Malay (Malaysia)","Malayalam (India)","Mongolian (Mongolia)","Nepali (Nepal)","Norwegian Bokmal (Norway)","Norwegian Nynorsk (Norway)","Odia (India)","Pashto (Afghanistan)","Persian (Iran)","Portuguese (Portugal)","Punjabi (India)","Serbian (Serbia)","Sindhi (India)","Sinhala (Sri Lanka)","Slovak (Slovakia)","Slovenian (Slovenia)","Spanish (Latin America)","Spanish (Mexico)","Swahili (Kenya)","Swedish (Sweden)","Urdu (Pakistan)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_code","required":false,"type":"enum"},{"default":null,"description":"Multi-speaker voice configuration. When set, enables multi-speaker synthesis where different parts of the text are spoken by different voices. Each speaker needs a voice and a speaker_id (alias) that matches prefixes in the prompt. Requires gemini-2.5-pro-tts or gemini-2.5-flash-tts model. Not supported with gemini-2.5-flash-lite-preview-tts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speakers","required":false,"type":"json"},{"default":1,"description":"Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":"mp3","description":"Audio output format. mp3: compressed, small file size (recommended). wav: uncompressed PCM wrapped in WAV (24 kHz, 16-bit mono). ogg_opus: Ogg container with Opus codec, good quality-to-size ratio.","enum":["wav","mp3","ogg_opus"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Google","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost 0.5$ per 1 M input tokens and 10$ per 1 M output token for flash model. Cost will be double for pro model.","published_at":"2026-03-20T18:39:43.785000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a92f535/ZqM4YG4tJYjTMInUjWqEg_ce8628b8677f4b4dba1fd041fc169dac.png","title":"Gemini TTS"},{"category":"image-to-image","description":"Reimagine and transform your ordinary photos into enchanting Studio Ghibli style artwork","endpoint_id":"fal-ai/ghiblify","family":"","inputs":[{"default":null,"description":"The URL of the image to upscale.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The seed to use for the upscale. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-03-31T21:39:16.233000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/ghibli/ghibli_example.webp","title":"Ghiblify Images"},{"category":"text-to-image","description":"Create high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.","endpoint_id":"fal-ai/glm-image","family":"","inputs":[{"default":null,"description":"Text prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Output image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","portrait_3_2","landscape_3_2","portrait_hd","landscape_hd","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"Number of diffusion denoising steps. More steps generally produce higher quality images.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1.5,"description":"Classifier-free guidance scale. Higher values make the model follow the prompt more closely.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility. The same seed with the same prompt will produce the same image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Enable NSFW safety checking on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"If True, the prompt will be enhanced using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images"],"pricing":"","published_at":"2026-01-14T02:17:38.633000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a4c6f/XY6gc2c6YgtIKHKiTKRfO_c7be09cba1eb4ebe850aea98676df98d.jpg","title":"GLM Image"},{"category":"image-to-image","description":"Create high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.","endpoint_id":"fal-ai/glm-image/image-to-image","family":"","inputs":[{"default":null,"description":"Text prompt for image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Output image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","portrait_3_2","landscape_3_2","portrait_hd","landscape_hd","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"Number of diffusion denoising steps. More steps generally produce higher quality images.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1.5,"description":"Classifier-free guidance scale. Higher values make the model follow the prompt more closely.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility. The same seed with the same prompt will produce the same image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Enable NSFW safety checking on the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"If True, the prompt will be enhanced using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL(s) of the condition image(s) for image-to-image generation. Supports up to 4 URLs for multi-image references.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images"],"pricing":"","published_at":"2026-01-14T02:44:07.704000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a4d0f/umwWSuRRBSyt9U_bdGB9i_2de7b25b3997468f8166d372a12dff93.jpg","title":"Glm Image"},{"category":"vision","description":"GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.","endpoint_id":"fal-ai/got-ocr/v2","family":"","inputs":[{"default":[],"description":"URL of images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":false,"description":"Generate the output in formatted mode.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"do_format","required":false,"type":"boolean"},{"default":false,"description":"Use provided images to generate a single output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_page","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["outputs"],"pricing":"","published_at":"2025-02-12T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/BEb6pE3CEr6Y89AkI_kEe_WN3XECwa.png","title":"GOT OCR 2.0"},{"category":"text-to-image","description":"GPT Image 1 mini combines OpenAI's advanced language capabilities, powered by GPT-5, with GPT Image 1 Mini for efficient image generation.","endpoint_id":"fal-ai/gpt-image-1-mini","family":"GPT Image 1","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"Aspect ratio for the generated image","enum":["auto","1024x1024","1536x1024","1024x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"auto","description":"Background for the generated image","enum":["auto","transparent","opaque"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":"auto","description":"Quality for the generated image","enum":["auto","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Your request will cost different amounts based on the input and output.\n- You will be charged $0.002 per 1,000 input text tokens. One word is roughly 4 tokens.\n- For low quality, you will be charged $0.005 for 1024x1024 or $0.006 for any other size *per output image*. \n- For medium quality, you will be charged $0.011 for 1024x1024 or $0.015 for any other size *per output image*.\n- For high quality, you will be charged $0.036 for 1024x1024 or $0.052 for any other size *per output image*.\n- Your total request price will be rounded up to the nearest cent.","published_at":"2025-10-21T22:06:41.680000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/Z7Y5fVvUXaT1XzWGqVngY_f333390b078a4bed9491ccda3b9f0e90.jpg","title":"GPT Image 1 Mini"},{"category":"image-to-image","description":"GPT Image 1 mini combines OpenAI's advanced language capabilities, powered by GPT-5, with GPT Image 1 Mini for efficient image generation.","endpoint_id":"fal-ai/gpt-image-1-mini/edit","family":"GPT Image 1","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URLs of the images to use as a reference for the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"auto","description":"Aspect ratio for the generated image","enum":["auto","1024x1024","1536x1024","1024x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"auto","description":"Background for the generated image","enum":["auto","transparent","opaque"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":"auto","description":"Quality for the generated image","enum":["auto","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Your request will cost different amounts based on the input and output.\n- You will be charged $0.002 per 1,000 input text tokens. One word is roughly 4 tokens.\n- You will be charged $0.0025 per 1,000 input image tokens. One 1024x1024 image is roughly 135 tokens.\n- For low quality, you will be charged $0.005 for 1024x1024 or $0.006 for any other size *per output image*. \n- For medium quality, you will be charged $0.011 for 1024x1024 or $0.015 for any other size *per output image*.\n- For high quality, you will be charged $0.036 for 1024x1024 or $0.052 for any other size *per output image*.\n- Your total request price will be rounded up to the nearest cent.","published_at":"2025-10-21T22:09:49.003000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/cG0uNtODkeDPtNDUXms1H_63d395581f334382bf6806b78849ffb0.jpg","title":"GPT Image 1 Mini"},{"category":"text-to-image","description":"GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.","endpoint_id":"fal-ai/gpt-image-1.5","family":"GPT Image 1.5","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1024x1024","description":"Aspect ratio for the generated image","enum":["1024x1024","1536x1024","1024x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"auto","description":"Background for the generated image","enum":["auto","transparent","opaque"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":"high","description":"Quality for the generated image","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Your request will cost different amounts based on the number of images, quality, and size.\n\n- You will be charged $0.005 per 1,000 input text tokens. One word is roughly 4 tokens.\n-  You will be charged $0.010 per 1,000 output text tokens. The model will consume tokens reasoning about your prompt based on it's complexity.\n- For low quality, you will be charged $0.009 for 1024x1024 or $0.013 for any other size *per image*. \n- For medium quality, you will be charged $0.034 for 1024x1024, $0.051 for 1024x1536 and $0.050 for 1536x1024 *per image*.\n- For high quality, you will be charged $0.133 for 1024x1024, $0.200 for 1024x1536 or $0.199 for 1536x1024 *per image*.","published_at":"2025-12-16T18:36:42.550000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87580d/tNVCM7rX3ST05Lko3RnxC_46dfd21f89e34bf99546dce50117a568.jpg","title":"GPT-Image 1.5"},{"category":"image-to-image","description":"GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.","endpoint_id":"fal-ai/gpt-image-1.5/edit","family":"GPT Image 1.5","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URLs of the images to use as a reference for the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"auto","description":"Aspect ratio for the generated image","enum":["auto","1024x1024","1536x1024","1024x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"auto","description":"Background for the generated image","enum":["auto","transparent","opaque"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":"high","description":"Quality for the generated image","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":"high","description":"Input fidelity for the generated image","enum":["low","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"input_fidelity","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the mask image to use for the generation. This indicates what part of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Your request will cost different amounts based on the number of images, quality, and size.\n\n- You will be charged $0.005 per 1,000 input text tokens. One word is roughly 4 tokens.\n- You will be charged $0.008 per 1,000 input image tokens. One 1024x1024 image is roughly 135 tokens in low fidelity mode, or 3,050 tokens in high fidelity mode.\n-  You will be charged $0.010 per 1,000 output text tokens. The model will consume tokens reasoning about your prompt based on it's complexity.\n- For low quality, you will be charged $0.009 for 1024x1024 or $0.013 for any other size *per image*. \n- For medium quality, you will be charged $0.034 for 1024x1024, $0.051 for 1024x1536 and $0.050 for 1536x1024 *per image*.\n- For high quality, you will be charged $0.133 for 1024x1024, $0.200 for 1024x1536 or $0.199 for 1536x1024 *per image*.","published_at":"2025-12-16T18:38:20.664000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875814/3KvlvWItvogHIOuPRWIVl_001c9e77742a4ff2a829a8ece127c0d1.jpg","title":"GPT-Image 1.5"},{"category":"image-to-image","description":"OpenAI's latest image generation and editing model: gpt-1-image.","endpoint_id":"fal-ai/gpt-image-1/edit-image","family":"GPT Image 1","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URLs of the images to use as a reference for the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"auto","description":"Aspect ratio for the generated image","enum":["auto","1024x1024","1536x1024","1024x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"auto","description":"Background for the generated image","enum":["auto","transparent","opaque"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":"auto","description":"Quality for the generated image","enum":["auto","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":"high","description":"Input fidelity for the generated image","enum":["low","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"input_fidelity","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Your request will cost different amounts based on the input and output.\n- You will be charged $0.002 per 1,000 input text tokens. One word is roughly 4 tokens.\n- You will be charged $0.005 per 1,000 input image tokens. One 1024x1024 image is roughly 135 tokens in low fidelity mode, or 3,050 tokens in high fidelity mode.\n- For low quality, you will be charged $0.011 for 1024x1024 or $0.016 for any other size *per output image*. \n- For medium quality, you will be charged $0.042 for 1024x1024 or $0.063 for any other size *per output image*.\n- For high quality, you will be charged $0.167 for 1024x1024 or $0.25 for any other size *per output image*.\nYour request will cost different amounts based on the input and output.\n- You will be charged $0.002 per 1,000 input text tokens. One word is roughly 4 tokens.\n- For low quality, you will be charged $0.011 for 1024x1024 or $0.016 for any other size *per output image*. \n- For medium quality, you will be charged $0.042 for 1024x1024 or $0.063 for any other size *per output image*.\n- For high quality, you will be charged $0.167 for 1024x1024 or $0.25 for any other size *per output image*.\n- Your total request cost will be rounded up to the nearest cent.","published_at":"2025-04-23T17:29:21.329000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"gpt-image-1"},{"category":"text-to-image","description":"OpenAI's latest image generation and editing model: gpt-1-image.","endpoint_id":"fal-ai/gpt-image-1/text-to-image","family":"GPT Image 1","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"Aspect ratio for the generated image","enum":["auto","1024x1024","1536x1024","1024x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"auto","description":"Background for the generated image","enum":["auto","transparent","opaque"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":"auto","description":"Quality for the generated image","enum":["auto","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Your request will cost different amounts based on the input and output.\n- You will be charged $0.002 per 1,000 input text tokens. One word is roughly 4 tokens.\n- For low quality, you will be charged $0.011 for 1024x1024 or $0.016 for any other size *per output image*. \n- For medium quality, you will be charged $0.042 for 1024x1024 or $0.063 for any other size *per output image*.\n- For high quality, you will be charged $0.167 for 1024x1024 or $0.25 for any other size *per output image*.\n- Your total request cost will be rounded up to the nearest cent.","published_at":"2025-04-23T17:29:52.367000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-2.jpg","title":"gpt-image-1"},{"category":"text-to-video","description":"Heygen Avatar V3 Model for Digital Twin","endpoint_id":"fal-ai/heygen/avatar3/digital-twin","family":"","inputs":[{"default":null,"description":"Character configuration for the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"character","required":true,"type":"json"},{"default":null,"description":"Voice configuration for the character","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"json"},{"default":null,"description":"URL of an audio file for the avatar to lip-sync to. When provided, the avatar uses this audio instead of text-to-speech.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":"720p","description":"Video resolution preset. Options: 360p, 480p, 540p, 720p, 1080p","enum":["360p","480p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the output video. Use '9:16' for portrait (vertical) videos, '16:9' for landscape, '1:1' for square, '4:5' for portrait social video, or '5:4' for landscape social video.","enum":["16:9","9:16","4:5","5:4","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.034 per output video second.","published_at":"2026-02-23T18:28:07.025000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90144d/5pYP_7oyKhCOtdFK_2sNY_d4a3e0b219364f3184738088b45b9fcf.jpg","title":"Heygen"},{"category":"text-to-video","description":"Heygen Avatar 4 Digital Twin Model","endpoint_id":"fal-ai/heygen/avatar4/digital-twin","family":"Avatar 4","inputs":[{"default":null,"description":"Character configuration for the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"character","required":true,"type":"json"},{"default":null,"description":"Voice configuration for the character","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"json"},{"default":null,"description":"URL of an audio file for the avatar to lip-sync to. When provided, the avatar uses this audio instead of text-to-speech.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":"720p","description":"Video resolution preset. Options: 360p, 480p, 540p, 720p, 1080p","enum":["360p","480p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the output video. Supported values: '16:9', '9:16', '4:5', '5:4', '1:1', and 'auto'. 'auto' preserves the source aspect ratio when HeyGen can read it, falling back to '16:9' otherwise.","enum":["16:9","9:16","4:5","5:4","1:1","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.1 per output video second.","published_at":"2026-02-23T18:32:24.919000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e8e51/T6VXguv9KYP018KAxFsLa_9b6beffdb69643c79edf6e76e3233d63.png","title":"Heygen"},{"category":"image-to-video","description":"Heygen Photo Avatar 4 Model","endpoint_id":"fal-ai/heygen/avatar4/image-to-video","family":"Avatar 4","inputs":[{"default":null,"description":"URL of the image to animate. The image should contain a clear face.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text the avatar will speak","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Name of the voice to use for the avatar","enum":["Warm Pro Narrator","Chill Brian","Ivy","John Doe","Monika Sogam","Hope ","Archer ","Brittney","Patrick","David Castlemore","Michael C","Adam Stone ","Juniper","Cassidy ","Jessica Anne Bogart","Arabella","Andrew","Spuds Oxley ","Grace Elder","Helen","Canyon Rivers","Derya - Lifelike - Excited 🤩","Mellow Marcus","Jack Sterling - Broadcaster 🎙️","Brenda - UGC - 1.mp4","Reid","Reagan","Terry","Jenny","Radio Rick","Denise","Tim in car - Excited 🤩","Iskander","Thompson","Delicate Daisy - Excited 🤩","Kingston","George UGC 1","Bold Blake","Jane","Expressive Evan","Marianne - IA","Aaron","Modern Recipe Host - Voice 1","Willow","Cute Chloe - Friendly 😊","Rafael","June - Lifelike","Crisp Chloe","Slick Simon","Nassim - Informative","Baritone Ben","Maxwell","Ellie Faye - Excited 🤩","Milani","Feisty Fiona - Excited 🤩","Professor Dean","Rose - UGC - 1.mp4","Shona","Hudson Wilder","Ann - IA","Alastair Kensington","Oxley","Christina","Andrew Rizz ","Peyton","Gerardo - Outdoor","Chloe - Lifelike","Stephanie","Anthony - IA","Signal - Voice 1","Luca","Lisa - Voice 1","T.W.Tucker","Jack Sullivan - Serious 😐","Winter","Mireia - Lifelike","Georgia","Stella","Masha - Lifelike","Charming Charles - Friendly 😊","Serenity","Annie - Excited","Ralph","Bethany","Dominic","Mason Finn","Leena","Veteran Victor","Tamara","Nik Public","Calm Chloe","Sevik","Reilly","Raul","Imposing Ian","Relaxed Ray","Dexter - Professional","Relaxed Rick","Edwin","Rupert Blackwood","Ginny","Hope"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"URL of an audio file for the avatar to lip-sync to. When provided, overrides prompt and voice.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":"stable","description":"Talking style - 'stable' for minimal movement, 'expressive' for more animation","enum":["stable","expressive"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"talking_style","required":false,"type":"enum"},{"default":null,"description":"Facial expression","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expression","required":false,"type":"string"},{"default":null,"description":"Background configuration","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"json"},{"default":"720p","description":"Video resolution preset. Options: 360p, 480p, 540p, 720p, 1080p","enum":["360p","480p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the output video. Supported values: '16:9', '9:16', '4:5', '5:4', '1:1', and 'auto'. 'auto' preserves the source aspect ratio when HeyGen can read it, falling back to '16:9' otherwise.","enum":["16:9","9:16","4:5","5:4","1:1","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether to add captions to the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"caption","required":false,"type":"boolean"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.1 per output video second.","published_at":"2026-02-23T18:33:44.115000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90145c/8wK3ckSYxnnVDeNdGTbc8_4c2266798c21413da1f19c6026d5df52.jpg","title":"Heygen"},{"category":"text-to-video","description":"Create natural HeyGen Avatar V digital twin videos from text or audio, with lip-sync, optional backgrounds, captions, and MP4/WebM output.","endpoint_id":"fal-ai/heygen/avatar5/digital-twin","family":"Avatar V","inputs":[{"default":"Abigail Sofa Front","description":"Name of the Avatar V-eligible avatar to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"avatar","required":false,"type":"string"},{"default":null,"description":"Text the avatar will speak. Required when ``audio_url`` is not provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"Warm Pro Narrator","description":"Name of the text-to-speech voice to use for the avatar when ``audio_url`` is not provided.","enum":["Warm Pro Narrator","Chill Brian","Ivy","John Doe","Monika Sogam","Hope ","Archer ","Brittney","Patrick","David Castlemore","Michael C","Adam Stone ","Juniper","Cassidy ","Jessica Anne Bogart","Arabella","Andrew","Spuds Oxley ","Grace Elder","Helen","Canyon Rivers","Derya - Lifelike - Excited 🤩","Mellow Marcus","Jack Sterling - Broadcaster 🎙️","Brenda - UGC - 1.mp4","Reid","Reagan","Terry","Jenny","Radio Rick","Denise","Tim in car - Excited 🤩","Iskander","Thompson","Delicate Daisy - Excited 🤩","Kingston","George UGC 1","Bold Blake","Jane","Expressive Evan","Marianne - IA","Aaron","Modern Recipe Host - Voice 1","Willow","Cute Chloe - Friendly 😊","Rafael","June - Lifelike","Crisp Chloe","Slick Simon","Nassim - Informative","Baritone Ben","Maxwell","Ellie Faye - Excited 🤩","Milani","Feisty Fiona - Excited 🤩","Professor Dean","Rose - UGC - 1.mp4","Shona","Hudson Wilder","Ann - IA","Alastair Kensington","Oxley","Christina","Andrew Rizz ","Peyton","Gerardo - Outdoor","Chloe - Lifelike","Stephanie","Anthony - IA","Signal - Voice 1","Luca","Lisa - Voice 1","T.W.Tucker","Jack Sullivan - Serious 😐","Winter","Mireia - Lifelike","Georgia","Stella","Masha - Lifelike","Charming Charles - Friendly 😊","Serenity","Annie - Excited","Ralph","Bethany","Dominic","Mason Finn","Leena","Veteran Victor","Tamara","Nik Public","Calm Chloe","Sevik","Reilly","Raul","Imposing Ian","Relaxed Ray","Dexter - Professional","Relaxed Rick","Edwin","Rupert Blackwood","Ginny","Hope"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"HTTP(S) URL of an audio file for the avatar to lip-sync to. When provided, the avatar uses this audio instead of text-to-speech and ``prompt``/``voice`` are ignored.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"cover","description":"How the avatar fits within the output frame. 'contain' keeps the full avatar in view (may letterbox); 'cover' fills the frame (may crop).","enum":["contain","cover"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fit","required":false,"type":"enum"},{"default":false,"description":"Remove the avatar's background. Requires a matting-enabled avatar.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_background","required":false,"type":"boolean"},{"default":null,"description":"Optional background to composite behind the avatar. Ignored when ``output_format='webm'`` (webm output is transparent).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"json"},{"default":null,"description":"Optional watermark image to overlay on the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"watermark","required":false,"type":"json"},{"default":false,"description":"Generate a sidecar SRT caption file alongside the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"caption","required":false,"type":"boolean"},{"default":"mp4","description":"Output container format. 'webm' produces a transparent video (automatically removes the background) and ignores the ``background`` field.","enum":["mp4","webm"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"720p","description":"Output resolution preset.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the output video. Supported values: '16:9', '9:16', '4:5', '5:4', '1:1', and 'auto'. 'auto' preserves the source aspect ratio when HeyGen can read it, falling back to '16:9' otherwise.","enum":["16:9","9:16","4:5","5:4","1:1","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Heygen","output_kind":"video","output_props":["video","caption_file"],"pricing":"$0.10  per second of generated output video. The charge is based on final output duration in seconds.","published_at":"2026-05-20T13:17:53.318000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9aa011/vdGl5om9jDtRhB8kiH8LS_70badfd7deb047e1a3d8c0bf65609406.jpg","title":"Heygen v5 Digital Twin"},{"category":"video-to-video","description":"Heygen Translate Model with Extreme Precision","endpoint_id":"fal-ai/heygen/v2/translate/precision","family":"","inputs":[{"default":null,"description":"URL of the video to translate. Maximum length is 8 minutes.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The target language to translate the video into","enum":["English","Spanish","French","Hindi","Italian","German","Polish","Portuguese","Chinese","Japanese","Dutch","Turkish","Korean","Danish","Arabic","Romanian","Mandarin","Filipino","Swedish","Indonesian","Ukrainian","Greek","Czech","Bulgarian","Malay","Slovak","Croatian","Tamil","Finnish","Russian","Afrikaans (South Africa)","Albanian (Albania)","Amharic (Ethiopia)","Arabic (Algeria)","Arabic (Bahrain)","Arabic (Egypt)","Arabic (Iraq)","Arabic (Jordan)","Arabic (Kuwait)","Arabic (Lebanon)","Arabic (Libya)","Arabic (Morocco)","Arabic (Oman)","Arabic (Qatar)","Arabic (Saudi Arabia)","Arabic (Syria)","Arabic (Tunisia)","Arabic (United Arab Emirates)","Arabic (Yemen)","Armenian (Armenia)","Azerbaijani (Latin, Azerbaijan)","Bangla (Bangladesh)","Basque","Bengali (India)","Bosnian (Bosnia and Herzegovina)","Bulgarian (Bulgaria)","Burmese (Myanmar)","Catalan","Chinese (Cantonese, Traditional)","Chinese (Jilu Mandarin, Simplified)","Chinese (Mandarin, Simplified)","Chinese (Northeastern Mandarin, Simplified)","Chinese (Southwestern Mandarin, Simplified)","Chinese (Taiwanese Mandarin, Traditional)","Chinese (Wu, Simplified)","Chinese (Zhongyuan Mandarin Henan, Simplified)","Chinese (Zhongyuan Mandarin Shaanxi, Simplified)","Croatian (Croatia)","Czech (Czechia)","Danish (Denmark)","Dutch (Belgium)","Dutch (Netherlands)","English (Australia)","English (Canada)","English (Hong Kong SAR)","English (India)","English (Ireland)","English (Kenya)","English (New Zealand)","English (Nigeria)","English (Philippines)","English (Singapore)","English (South Africa)","English (Tanzania)","English (UK)","English (United States)","Estonian (Estonia)","Filipino (Philippines)","Finnish (Finland)","French (Belgium)","French (Canada)","French (France)","French (Switzerland)","Galician","Georgian (Georgia)","German (Austria)","German (Germany)","German (Switzerland)","Greek (Greece)","Gujarati (India)","Hebrew (Israel)","Hindi (India)","Hungarian (Hungary)","Icelandic (Iceland)","Indonesian (Indonesia)","Irish (Ireland)","Italian (Italy)","Japanese (Japan)","Javanese (Latin, Indonesia)","Kannada (India)","Kazakh (Kazakhstan)","Khmer (Cambodia)","Korean (Korea)","Lao (Laos)","Latvian (Latvia)","Lithuanian (Lithuania)","Macedonian (North Macedonia)","Malay (Malaysia)","Malayalam (India)","Maltese (Malta)","Marathi (India)","Mongolian (Mongolia)","Nepali (Nepal)","Norwegian Bokmål (Norway)","Pashto (Afghanistan)","Persian (Iran)","Polish (Poland)","Portuguese (Brazil)","Portuguese (Portugal)","Romanian (Romania)","Russian (Russia)","Serbian (Latin, Serbia)","Sinhala (Sri Lanka)","Slovak (Slovakia)","Slovenian (Slovenia)","Somali (Somalia)","Spanish (Argentina)","Spanish (Bolivia)","Spanish (Chile)","Spanish (Colombia)","Spanish (Costa Rica)","Spanish (Cuba)","Spanish (Dominican Republic)","Spanish (Ecuador)","Spanish (El Salvador)","Spanish (Equatorial Guinea)","Spanish (Guatemala)","Spanish (Honduras)","Spanish (Mexico)","Spanish (Nicaragua)","Spanish (Panama)","Spanish (Paraguay)","Spanish (Peru)","Spanish (Puerto Rico)","Spanish (Spain)","Spanish (United States)","Spanish (Uruguay)","Spanish (Venezuela)","Sundanese (Indonesia)","Swahili (Kenya)","Swahili (Tanzania)","Swedish (Sweden)","Tamil (India)","Tamil (Malaysia)","Tamil (Singapore)","Tamil (Sri Lanka)","Telugu (India)","Thai (Thailand)","Turkish (Türkiye)","Ukrainian (Ukraine)","Urdu (India)","Urdu (Pakistan)","Uzbek (Latin, Uzbekistan)","Vietnamese (Vietnam)","Welsh (United Kingdom)","Zulu (South Africa)","English - Your Accent","English - American Accent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_language","required":true,"type":"enum"},{"default":false,"description":"Translate only the audio, ignore the faces and only translate the voice track","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"translate_audio_only","required":false,"type":"boolean"},{"default":null,"description":"Number of speakers in the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speaker_num","required":false,"type":"integer"},{"default":true,"description":"Enable dynamic duration to enhance conversational fluidity between languages with different speaking rates","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_dynamic_duration","required":false,"type":"boolean"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.1 per output video second.","published_at":"2026-02-23T18:38:58.297000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a901470/P3xLjDZMP1Cg2hVMd_AMw_b865f82e42474449b5ca950e007506a3.jpg","title":"Heygen"},{"category":"video-to-video","description":"Heygen Translate Model with Extreme Speed","endpoint_id":"fal-ai/heygen/v2/translate/speed","family":"","inputs":[{"default":null,"description":"URL of the video to translate. Maximum length is 8 minutes.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The target language to translate the video into","enum":["English","Spanish","French","Hindi","Italian","German","Polish","Portuguese","Chinese","Japanese","Dutch","Turkish","Korean","Danish","Arabic","Romanian","Mandarin","Filipino","Swedish","Indonesian","Ukrainian","Greek","Czech","Bulgarian","Malay","Slovak","Croatian","Tamil","Finnish","Russian","Afrikaans (South Africa)","Albanian (Albania)","Amharic (Ethiopia)","Arabic (Algeria)","Arabic (Bahrain)","Arabic (Egypt)","Arabic (Iraq)","Arabic (Jordan)","Arabic (Kuwait)","Arabic (Lebanon)","Arabic (Libya)","Arabic (Morocco)","Arabic (Oman)","Arabic (Qatar)","Arabic (Saudi Arabia)","Arabic (Syria)","Arabic (Tunisia)","Arabic (United Arab Emirates)","Arabic (Yemen)","Armenian (Armenia)","Azerbaijani (Latin, Azerbaijan)","Bangla (Bangladesh)","Basque","Bengali (India)","Bosnian (Bosnia and Herzegovina)","Bulgarian (Bulgaria)","Burmese (Myanmar)","Catalan","Chinese (Cantonese, Traditional)","Chinese (Jilu Mandarin, Simplified)","Chinese (Mandarin, Simplified)","Chinese (Northeastern Mandarin, Simplified)","Chinese (Southwestern Mandarin, Simplified)","Chinese (Taiwanese Mandarin, Traditional)","Chinese (Wu, Simplified)","Chinese (Zhongyuan Mandarin Henan, Simplified)","Chinese (Zhongyuan Mandarin Shaanxi, Simplified)","Croatian (Croatia)","Czech (Czechia)","Danish (Denmark)","Dutch (Belgium)","Dutch (Netherlands)","English (Australia)","English (Canada)","English (Hong Kong SAR)","English (India)","English (Ireland)","English (Kenya)","English (New Zealand)","English (Nigeria)","English (Philippines)","English (Singapore)","English (South Africa)","English (Tanzania)","English (UK)","English (United States)","Estonian (Estonia)","Filipino (Philippines)","Finnish (Finland)","French (Belgium)","French (Canada)","French (France)","French (Switzerland)","Galician","Georgian (Georgia)","German (Austria)","German (Germany)","German (Switzerland)","Greek (Greece)","Gujarati (India)","Hebrew (Israel)","Hindi (India)","Hungarian (Hungary)","Icelandic (Iceland)","Indonesian (Indonesia)","Irish (Ireland)","Italian (Italy)","Japanese (Japan)","Javanese (Latin, Indonesia)","Kannada (India)","Kazakh (Kazakhstan)","Khmer (Cambodia)","Korean (Korea)","Lao (Laos)","Latvian (Latvia)","Lithuanian (Lithuania)","Macedonian (North Macedonia)","Malay (Malaysia)","Malayalam (India)","Maltese (Malta)","Marathi (India)","Mongolian (Mongolia)","Nepali (Nepal)","Norwegian Bokmål (Norway)","Pashto (Afghanistan)","Persian (Iran)","Polish (Poland)","Portuguese (Brazil)","Portuguese (Portugal)","Romanian (Romania)","Russian (Russia)","Serbian (Latin, Serbia)","Sinhala (Sri Lanka)","Slovak (Slovakia)","Slovenian (Slovenia)","Somali (Somalia)","Spanish (Argentina)","Spanish (Bolivia)","Spanish (Chile)","Spanish (Colombia)","Spanish (Costa Rica)","Spanish (Cuba)","Spanish (Dominican Republic)","Spanish (Ecuador)","Spanish (El Salvador)","Spanish (Equatorial Guinea)","Spanish (Guatemala)","Spanish (Honduras)","Spanish (Mexico)","Spanish (Nicaragua)","Spanish (Panama)","Spanish (Paraguay)","Spanish (Peru)","Spanish (Puerto Rico)","Spanish (Spain)","Spanish (United States)","Spanish (Uruguay)","Spanish (Venezuela)","Sundanese (Indonesia)","Swahili (Kenya)","Swahili (Tanzania)","Swedish (Sweden)","Tamil (India)","Tamil (Malaysia)","Tamil (Singapore)","Tamil (Sri Lanka)","Telugu (India)","Thai (Thailand)","Turkish (Türkiye)","Ukrainian (Ukraine)","Urdu (India)","Urdu (Pakistan)","Uzbek (Latin, Uzbekistan)","Vietnamese (Vietnam)","Welsh (United Kingdom)","Zulu (South Africa)","English - Your Accent","English - American Accent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_language","required":true,"type":"enum"},{"default":false,"description":"Translate only the audio, ignore the faces and only translate the voice track","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"translate_audio_only","required":false,"type":"boolean"},{"default":null,"description":"Number of speakers in the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speaker_num","required":false,"type":"integer"},{"default":true,"description":"Enable dynamic duration to enhance conversational fluidity between languages with different speaking rates","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_dynamic_duration","required":false,"type":"boolean"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.05 per output video second.","published_at":"2026-02-23T18:39:44.788000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a901479/nonDlddF3DvH0dOZvkmWy_16858ef8ab5d472381ffd575c5bf6d8d.jpg","title":"Heygen"},{"category":"text-to-video","description":"Heygen Text to Video Generation Model","endpoint_id":"fal-ai/heygen/v2/video-agent","family":"","inputs":[{"default":null,"description":"Natural language prompt describing the video to generate. Include details about style, visual elements, and desired length for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Video configuration options","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"config","required":false,"type":"json"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.034 per output video second.","published_at":"2026-02-15T09:27:45.511000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90146a/u7hMUxCHLeXnu_XlFPiEd_4f395a3b87574d7db393dd5c63626258.jpg","title":"Heygen"},{"category":"video-to-video","description":"Replace or dub audio on an existing video with high-accuracy avatar-inference lip-sync.","endpoint_id":"fal-ai/heygen/v3/lipsync/precision","family":"Lipsync","inputs":[{"default":null,"description":"URL of the source video to lip-sync.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the replacement audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional title for the lipsync job.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"title","required":false,"type":"string"},{"default":false,"description":"Generate captions in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_caption","required":false,"type":"boolean"},{"default":true,"description":"Allow duration adjustment to match the new audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_dynamic_duration","required":false,"type":"boolean"},{"default":false,"description":"Remove background music from the source video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"disable_music_track","required":false,"type":"boolean"},{"default":false,"description":"Enhance the replacement audio quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_speech_enhancement","required":false,"type":"boolean"},{"default":null,"description":"Start time in seconds for partial lipsync.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_time","required":false,"type":"number"},{"default":null,"description":"End time in seconds for partial lipsync.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"end_time","required":false,"type":"number"}],"lab":"Heygen","output_kind":"video","output_props":["video","caption_file"],"pricing":"","published_at":"2026-04-16T16:49:06.953000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a963882/KCALnCjdY-gy0UYJWXn3-_22975c38070b4ed290bbcc03cd49e439.jpg","title":"Heygen Lipsync - Precision"},{"category":"video-to-video","description":"Replace or dub audio on an existing video with fast audio-only lip-sync.","endpoint_id":"fal-ai/heygen/v3/lipsync/speed","family":"Lipsync","inputs":[{"default":null,"description":"URL of the source video to lip-sync.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the replacement audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional title for the lipsync job.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"title","required":false,"type":"string"},{"default":false,"description":"Generate captions in the output video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_caption","required":false,"type":"boolean"},{"default":true,"description":"Allow duration adjustment to match the new audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_dynamic_duration","required":false,"type":"boolean"},{"default":false,"description":"Remove background music from the source video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"disable_music_track","required":false,"type":"boolean"},{"default":false,"description":"Enhance the replacement audio quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_speech_enhancement","required":false,"type":"boolean"},{"default":null,"description":"Start time in seconds for partial lipsync.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_time","required":false,"type":"number"},{"default":null,"description":"End time in seconds for partial lipsync.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"end_time","required":false,"type":"number"}],"lab":"Heygen","output_kind":"video","output_props":["video","caption_file"],"pricing":"","published_at":"2026-04-16T16:48:56.833000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9638b7/j0B3GftjEw-3e9otUPh5M_47dfe43e428a49259eb6c58f30e4ccfb.jpg","title":"Heygen Lipsync - Speed"},{"category":"text-to-video","description":"Generate videos with a single prompt. Describe what you want in plain text, and the agent handles avatar selection, scripting, scene composition - all in one.","endpoint_id":"fal-ai/heygen/v3/video-agent","family":"Avatar Agent","inputs":[{"default":null,"description":"Natural language prompt describing the video to generate. The agent handles avatar selection, script, and production automatically.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"Avatar to use in the video. Set to 'auto' to let the agent auto-select based on the prompt.","enum":["auto","Abigail (Upper Body)","Abigail Office Front","Abigail Office Side","Abigail Sofa Front","Abigail Sofa Side","Aditya in Brown blazer","Aditya in Blue blazer","Aditya in Blue shirt","Aditya in Blue t-shirt","Aditya in Beige blazer","Adrian in Blue Shirt","Adrian in Blue Suit","Adrian in Blue Sweater","Adriana BizTalk Front","Adriana BizTalk Side","Adriana Business Front 2","Adriana Business Front ","Adriana Business Side","Adriana Nurse Front 2","Adriana Nurse Front","Adriana Nurse Side 2","Adriana Nurse Side","Adriana Nurse Sitting Side","Adriana SuitSofa Front","Aiko","Albert in Blue Polo shirt","Albert in Blue blazer","Albert in Blue shirt","Albert in Blue suit","Albert in Khaki blazer","Albert in White shirt","Amanda in Blue Shirt (Front)","Amanda in Blue Shirt (Left)","Amanda in Blue Shirt (Right)","Amanda in Grey Shirt (Front)","Amanda in Grey Shirt (Left)","Amanda in Grey Shirt (Right)","Amanda in Maintenance (Front)","Amanda in Maintenance (Left)","Amanda in Maintenance (Right)","Amelia Business Training Front 2","Amelia Business Training Front","Amelia Business Training Side 2","Amelia Business Training Side","Amelia Lounge Front 2","Amelia Lounge Front","Amelia Lounge Side 2","Amelia Lounge Side","Amelia Yoga Front 2","Amelia Yoga Front","Amelia Yoga Side 2","Amelia Yoga Side","Alex in Black Suit","Alex in Jacket","Alex in White Coat","Alex in Yellow Sweater","Anja Office Front","Anja Office Side ","Anja Sofa Front","Anja Sofa Side ","Ann Business Front","Ann Business Sitting","Ann Casual Front","Ann Casual Lying","Ann Casual Sitting 2","Ann Casual Sitting","Ann Doctor Sitting","Ann Doctor Standing","Ann Sweater Front","Ann Sweater Side","Ann Therapist","Anna in White T-shirt","Anna in Turtleneck T-shirt","Anna in Brown T-shirt","Annelise in Dark blue dress","Annelise in Off white dress","Annelise in Sky blue dress","Annelise in White dress","Annelore in Blue blazer","Annelore in Blue dress","Annelore in Red blazer","Annelore in Red sweater","Annelore in White shirt","Annie in Grey Jacket","Annie in White Shirt","Annie in Tan Jacket","Annie in Blue Casual","Annie in Light Blue","Annie in Brown Shirt","Annie in Black Shirt","Annie in Pink Suit","Annie in Grey Dress","Annie in Blue Vest","Annie in Black V-neck Shirt","Annie in Blue Suit","Annie Bar Sitting Front","Annie Bar Sitting Side","Annie Bar Standing Front 2","Annie Bar Standing Front 3","Annie Bar Standing Front","Annie Bar Standing Side 2","Annie Bar Standing Side 3","Annie Bar Standing Side","Annie Business Casual Standing Front 2","Annie Business Casual Standing Front","Annie Business Casual Standing Side 2","Annie Business Casual Standing Side","Annie Casual Sitting Front 2","Annie Casual Sitting Front","Annie Casual Sitting Side 2","Annie Casual Sitting Side","Annie Casual Standing Front 2","Annie Casual Standing Front","Annie Casual Standing Side 2","Annie Casual Standing Side","Annie Desk Sitting Front 2","Annie Desk Sitting Front","Annie Desk Sitting Side 2","Annie Desk Sitting Side","Annie Lounge Standing Front","Annie Lounge Standing Side","Annie Office Sitting Front 2","Annie Office Sitting Front","Annie Office Sitting Side 2","Annie Office Sitting Side","Annie Office Standing Front","Annie Office Standing Side","Annie Sofa Sitting Front 3","Annie Sofa Sitting Front","Annie Sofa Sitting Side 2","Annie Sofa Sitting Side 3","Annie Sofa Sitting Side","Annie Sofa Sitting Front 2","Annie Studio Pink Sitting Front","Annie Studio Pink Sitting Side","Annie Studio Pink Standing Front","Annie Studio Pink Standing Side","Armando Casual Front","Armando Casual Side","Armando Suit Front","Armando Suit Side","Armando Sweater Front 2","Armando Sweater Front","Armando Sweater Side 2","Armando Sweater Side","Artur Office Front 2","Artur Office Front","Artur Office Side 2","Artur Office Side","Artur Sofa Casual Front 2","Artur Sofa Casual Front","Artur Sofa Casual Side 2","Artur Sofa Causal Side","Aubrey Sofa Side","Aubrey (Upper Body)","Aubrey Night Scene Front","Aubrey Outdoor Sport Front","Aubrey Outdoor Sport Side","Aubrey Sofa Front","August Casual Front 2","August Casual Front","August Cool Sitting","August Cool Style","August Employee Front","August Hoodies Front 2","August Hoodies Front","Bahar (Upper Body)","Bahar Business Front","Bahar Business Side","Bahar Business Sitting Front","Bahar Business Sitting Side","Bahar Casual Sitting Front 2","Bahar Casual Sitting Front","Bahar Casual Sitting Side 2","Bahar Casual Sitting Side","Bahar Denim Casual Front","Bahar Denim Casual Side","Bahar Denim Front","Bahar Denim Side","Bahar Jacket Casual Front","Bahar Jacket Casual Side","Bahar Jacket Front","Bahar Jacket Side","Bahar Suit Front","Bahar Suit Side","Bastien in Blue T-shirt","Bastien in Blue blazer","Bastien in Blue shirt","Bastien in White shirt","Blanka Lounge Front","Blanka Lounge Side","Blanka Outdoor Business Front","Blanka Outdoor Business Side","Blanka Outdoor Reading Front","Blanka Outdoor Reading Side","Blanka Picnic Front","Blanka Picnic Side","Bojan Business Training Front 2","Bojan Business Training Front","Bojan Business Training Side 2","Bojan Business Training Side","Bojan Lounge Front 2","Bojan Lounge Front","Bojan Lounge Side 2","Bojan Lounge Side","Bojan Sport Front 2","Bojan Sport Front","Bojan Sport Side 2","Bojan Sport Side","Bradley in Blue Polo (Front)","Bradley in Blue Polo (Left)","Bradley in Blue Polo (Right)","Bradley in Blue Shirt (Front)","Bradley in Blue Shirt (Left)","Bradley in Blue Shirt (Right)","Bradley in Doctor (Front)","Bradley in Doctor (Left)","Bradley in Doctor (Right)","Brandon in Grey Suit","Brandon in Blue Sweater","Brandon in White Shirt","Brandon Business Sitting Front","Brandon Business Sitting Side","Brandon Business Standing Front","Brandon Business Standing Side","Brandon Casual Sitting Front","Brandon Casual Sitting Side","Brandon Kitchen Standing Front","Brandon Kitchen Standing Side","Brandon Lobby Sitting Front","Brandon Lobby Sitting Side","Brandon Lobby Standing Front","Brandon Lobby Standing Side","Brandon Office Sitting Front","Brandon Office Sitting Side","Brandon Office Standing Front","Brandon Office Standing Side","Brandon Sofa Sitting Front","Brandon Sofa Sitting Side","Brent Office Front 2","Brent Office Front","Brent Office Side 2","Brent Office Side","Brent Sofa Front 2","Brent Sofa Front","Brent Sofa Side 2","Brent Sofa Side","Briana in White shirt","Briana in Striped T-shirt","Briana in Brown suit","Bruce","Bryan Casual Front","Bryan Casual Side","Bryan Fitness Coach","Bryan Tech Expert","Bryan Plaid Shirt Front","Bryan Plaid Shirt Side","Bryan Suit Front","Bryan Suit Side","Bryce in Black t-shirt","Bryce in Blue blazer","Bryce in Blue shirt","Bryce in Grey blazer","Bryce in White shirt","Byron Business Front 2","Byron Business Front","Byron Business Side 2","Byron Business Side","Byron Business Sitting Front","Byron Business Sitting Size","Byron Casual Front 2","Byron Casual Front","Byron Casual Side 2","Byron Casual Side","Byron Casual Sitting Front","Byron Casual Sitting Side","Byron Jacket Front","Byron Jacket Side","Byron Sitting Front","Byron Sitting Side","Byron Suit Front","Byron Suit Side","Candace in Beige Dress (Front)","Candace in Beige Dress (Left)","Candace in Beige Dress (Right)","Candace in Doctor (Front)","Candace in Doctor (Left)","Candace in Doctor (Right)","Candace in Pink Blazer (Front)","Candace in Pink Blazer (Right)","Candace in Pink Blazer  (Left)","Carla in Doctor (Front)","Carla in Doctor (Left)","Carla in Doctor (Right)","Carla in Dress  (Left)","Carla in Shirt (Front)","Carla in Shirt (Left)","Carla in Shirt (Right)","Carlotta BizTalk Front","Carlotta BizTalk Side","Carlotta Business Front","Carlotta Business Side","Carlotta Casual Front","Carlotta Casual Side","Carlotta Casual Sitting Front","Carlotta Casual Sitting Side","Carlotta Half Front","Carlotta Pink Jumpsuit Front 2","Carlotta Pink Jumpsuit Front","Carlotta Pink Jumpsuit Side 2","Carlotta Pink Jumpsuit Side","Carlotta Pink Jumpsuit Sitting Front","Carlotta Pink Jumpsuit Sitting Side","Caroline Business Sitting Front","Caroline Business Sitting Side","Caroline Business Standing Front","Caroline Business Standing Side","Caroline in Blue Suit","Caroline in White Shirt","Caroline in Yellow Casual","Caroline in Yellow Skirt","Caroline Casual Sitting Front","Caroline Casual Sitting Side","Caroline Kitchen Standing Front","Caroline Kitchen Standing Side","Caroline Lobby Sitting Front","Caroline Lobby Sitting Side","Caroline Lobby Standing Front","Caroline Lobby Standing Side","Caroline Office Sitting Front","Caroline Office Sitting Side","Caroline Office Standing Front","Caroline Office Standing Side","Caroline Sofa Sitting Front","Caroline Sofa Sitting Side","Chad in Blue Shirt (Front)","Chad in Blue Shirt (Left)","Chad in Blue Shirt (Right)","Chad in Grey Shirt (Front)","Chad in Grey Shirt (Left)","Chad in Grey Shirt (Right)","Chad in Maintenance (Front)","Chad in Maintenance (Left)","Chad in Maintenance (Right)","Chakir in Headscarf (Front)","Chakir in Headscarf (Left)","Chakir in Headscarf (Right)","Chakir in White Shirt (Front)","Chakir in White Shirt (Right)","Chakir in white Shirt (Left)","Chloe (Upper Body)","Chloe Lounge Front","Chloe Lounge Side","Chloe Outdoor Side","Colin Business Front 2","Colin Business Front","Colin Jacket Front","Colin Sitting Cool Style 2","Colin Sitting Cool Style","Colin Suit Front","Colin Sweater Front","Colin Sweater Sitting Front","Connie Business Front","Connie Business Sitting Front","Connie Casual Sitting Front","Connie Casual Sitting Side","Connie Education Front","Connie Education Side 2","Connie Education Side","Connie Skirt Front","Connie Skirt Side","Connie Skirt Sitting Front","Connie Skirt Sitting Side","Connie Suit Front","Conrad House Front","Conrad House Side","Conrad Sofa Front","Conrad Sofa Side","Crisanto Business Front","Crisanto Business Side","Crisanto Chef Front 2","Crisanto Chef Front","Crisanto Chef Side 2","Crisanto Chef Side","Crisanto Chef Sitting ","Crisanto Education Front","Crisanto Education Side","Crisanto Nurse Front 2","Crisanto Nurse Front","Crisanto Nurse Side 2","Crisanto Nurse Side","Crisanto Nurse Sitting Front","Crisanto Nurse Sitting Side","Crisanto Suit Front","Crisanto Suit Side","Daphne in Blue blazer","Daphne in Blue shirt","Daphne in Grey blazer","Daphne in Grey suit","Daphne in Pink hoodie","Daphne in White t-shirt","Darnell in Blue Shirt (Front)","Darnell in Blue Shirt (Left)","Darnell in Blue Shirt (Right)","Darnell in Bordeaux Polo (Front)","Darnell in Bordeaux Polo (Left)","Darnell in Bordeaux Polo (Right)","Darnell in Doctor (Front)","Darnell in Doctor (Left)","Darnell in Doctor (Right)","Derya Indoor Front 2","Derya Indoor Front","Derya Indoor Side 2","Derya Indoor Side","Derya Office Front 2","Derya Office Front","Derya Office Side 2","Derya Office Side","Dexter Casual Front","Dexter Casuat Side","Dexter Doctor Sitting","Dexter Doctor Standing","Dexter Lawyer","Dexter Suit Front","Dexter Suit Side","Dexter Winter Coat Front","Dexter Winter Coat Side","Diana in Black Camisole Top","Diana in Striped Shirt","Diana in White Shirt","Diora in Blue blazer","Diora in Green blazer","Diora in Pink shirt","Diora in White shirt","Diora in White t-shirt","Diran Casual Front","Diran Casual Side","Diran Jacket Front","Diran Jacket Side","Diran Macbook Business Front","Diran Macbook Business Side","Diran Macbook Casual Front","Diran Macbook Casual Side","Diran Macbook Sitting Front 2","Diran Macbook Sitting Front","Diran Macbook Sitting Side 2","Diran Macbook Sitting Side","Diran Suit Front","Diran Suit Side","Diran iPad Front","Diran iPad Side","Diran iPad Sitting Front","Diran iPad Sitting Side","Elenora Casual Front","Elenora Casual Side","Elenora Fitness Coach","Elenora Fitness Coach 2","Elenora Tech Expert","Elenora Suit Front","Elenora Suit Side","Elenora YellowDress Front","Elenora YellowDress Side","Emanuel Office Front","Emanuel Office Side","Emanuel Sofa Front","Emanuel Sofa Side","Emery in Blue blazer","Emery in Blue suit","Emery in Green shirt","Emery in Khaki blazer","Emery in Red blazer","Emery in White t-shirt","Emilia Outdoor Business Front","Emilia Outdoor Business Side","Emilia Outdoor Yoga Front 2","Emilia Outdoor Yoga Front","Emilia Outdoor Yoga Side","Emilia Picnic Front","Emilia Picnic Side","Edward in Black Suit","Edward","Edward in Blue Shirt","Esmond in Black coat","Esmond in Black shirt","Esmond in Blue blazer","Esmond in Blue suit","Esmond in Grey sweater","Fernando Business Indoor Front","Fernando Business Indoor Side","Fernando OutdoorChair Front 2","Fernando Outdoor Chair Front","Fernando Outdoor Chair Side","Fernando Outdoor Front","Fernando Outdoor Side","Fernando Outdoor Table Front","Fernando Outdoor Table Side","Fina Business Sitting Front","Fina Business Sitting Side","Fina Casual Front 2","Fina Casual Front","Fina Casual Side 2","Fina Casual Side","Fina Casual Sitting Front","Fina Casual Sitting Side","Fina Denim Front","Fina Denim Side","Fina Denim Sitting Front","Fina Employee Front","Fina Employee Side","Fina Suit Front","Fina Suit Side","Fina Support Front","Fina Support Side","Florin Business Sitting Front","Florin Business Sitting Side","Florin Maintain Front 2","Florin Maintain Front","Florin Maintain Side 2","Florin Maintain Side","Florin Maintain Siiting Front","Florin Maintain Siiting Side","Florin Suit Front 2","Florin Suit Front","Florin Suit Side 2","Florin Suit Side","Francis in Blazer (Front)","Francis in Blazer (Left)","Francis in Blazer (Right)","Francis in Doctor (Front)","Francis in Doctor (Left)","Francis in Doctor (Right)","Francis in Shirt (Front)","Francis in Shirt (Left)","Francis in Shirt (Right)","Fred in Blue Long Shirt (Front)","Fred in Blue Long Shirt (Left)","Fred in Blue Long Shirt (Right)","Fred in Blue Short Shirt (Front)","Fred in Blue Short Shirt (Left)","Fred in Blue Short Shirt (Right)","Freja in Blue blazer","Freja in Grey blazer","Freja in White blazer","Freja in White polo shirt","Freja in White shirt","Gabriel in Black Sweatshirt","Gabriel in Blue Suit","Gabriel in Gray Shirt","Gala Bedroom Front","Gala Business Sofa Front 2","Gala Business Sofa Front 3","Gala Business Sofa Front","Gala Business Sofa Side 2","Gala Business Sofa Side 3","Gala Business Sofa Side","Gala Casual Sofa with iPad Front","Gala Casual Sofa with iPad Side 2","Gala Casual Sofa with iPad Side","Gala Office Front","Gala Office Side","Gala Sofa Front 2","Gala Sofa Front 3","Gala Sofa Front","Gala Sofa Side 2","Gala Sofa Side 3","Gala Sofa Side","Georgia (Upper Body)","Georgia Casual Front","Georgia Casual Side","Georgia Office Front","Georgia Office Side","Gerardo Sofa Side","Gerardo Indoor Front","Gerardo Indoor Side","Gerardo Night Scene Front 2","Gerardo Night Scene Front","Gerardo Outdoor Sport Front","Gerardo Outdoor Sport Side","Gerardo Sofa Front","Giulia Office Front 2","Giulia Office Front","Giulia Office Side 2","Giulia Office Side","Giulia Sofa Front","Giulia Sofa Side","Giulia Sofa  Front 2","Giulia Sofa  Side 3","Hada Casual Cup Front","Hada Casual Cup Side","Hada Casual Front","Hada Casual Side","Hada Casual Sitting Front 2","Hada Casual Sitting Front","Hada Casual Sitting Side 2","Hada Casual Sitting Side","Hada LivelyGestures Front","Hada LivelyGestures Side","Hada LivelyGestures Sitting Front","Hada LivelyGestures Sitting Side","Hada Suit Front 2","Hada Suit Front","Hada Suit Side 2","Hada Suit Side","Hada Suit Sitting Front 2","Hada Suit Sitting Front","Hada Suit Sitting Side","Harrison in Black Suit","Harrison in Gray Suit","Harrison in White Shirt","Ian in Beige Shirt","Ian in Black Jacket","Ian in Gray Suit","Ida Lounge Front 2","Ida Lounge Front","Ida Lounge Side 2","Ida Lounge Side","Ida Sofa Front 2","Ida Sofa Front","Ida Sofa Side 2","Ida Sofa Side","Iker in Almond sweater","Iker in Black blazer","Iker in Blue shirt","Iker in Grey blazer","Iker in White shirt","Imelda BizTalk Front","Imelda BizTalk Side","Imelda Business Front","Imelda Business Side","Imelda Business Sitting Front 2","Imelda Business Sitting Front","Imelda Business Sitting Side 2","Imelda Business Sitting Side","Imelda Casual Front","Imelda Casual Side","Imelda Coat Front 2","Imelda Coat Front","Imelda Coat Side","Imelda Customer Support Front","Imelda Customer Support Side","Imelda Full Side ","Imelda Suit Front","Imelda Suit Side","Ivan in Black Suit","Ivan in Gary Suit","Ivan in Suit","Ivan in Sweater","Jason in Black Jacket","Jason in Blue Suit","Jason in Gray Shirt","Javi Intense Sitting Speaking Front","Javi Intense Sitting Speaking Side","Javi Intense Sitting Speaking ","Javi Intense Speaking Front 2","Javi Intense Speaking Front 3","Javi Intense Speaking Front","Javi Intense Speaking Side 3","Javi Intense Speaking Side","Javi in Passionate Gestures 2","Javi in Passionate Gestures 3","Javi in Passionate Gestures","Jin (Upper Body)","Jin Blue Casual Front","Jin Blue Casual Side","Jin Business Café Mode Front","Jin Business Café Mode Side","Jin Business Sitting Front","Jin Business Sitting Side","Jin Casual Café Mode Front","Jin Casual Café Mode Side","Jin Casual Sitting Front","Jin Casual Sitting Side","Jin Suit Front","Jin Suit Side","Jin Vest Front","Jin Vest Side","Jin Vest Sitting Front","Jin Vest Sitting Side","Jin in Education Front","Jin in Education Side","Jinwoo in Black vest","Jinwoo in Blue suit","Jinwoo in White T-shirt","Jinwoo in White shirt","Jinwoo in White suit","Jocelyn Office Front 2","Jocelyn Office Front","Jocelyn Office Side 2","Jocelyn Office Side","Jocelyn Sofa Front 2","Jocelyn Sofa Front","Jocelyn Sofa Side 2","Jocelyn Sofa Side","Joel Couch Front","Joel Couch Side","Joel Gym Front","Joel Gym Side","Joel Mountain Front","Joel Mountain Side","Jonas (Upper Body)","Jonas Gym Front 2","Jonas Gym Front","Jonas Gym Side 2","Jonas Gym Side ","June Office Front 2","Juan Office Front","Juan Office Side 2","Juan Office Side","Juan Sofa Front 2","Juan Sofa Front","Juan Sofa Side 2","Juan Sofa Side","Judita (Upper Body)","Judita Yoga Front 2","Judita Yoga Front","Judita Yoga Side 2","Judita Yoga Side","Judith (Upper Body)","Judith Business Front 2","Judith Business Front","Judith Business Sitting Front","Judith Casual Front","Judith Casual Sitting Front","Judith Suit Front","Judy Business Front","Judy Business Side","Judy Business Sitting Front","Judy Casual Front","Judy Casual Side","Judy Casual Sitting","Judy ConfidentSpeaking Front","Judy ConfidentSpeaking Side","Judy Doctor Sitting","Judy Doctor Standing","Judy Lawyer","Judy NurseSitting Front 2","Judy NurseSitting Front","Judy NurseSitting Side 2","Judy NurseSitting Side","Judy Nurse Front 2","Judy Nurse Front","Judy Nurse OnDuty Front","Judy Nurse OnDuty Side","Judy Nurse Side 2","Judy Nurse Side","Judy Suit Front","Judy Suit Side","Judy Teacher Sitting","Judy HR","Judy Teacher Standing","June (Upper Body)","June HR","June Office Front","June Office Side 2","June Office Side","June Sofa Casual Front 2","June Sofa Casual Front","June Sofa Casual Side 2","June Sofa Casual Side","Justin in Black Shirt","Justin in Black Suit","Justin in White Shirt","Justo Business Front 2","Justo Business Front","Justo Business Side 2","Justo Business Side","Justo Casual Sitting","Justo CustomerService Front 2","Justo CustomerService Front","Justo CustomerService Side","Justo CustomerService Sitting Front","Justo CustomerService Sitting Side","Justo EmployeeTraining Front","Justo Suit Casual Front ","Justo Suit Casual Side ","Karolin in Gray Suit","Karolin in Sweatshirt","Karolin in Black Suit","Kavya Indoor Front","Kavya Indoor Side","Kavya Outdoor Side","Kavya Outdoor Sport Front","Kavya Outdoor Sport Side","Kavya Sofa Front","Kavya Sofa Side","Kelly in Blue Shirt  (Front)","Kelly in Blue Shirt (Left)","Kelly in Blue Shirt (Right)","Kelly in Doctor (Front)","Kelly in Doctor (Left)","Kelly in Doctor (Right)","Kelly in Pink Shirt (Front)","Kelly in Pink Shirt (Left)","Kelly in Pink Shirt (Right)","Klara in Black blazer","Klara in Blue blazer","Klara in Blue dress","Klara in Pink shirt","Klara in White blazer","Klara in White shirt","Kristin in Lace Dress","Kristin in V-neck Shirt","Kristin in Black Suit","Leos Office Front 2","Leos Office Front","Leos Office Side 2","Leos Office Side","Leos Sofa Front 2","Leos Sofa Front","Leos Sofa Side 2","Leos Sofa Side","Leszek Lounge Front","Leszek Lounge Side","Leszek Outdoor Business Front","Leszek Outdoor Business Side","Leszek Outdoor Casual Front","Leszek Outdoor Casual Side","Leszek Sofa Front","Leszek Sofa Side","Leah","Leah in Black Suit","Lina Casual Front 2","Lina Casual Front","Lina Casual Side 2","Lina Casual Side","Lina Casual Sitting Front","Lina Casual Sitting Side","Lina Dress Front","Lina Dress Side 2","Lina Dress Side","Lina Dress Sitting Front","Lina Dress Sitting Side","Lina Sweater Front 2","Lina Sweater Front","Lina Sweater Side 2","Lina Sweater Side","Lina Sweater Sitting Front 2","Lina Sweater Sitting Front","Lina Sweater Sitting Side 2","Lina Sweater Sitting Side","Lisa","Luca","Lucien in Black coat","Lucien in Black polo-shirt","Lucien in Blue blazer","Lucien in Blue shirt","Lucien in Grey blazer","Lucien in White shirt","Luke in Brown Suit","Luke in Yellow Jacket","Luke in Blue Suit","Marcus (Upper Body)","Marcus Café Front 2","Marcus Café Front","Marcus Café Side 2","Marcus Café Side","Marcus Casual Front","Marcus Casual Side","Marcus Casual Sitting Front 2","Marcus Casual Sitting Front","Marcus Casual Sitting Side 2","Marcus Casual Sitting Side","Marcus Denim Jacket Front","Marcus Denim Jacket Side","Marcus Education Front","Marcus Education Side","Marcus Sitting Front","Marcus Sitting Side","Marcus Suit Front","Marcus Suit Side","Maria in Suit","Maria in Sweater","Maria in Black Suit","Martina Office Front 2","Martina Office Front","Martina Office Side 2","Martina Office Side","Martina Sofa Front 2","Martina Sofa Front","Martina Sofa Side 2","Martina Sofa Side","Masha Office Front 2","Masha Office Front","Masha Office Side 2","Masha Office Side","Masha Sofa Casual Front 2","Masha Sofa Casual Front","Masha Sofa Casual Side 2","Masha Sofa Casual Side","Mason in Blue Suit","Mason in White Shirt","Mason in Blue Sweater","Matteo Office Front 2","Matteo Office Front","Matteo Office Side 2","Matteo Office Side","Matteo Sofa Front 2","Matteo Sofa Front","Matteo Sofa Side 2","Matteo Sofa Side","Max (Upper Body)","Max Indoor Front","Max Indoor Side","Max Outdoor Sport Front","Max Outdoor Sport Side","Milena Office Front 2","Milena Office Front","Milena Office Side 2","Milena Office Side","Milena Sofa Front 2","Milena Sofa Front","Milena Sofa Side 2","Milena Sofa Side","Miles (Upper Body)","Miles Outdoor Front","Miles Outdoor Side","Miles Sofa Front 2","Miles Sofa Front","Miles Sofa Side 2","Miles Sofa Side","Minho in Blue blazer","Minho in Blue shirt","Minho in Green polo-shirt","Minho in Khaki jacket","Minho in White shirt","Minho in White t-shirt","Mireia Business Indoor Front","Mireia Business Indoor Side","Mireia Outdoor Chair Front","Mireia Outdoor Front","Mireia Outdoor Side","Mireia Outdoor Table Front","Mireia Outdoor Table Side","Miyu Office Front 2","Miyu Office Front","Miyu Office Side 2","Miyu Office Side","Miyu Sofa Business Front","Miyu Sofa Business Side","Miyu Sofa Casual Front 2","Miyu Sofa Casual Front","Miyu Sofa Casual Side 2 ","Miyu Sofa Casual Side","Nadim in Black blazer","Nadim in Blue blazer","Nadim in Blue jacket","Nadim in Puffer vest","Nadim in White shirt","Neil in Black Shirt","Neil in Black Suit ","Neil in Yellow Jacket","Nico","Noah Lobby Front 2","Noah Lobby Front","Noah Lobby Side 2","Noah Lobby Side","Noah Office Front 2","Noah Office Front","Noah Office Side 2","Noah Office Side","Noah Sofa Front 2","Noah Sofa Front ","Noah Sofa Side 2","Noah Sofa Side","Nour in Black blazer","Nour in Brown dress","Nour in Grey hoodie","Nour in Sporty vest","Nour in White shirt","Odelia in Blue Suit","Odelia in Red Dress ","Odelia in Yellow Suit","Onat (Upper Body)","Onat Casual Front","Onat Casual Side","Onat Casual Sitting Front","Onat Casual Sitting Side","Onat Macbook Front 2","Onat Macbook Front","Onat Macbook Side 2","Onat Macbook Side","Onat Suit Front","Onat Suit Side","Onat Suit Sitting Front","Onat Suit Sitting Side","Onat iPad Front","Onat iPad Side","Onat iPad Sitting Front","Onat iPad Sitting Side","Oxana (Upper Body)","Oxana Gym Front 2","Oxana Gym Front","Oxana Gym Side 2","Oxana Gym Side","Oxana Office Front 2","Oxana Office Front","Oxana Office Side 2","Oxana Office Side","Oxana Sofa Front 2","Oxana Sofa Front","Oxana Sofa Side 2","Oxana Sofa Side","Oxana Yoga Front 2","Oxana Yoga Front","Oxana Yoga Side 2","Oxana Yoga Side","Patrizio Business Training Front","Patrizio Business Training Side","Patrizio Office Front","Patrizio Office Side 2","Patrizio Office Side","Patrizio Sofa Front","Patrizio Sofa Side","Piper Business Sofa Front","Piper Business Sofa Side","Piper Education Front","Piper Education Side","Rasmus Lounge Front 2","Rasmus Lounge Front","Rasmus Lounge Side 2","Rasmus Lounge Side","Rasmus Sofa Front 2","Rasmus Sofa Front","Rasmus Sofa Side 2","Rasmus Sofa Side","Raul (Upper Body)","Raul Business Sofa Front 2","Raul Business Sofa Front","Raul Business Sofa Side 2","Raul Business Sofa Side","Raul Casual Sofa Front 2","Raul Casual Sofa Front","Raul Casual Sofa Side 2","Raul Casual Sofa Side","Raul Casual Sofa no iPad Front","Raul Casual Sofa no iPad Side","Raul Casual Sofa with iPad Front","Raul Casual Sofa with iPad Side","Raul Office Front 2","Raul Office Front","Raul Office Side","Raul Sofa Front 2","Raul Sofa Front","Raul Sofa Side 2","Raul Sofa Side","Rebecca","Ren (Upper Body)","Ren Office Front 2","Ren Office Front","Ren Office Side 2","Ren Office Side","Ren Sofa Business Front","Ren Sofa Business Side","Ren Sofa Casual Front 2","Ren Sofa Casual Front","Ren Sofa Casual Side 2 ","Ren Sofa Casual Side","Riley (Upper Body)","Riley Casual Front","Riley Casual Side","Riley Office Front","Riley Office Side","Roman Outdoor Sport Front","Roman Outdoor Sport Side","Sabine Office Front 2","Sabine Office Front","Sabine Office Side","Sabine Sofa Side","Salma in headscarf (Front)","Salma in headscarf (Left)","Salma in headscarf (Right)","Santa Avatar Present Standing ","Santa Avatar Sitting 2","Santa Avatar Sitting","Santa Avatar Sitting Side","Santa Avatar Standing","Santa Fireplace Front","Santa Fireplace Side","Saskia in Blue blazer","Saskia in Blue shirt","Saskia in Green blazer","Saskia in Grey vest","Saskia in White blazer","Scarlett Couch Front 2","Scarlett Couch Front","Scarlett Couch Side 2","Scarlett Couch Side","Scarlett Fireplace Front","Scarlett Fireplace Side","Scarlett Hall Front","Scarlett Hall Side","Scarlett Yoga Front","Scarlett Yoga Side","Seema Business Front","Seema Business Side","Seema Business Sitting Side","Seema Casual Front","Seema Casual Side","Seema Casual Sitting Front","Seema Casual Sitting Side","Seema Nurse Front 2","Seema Nurse Front","Seema Nurse Side 2","Seema Nurse Side","Shawn Business Front","Shawn Business Side","Shawn Casual Sitting Front","Shawn Casual Sitting Side","Shawn Sitting Front","Shawn Sitting Side","Shawn Suit Front","Shawn Suit Side","Shawn Therapist","Shirley Business Front","Shirley Business Side","Shirley Casual Front 2","Shirley Casual Front","Shirley Casual Side","Shirley Casual Sitting Front 2","Shirley Casual Sitting Front","Shirley Casual Sitting Side 2","Shirley Casual Sitting Side","Shirley Education Front","Shirley Education Side 2","Shirley Education Side","Shirley Sitting Front","Shirley Sitting Side","Shirley Skirt Front","Shirley Skirt Side","Shirley Suit Front","Shirley Suit Side","Silas (Upper Body)","Silas Customer Support","Silas HR","Silas Lounge Front","Silas Lounge Side","Silas Sofa Side 2","Silas Sofa Side","Sloane in Blue dress","Sloane in Grey suit","Sloane in Pink sweater","Sophia in Black Shirt","Sophia in Suit ","Sophia in White Suit","Sophie","Stacy in Doctor (Front)","Stacy in Doctor (Left)","Stacy in Doctor (Right)","Stacy in Dress (Front)","Stacy in Dress (Left)","Stacy in Dress (Right)","Stacy in Shirt (Front)","Stacy in Shirt (Left)","Stacy in Shirt (Right)","Susan in Black Shirt","Susan in Black Suit","Susan in Suit","Tahlia in Blue dress","Tahlia in Blue suit","Tahlia in Dark blue suit","Tahlia in Red suit","Tahlia in White shirt","Teodor (Upper Body)","Teodor Office Front 2","Teodor Office Front","Teodor Office Side 2","Teodor Office Side","Teodor Sofa Front 2","Teodor Sofa Front","Teodor Sofa Side 2","Teodor Sofa Side","Timothy (Upper Body)","Timothy Casual Front","Timothy Casual Side","Timothy Office Front","Timothy Office Side","Tito Casual Front 2","Tito Casual Front","Tito Casual Side 2","Tito Casual Side","Tito Casual Sitting Front","Tito Casual Sitting Side","Tito Coat Front 2","Tito Coat Front","Tito Coat Full Side","Tito Coat Side 2","Tito Coat Side","Tito Painter Front","Tito Painter Full Side","Tito Painter Side","Tito Painter Sitting Front","Tito Painter Sitting Side","Travis in Polo Shirt","Travis in Gray Suit","Travis in Black Suit","Trevor  in Plaid Shirt","Trevor in Blue Shirt","Trevor in Blue Suit","Trevor in Suit","Tuba Business Chair Front","Tuba Business Chair Side","Tuba Business Front","Tuba Business Side","Tuba Business Sofa Front","Tuba Business Sofa Side","Tuba Casual Front","Tuba Casual Side","Tuba Casual Sitting Front","Tuba Casual Sitting Side","Tuba Macbook Front","Tuba Macbook Side","Veit Office Front","Veit Office Side","Veit Sofa Front","Veit Sofa Side","Vernon Office Front 2","Vernon Office Front","Vernon Office Side 2","Vernon Office Side","Verena Office Front","Verena Office Side","Verena Sofa Front","Verena Sofa Side","Vernon (Upper Body)","Vernon Lounge Front 2","Vernon Lounge Side 2","Vernon Lounge Side","Vince (Upper Body)","Vince Business Sofa Front","Vince Business Training Front","Vince Business Training Side 2","Vince Business Training Side","Vince Sofa Casual Front 2","Vince Sofa Casual Front","Vince Sofa Casual Side 2","Vince Sofa Casual Side","Violante Brown Suit Front 2","Violante Brown Suit Front ","Violante Business Sitting Front","Violante Business Sitting Side","Violante Casual Sitting Front ","Violante Casual Sitting Side","Violante Sport Front 2","Violante Sport Front","Violante Sport Side","Violante Sport Sitting Side","Violante Suit Front","Vivianna in Black shirt","Wade in Black Suit","Wade in Black Jacket","Wade in Gray Jacket","Yola Active Speaking Front","Yola Active Speaking Side","Yola Business Front","Yola Business Side","Yola Calm Speaking Front","Yola Calm Speaking Side","Yola Casual Front","Yola Casual Side","Yola Employee Badge Front","Yola Employee Badge Side","Zosia in Blue blazer","Zosia in Green dress","Zosia in Khaki blazer","Zosia in White dress","Zosia in Yellow shirt","Austin in Suit","Austin in Blue Casual Suit","Austin in Black Jacket","Austin in Blue Suit","Candace in Pink Blazer (Upper Body)","Chad in Blue Shirt (Upper Body)","Daisy in Suit","Daisy in Shirt","Daisy in Dress","Daisy in T-shirt","Francis in Blazer (Upper Body)","Matthew","Matthew in Suit","Matthew in Flowery Shirt","Matthew in Grey Sweater","Nik in Black Shirt","Nik in Blue Sweater","Tyler in Casual Suit","Tyler in Shirt","Tyler in Suit"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"avatar","required":false,"type":"enum"},{"default":"auto","description":"Voice for narration. Set to 'auto' to let the agent auto-select.","enum":["auto","Warm Pro Narrator","Chill Brian","Ivy","John Doe","Monika Sogam","Hope ","Archer ","Brittney","Patrick","David Castlemore","Michael C","Adam Stone ","Juniper","Cassidy ","Jessica Anne Bogart","Arabella","Andrew","Spuds Oxley ","Grace Elder","Helen","Canyon Rivers","Derya - Lifelike - Excited 🤩","Mellow Marcus","Jack Sterling - Broadcaster 🎙️","Brenda - UGC - 1.mp4","Reid","Reagan","Terry","Jenny","Radio Rick","Denise","Tim in car - Excited 🤩","Iskander","Thompson","Delicate Daisy - Excited 🤩","Kingston","George UGC 1","Bold Blake","Jane","Expressive Evan","Marianne - IA","Aaron","Modern Recipe Host - Voice 1","Willow","Cute Chloe - Friendly 😊","Rafael","June - Lifelike","Crisp Chloe","Slick Simon","Nassim - Informative","Baritone Ben","Maxwell","Ellie Faye - Excited 🤩","Milani","Feisty Fiona - Excited 🤩","Professor Dean","Rose - UGC - 1.mp4","Shona","Hudson Wilder","Ann - IA","Alastair Kensington","Oxley","Christina","Andrew Rizz ","Peyton","Gerardo - Outdoor","Chloe - Lifelike","Stephanie","Anthony - IA","Signal - Voice 1","Luca","Lisa - Voice 1","T.W.Tucker","Jack Sullivan - Serious 😐","Winter","Mireia - Lifelike","Georgia","Stella","Masha - Lifelike","Charming Charles - Friendly 😊","Serenity","Annie - Excited","Ralph","Bethany","Dominic","Mason Finn","Leena","Veteran Victor","Tamara","Nik Public","Calm Chloe","Sevik","Reilly","Raul","Imposing Ian","Relaxed Ray","Dexter - Professional","Relaxed Rick","Edwin","Rupert Blackwood","Ginny","Hope"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"Style template ID from the /v3/video-agent/styles endpoint.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_id","required":false,"type":"string"},{"default":null,"description":"Video orientation. Auto-detected from the prompt if omitted.","enum":["landscape","portrait"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"orientation","required":false,"type":"enum"},{"default":null,"description":"URLs of files to include as assets in the video (images, videos, audio, PDFs). Maximum 20 files.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"file_urls","required":false,"type":"string"},{"default":false,"description":"When enabled, disables the agent's memory functions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"incognito_mode","required":false,"type":"boolean"}],"lab":"Heygen","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-04-16T16:49:14.520000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a967e3d/nTk59cJwBYo_fP1nr7be0_580a3501e6ab43e3854f054f865c3642.jpg","title":"Heygen Video Agent"},{"category":"text-to-image","description":"HiDream-I1 dev is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.","endpoint_id":"fal-ai/hidream-i1-dev","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":1024,"width":1024},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Hidream","output_kind":"images","output_props":["prompt","timings","images","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-04-11T00:44:31.342000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training.jpg","title":"Hidream I1 Dev"},{"category":"text-to-image","description":"HiDream-I1 fast is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within 16 steps.","endpoint_id":"fal-ai/hidream-i1-fast","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":1024,"width":1024},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":16,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Hidream","output_kind":"images","output_props":["images","prompt","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-04-11T00:43:21.382000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9226/f1G6Fr3Dn7wYLjwpIT9OR_X8LCWO2h.png","title":"Hidream I1 Fast"},{"category":"text-to-image","description":"HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.","endpoint_id":"fal-ai/hidream-i1-full","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":1024,"width":1024},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"A list of LoRAs to apply to the model. Each LoRA specifies its path, scale, and optional weight name.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Hidream","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-04-11T00:45:47.743000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922b/JC26xmxz4BReVUCJn-jq9_xNDBmXhB.png","title":"Hidream I1 Full"},{"category":"image-to-image","description":"HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.","endpoint_id":"fal-ai/hidream-i1-full/image-to-image","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. Setting to None uses the input image's size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"A list of LoRAs to apply to the model. Each LoRA specifies its path, scale, and optional weight name.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"The image URL to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.75,"description":"Denoising strength for image-to-image generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Hidream","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-05-05T19:06:43.060000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"Hidream I1 Full"},{"category":"text-to-image","description":"Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.","endpoint_id":"fal-ai/hidream-o1-image","family":"","inputs":[{"default":null,"description":"Text prompt for image generation, editing, or subject-driven personalization.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":[],"description":"Optional reference images. Use none for text-to-image, one for image editing, or multiple for subject-driven personalization.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":false,"type":"string"},{"default":{"height":1024,"width":1024},"description":"Requested output image size. Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. The full model uses 5.0 by default.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable the safety checker on generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"When exactly one reference image is provided, preserve its aspect ratio for the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_aspect","required":false,"type":"boolean"}],"lab":"Hidream","output_kind":"images","output_props":["seed","timings","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2026-05-09T22:28:20.111000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a999217/79hRTD17Is8llel4R5GvK_fb7bcffb53ea405198c7978f9886a668.jpg","title":"Hidream O1 Image"},{"category":"text-to-image","description":"Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.","endpoint_id":"fal-ai/hidream-o1-image/dev","family":"","inputs":[{"default":null,"description":"Text prompt for image generation, editing, or subject-driven personalization.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":[],"description":"Optional reference images. Use none for text-to-image, one for image editing, or multiple for subject-driven personalization.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":false,"type":"string"},{"default":{"height":1024,"width":1024},"description":"Requested output image size. Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"Number of denoising steps. The dev model is distilled for 28 steps.","enum":null,"is_list":false,"max":28,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":0,"description":"Classifier-free guidance scale. The dev model uses 0.0 by default.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable the safety checker on generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"When exactly one reference image is provided, preserve its aspect ratio for the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_aspect","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","timings","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2026-05-09T22:26:28.913000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9991f9/vvcIi5jpPDoJJ_j-Mqjet_714dcf611a2d446381e3b2a8eb084c21.jpg","title":"Hidream O1 Image"},{"category":"image-to-image","description":"Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.","endpoint_id":"fal-ai/hidream-o1-image/dev/edit","family":"","inputs":[{"default":null,"description":"Text prompt for image generation, editing, or subject-driven personalization.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for image editing or subject-driven personalization.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":{"height":2048,"width":2048},"description":"Requested output image size. Reference-image outputs use the nearest model-supported resolution up to about 2048x2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"Number of denoising steps. The dev model is distilled for 28 steps.","enum":null,"is_list":false,"max":28,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":0,"description":"Classifier-free guidance scale. The dev model uses 0.0 by default.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable the safety checker on generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"When exactly one reference image is provided, preserve its aspect ratio for the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_aspect","required":false,"type":"boolean"}],"lab":"Hidream","output_kind":"images","output_props":["seed","timings","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2026-05-09T22:30:26.852000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a999225/QmwooLH3hpHa3255JhRoC_d6e5053b73d44e4a9b4593a043360e66.jpg","title":"Hidream O1 Image"},{"category":"image-to-image","description":"Unified image generation with HiDream-O1-Image. Create, edit, and personalize high-resolution images up to 2K—single native model handles text-to-image, editing, and custom subjects without external components.","endpoint_id":"fal-ai/hidream-o1-image/edit","family":"","inputs":[{"default":null,"description":"Text prompt for image generation, editing, or subject-driven personalization.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for image editing or subject-driven personalization.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":{"height":2048,"width":2048},"description":"Requested output image size. Reference-image outputs use the nearest model-supported resolution up to about 2048x2048 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. The full model uses 5.0 by default.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Enable the safety checker on generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"When exactly one reference image is provided, preserve its aspect ratio for the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_aspect","required":false,"type":"boolean"}],"lab":"Hidream","output_kind":"images","output_props":["seed","timings","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2026-05-09T22:29:40.245000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a99921e/VChBoBpjrCe5lbXHv97mB_220119a1d12448c2bb216d8e8ec6245e.jpg","title":"Hidream O1 Image"},{"category":"3d-to-3d","description":"Split 3D models into parts with Hunyuan 3D","endpoint_id":"fal-ai/hunyuan-3d/v3.1/part","family":"Hunyuan 3D","inputs":[{"default":null,"description":"URL of FBX file to split into parts. ONLY FBX format supported. Max size: 100MB, face count ≤30,000. Recommended: AIGC-generated models.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"input_file_url","required":true,"type":"string"}],"lab":"Tencent","output_kind":"json","output_props":["result_files"],"pricing":"Your request will cost $0.45 per generation. For $1.00, you can run this model 2 times.","published_at":"2026-01-27T21:42:17.195000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c430f/GWyDbICC6yewnuGL_ZRpU_33a2acc25d704e80a5f789c688496fbb.jpg","title":"Hunyuan 3D Part Splitter"},{"category":"image-to-3d","description":"Generate 3D models from images with Hunyuan 3D Pro","endpoint_id":"fal-ai/hunyuan-3d/v3.1/pro/image-to-3d","family":"Hunyuan 3D","inputs":[{"default":null,"description":"Front view image URL. Resolution: 128-5000px, max 8MB, formats: JPG/PNG/WEBP. Tips: simple background, single object, object >50% of frame.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"Optional back/rear view image URL (JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"back_image_url","required":false,"type":"string"},{"default":null,"description":"Optional left side view image URL (JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"left_image_url","required":false,"type":"string"},{"default":null,"description":"Optional right side view image URL (JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"right_image_url","required":false,"type":"string"},{"default":null,"description":"Optional top view image URL (v3.1 exclusive, JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"top_image_url","required":false,"type":"string"},{"default":null,"description":"Optional bottom view image URL (v3.1 exclusive, JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"bottom_image_url","required":false,"type":"string"},{"default":null,"description":"Optional left-front 45 degree angle view image URL (v3.1 exclusive, JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"left_front_image_url","required":false,"type":"string"},{"default":null,"description":"Optional right-front 45 degree angle view image URL (v3.1 exclusive, JPG/PNG recommended).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"right_front_image_url","required":false,"type":"string"},{"default":"Normal","description":"Generation task type. Normal: textured model. Geometry: geometry-only white model (no textures). LowPoly/Sketch are not available in v3.1.","enum":["Normal","Geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_type","required":false,"type":"enum"},{"default":false,"description":"Enable PBR material generation (metallic, roughness, normal textures). Ignored when generate_type is Geometry.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":500000,"description":"Target polygon face count. Range: 40,000-1,500,000. Default: 500,000.","enum":null,"is_list":false,"max":1500000,"media_kind":null,"min":40000,"multiline":false,"name":"face_count","required":false,"type":"integer"}],"lab":"Tencent","output_kind":"file","output_props":["thumbnail","seed","model_glb","model_urls"],"pricing":"Your request will cost $0.375 per generation. For $1.00, you can run this model 2 times.\nEnabling PBR materials adds $0.15. Using multi-view images adds $0.15. Custom face count adds $0.15.","published_at":"2026-01-27T22:01:04.639000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1eed/a9u-FinZ2o0AGqcGFlRoD_5c16e7c0e1ae412cacc53893cae95698.jpg","title":"Hunyuan 3D Pro Image to 3D"},{"category":"text-to-3d","description":"Generate 3D models from text prompts with Hunyuan 3D Pro","endpoint_id":"fal-ai/hunyuan-3d/v3.1/pro/text-to-3d","family":"Hunyuan 3D","inputs":[{"default":null,"description":"Text description of the 3D content to generate. Max 1024 UTF-8 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Normal","description":"Generation task type. Normal: textured model. Geometry: geometry-only white model (no textures). LowPoly/Sketch are not available in v3.1.","enum":["Normal","Geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_type","required":false,"type":"enum"},{"default":false,"description":"Enable PBR material generation (metallic, roughness, normal textures). Ignored when generate_type is Geometry.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":500000,"description":"Target polygon face count. Range: 40,000-1,500,000. Default: 500,000.","enum":null,"is_list":false,"max":1500000,"media_kind":null,"min":40000,"multiline":false,"name":"face_count","required":false,"type":"integer"}],"lab":"Tencent","output_kind":"file","output_props":["thumbnail","seed","model_glb","model_urls"],"pricing":"Your request will cost $0.375 per generation. For $1.00, you can run this model 2 times.\nEnabling PBR materials adds $0.15. Using multi-view images adds $0.15. Custom face count adds $0.15.","published_at":"2026-01-27T22:41:02.852000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c431d/UtISBa1ztdyamEsK0S2n7_49e72a0f05544a01b70bf20cebc2b795.jpg","title":"Hunyuan 3D Pro Text to 3D"},{"category":"image-to-3d","description":"Rapidly generate 3D models from images using Hunyuan 3D.","endpoint_id":"fal-ai/hunyuan-3d/v3.1/rapid/image-to-3d","family":"Hunyuan 3D","inputs":[{"default":null,"description":"Front view image URL. Resolution: 128-5000px, max 8MB (recommended ≤6MB for base64 encoding), formats: JPG/PNG/WEBP. Tips: simple background, single object, object >50% of frame.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"input_image_url","required":true,"type":"string"},{"default":false,"description":"Enable PBR material generation (metallic, roughness, normal textures). Does not take effect when enable_geometry is True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Generate geometry-only white model without textures. When enabled, enable_pbr is ignored and OBJ is not supported (default output is GLB).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_geometry","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["material_mtl","thumbnail","texture","model_glb","model_urls"],"pricing":"Your request will cost $0.225 per generation. For $1.00, you can run this model 4 times.\nBase generation (text or image to 3D) costs $0.225.\nEnabling PBR materials adds $0.15.","published_at":"2026-01-27T22:51:01.772000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c200a/ZLBPlKxexbZ3FeJjnT5vD_934f811d42f24e81a89313c8387a9bc8.jpg","title":"Hunyuan 3D Rapid Image to 3D"},{"category":"text-to-3d","description":"Create detailed, fully-textured 3D models with text","endpoint_id":"fal-ai/hunyuan-3d/v3.1/rapid/text-to-3d","family":"Hunyuan 3D","inputs":[{"default":null,"description":"Text description of the 3D content to generate. Max 200 UTF-8 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Enable PBR material generation (metallic, roughness, normal textures). Does not take effect when enable_geometry is True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Generate geometry-only white model without textures. When enabled, enable_pbr is ignored and OBJ is not supported (default output is GLB).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_geometry","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["material_mtl","thumbnail","model_obj","texture","model_urls"],"pricing":"Your request will cost $0.225 per generation. For $1.00, you can run this model 4 times. Base generation (text or image to 3D) costs $0.225. Enabling PBR materials adds $0.15.","published_at":"2026-01-29T11:55:24.432000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c542a/Qd0S35nuH5GWzvOH_eHjh_6812a7e9398647bab9255951a2b64306.jpg","title":"Hunyuan 3d"},{"category":"3d-to-3d","description":"Optimize 3D mesh topology with Hunyuan 3D Smart Topology.","endpoint_id":"fal-ai/hunyuan-3d/v3.1/smart-topology","family":"Hunyuan 3D 3","inputs":[{"default":"https://v3b.fal.media/files/b/0a8c09c0/VYDiCTcDGK55qY2-idGbX_model.glb","description":"URL of GLB or OBJ file to optimize topology. Max size: 200MB.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"input_file_url","required":false,"type":"string"},{"default":"glb","description":"Input 3D file format.","enum":["glb","obj"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"input_file_type","required":false,"type":"enum"},{"default":"triangle","description":"Output polygon type. triangle: triangular faces only. quadrilateral: mixed quad and triangle faces.","enum":["triangle","quadrilateral"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"polygon_type","required":false,"type":"enum"},{"default":"medium","description":"Target polygon density. high: more detail/polygons, medium: balanced, low: fewer polygons.","enum":["high","medium","low"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_level","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"file","output_props":["model_glb","model_urls"],"pricing":"Your request will cost $0.75 per generation. For $1.00, you can run this model 1 time.","published_at":"2026-01-27T23:31:42.305000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c433a/cbLCQZWgeVueUyM8sDJic_857e06fe878d49b4829f9c119170d13b.jpg","title":"Hunyuan 3D Smart Topology"},{"category":"text-to-image","description":"Use the amazing capabilities of hunyuan image 2.1 to generate images that express the feelings of your text.","endpoint_id":"fal-ai/hunyuan-image/v2.1/text-to-image","family":"Hunyuan","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to guide the image generation away from certain concepts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The desired size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":28,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3.5,"description":"Controls how much the model adheres to the prompt. Higher values mean stricter adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible results. If None, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable prompt enhancement for potentially better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_reprompt","required":false,"type":"boolean"},{"default":false,"description":"Enable the refiner model for improved image quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_refiner","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-09-09T16:54:57.565000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d5/nWqcm_KXaxOkCYUbW7X5Q_QxHOulWF.png","title":"Hunyuan Image"},{"category":"image-to-image","description":"Image editing endpoint for Hunyuan Image 3.0 Instruct.","endpoint_id":"fal-ai/hunyuan-image/v3/instruct/edit","family":"Hunyuan","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The desired size of the generated image. If auto, image size will be determined by the model.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":3.5,"description":"Controls how much the model adheres to the prompt. Higher values mean stricter adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the prompt will be expanded through the model's internal recaptioning step.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducible results. If None, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use as a reference for the generation. A maximum of 3 images are supported.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Tencent","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-01-28T19:56:28.617000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c3dc2/kFAFxnTUhioIU9gO4SE5x_6ab7631c86e84c4ab9645aea5a90242b.jpg","title":"Hunyuan Image"},{"category":"text-to-image","description":"Instruct version of Hunyuan-Image 3.0, with internal reasoning capabilities.","endpoint_id":"fal-ai/hunyuan-image/v3/instruct/text-to-image","family":"Hunyuan","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The desired size of the generated image. If auto, image size will be determined by the model.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":3.5,"description":"Controls how much the model adheres to the prompt. Higher values mean stricter adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the prompt will be expanded through the model's internal recaptioning step.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducible results. If None, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-01-28T14:35:52.431000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c3642/VkrnVjTwaSw6OOn2WTWNX_64a98d021f7842a58c7dfc3b2218fdab.jpg","title":"Hunyuan Image 3.0 Instruct"},{"category":"text-to-image","description":"Leverage the state-of-the-art capabilities of Hunyuan Image 3.0 to generate visual content that effectively conveys the messaging of your written material.","endpoint_id":"fal-ai/hunyuan-image/v3/text-to-image","family":"Hunyuan","inputs":[{"default":null,"description":"The text prompt for image-to-image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to guide the image generation away from certain concepts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The desired size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":28,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Controls how much the model adheres to the prompt. Higher values mean stricter adherence.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible results. If None, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-09-28T06:04:53.920000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/en7kxz5HNAQKg5QuONGDH_760708cdbc4b49e1a96e6b7628e43c35.jpg","title":"Hunyuan Image"},{"category":"text-to-3d","description":"Generate 3D human motions via text-to-generation interface of Hunyuan Motion!","endpoint_id":"fal-ai/hunyuan-motion","family":"Hunyuan","inputs":[{"default":null,"description":"Text prompt describing the motion to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"Motion duration in seconds (0.5-12.0).","enum":null,"is_list":false,"max":12,"media_kind":null,"min":0.5,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":5,"description":"Classifier-free guidance scale. Higher = more faithful to prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"fbx","description":"Output format: 'fbx' for animation files, 'dict' for raw JSON.","enum":["fbx","dict"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"json","output_props":["seed","fbx_file","motion_json"],"pricing":"","published_at":"2025-12-30T12:54:39.431000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a886121/DkVwzQN-tnXsEY9yW6wzM_473ed8506f41423181f1736357bde8f8.jpg","title":"Hunyuan Motion [1B]"},{"category":"text-to-3d","description":"Generate 3D human motions via text-to-generation interface of Hunyuan Motion!","endpoint_id":"fal-ai/hunyuan-motion/fast","family":"Hunyuan","inputs":[{"default":null,"description":"Text prompt describing the motion to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"Motion duration in seconds (0.5-12.0).","enum":null,"is_list":false,"max":12,"media_kind":null,"min":0.5,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":5,"description":"Classifier-free guidance scale. Higher = more faithful to prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"fbx","description":"Output format: 'fbx' for animation files, 'dict' for raw JSON.","enum":["fbx","dict"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"json","output_props":["seed","fbx_file","motion_json"],"pricing":"","published_at":"2025-12-30T12:58:39.853000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a886139/Y0oMLck1xMhSZq_SZO0kq_b33b912e9eb2401dbb38c48ec97b2cd3.jpg","title":"Hunyuan Motion [0.46B]"},{"category":"text-to-video","description":"Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.","endpoint_id":"fal-ai/hunyuan-video","family":"Hunyuan","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"By default, generations are done with 35 steps. Pro mode does 55 steps which results in higher quality videos but will take more time and cost 2x more billing units.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pro_mode","required":false,"type":"boolean"},{"default":"16:9","description":"The aspect ratio of the video to generate.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the video to generate.","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"129","description":"The number of frames to generate.","enum":["129","85"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_frames","required":false,"type":"enum"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-10-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/hunyuan-video.webp?v=1","title":"Hunyuan Video"},{"category":"video-to-video","description":"Use the capabilities of the hunyuan foley model to bring life to your videos by adding sound effect to them.","endpoint_id":"fal-ai/hunyuan-video-foley","family":"Hunyuan","inputs":[{"default":null,"description":"The URL of the video to generate audio for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Text description of the desired audio (optional).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":true,"type":"string"},{"default":"noisy, harsh","description":"Negative prompt to avoid certain audio characteristics.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":4.5,"description":"Guidance scale for audio generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"Number of inference steps for generation.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Tencent","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-09-08T16:50:54.317000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92ce/ZyOMewmHv9GF7a1sO8-aE_V2SR2PRo.png","title":"Hunyuan Video Foley"},{"category":"image-to-video","description":"Image to Video for the high-quality Hunyuan Video I2V model.","endpoint_id":"fal-ai/hunyuan-video-image-to-video","family":"Hunyuan","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image input.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the video to generate.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"string"},{"default":129,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_frames","required":false,"type":"string"},{"default":false,"description":"Turning on I2V Stability reduces hallucination but also reduces motion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"i2v_stability","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-03-06T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/hunyuan-video-image-to-video.webp","title":"Hunyuan Video Image-to-Video Inference"},{"category":"image-to-video","description":"Image to Video for the Hunyuan Video model using a custom trained LoRA.","endpoint_id":"fal-ai/hunyuan-video-img2vid-lora","family":"Hunyuan","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL to the image to generate the video from. The image must be 960x544 or it will get cropped and resized to that size.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Tencent","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-02-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/hunyuan-video.webp?v=1","title":"Hunyuan Video Image-to-Video LoRA Inference"},{"category":"image-to-video","description":"Hunyuan Video 1.5 is Tencent's latest and best video model","endpoint_id":"fal-ai/hunyuan-video-v1.5/image-to-video","family":"Hunyuan","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to guide what not to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":28,"description":"The number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"480p","description":"The resolution of the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":true,"description":"Enable prompt expansion to enhance the input prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of the reference image for image-to-video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Tencent","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-12-17T13:34:51.999000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/yRuXc12ZmJxhXiGcd_1jW_9ebc91f64d1a44b7995e66b3410547e9.jpg","title":"Hunyuan Video V1.5"},{"category":"text-to-video","description":"Hunyuan Video 1.5 is Tencent's latest and best video model","endpoint_id":"fal-ai/hunyuan-video-v1.5/text-to-video","family":"Hunyuan","inputs":[{"default":null,"description":"The prompt to generate the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to guide what not to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":28,"description":"The number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"480p","description":"The resolution of the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":true,"description":"Enable prompt expansion to enhance the input prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"video","output_props":["video","seed"],"pricing":"Current pricing is 0.075 cents/s of video, more resolutions arriving soon.","published_at":"2025-11-21T12:19:44.185000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/yRuXc12ZmJxhXiGcd_1jW_9ebc91f64d1a44b7995e66b3410547e9.jpg","title":"Hunyuan Video V1.5"},{"category":"video-to-video","description":"Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.","endpoint_id":"fal-ai/hunyuan-video/video-to-video","family":"Hunyuan","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for generating the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"By default, generations are done with 35 steps. Pro mode does 55 steps which results in higher quality videos but will take more time and cost 2x more billing units.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pro_mode","required":false,"type":"boolean"},{"default":"16:9","description":"The aspect ratio of the video to generate.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the video to generate.","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"129","description":"The number of frames to generate.","enum":["129","85"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_frames","required":false,"type":"enum"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"URL of the video input.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":0.85,"description":"Strength for Video-to-Video","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Tencent","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-01-30T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/hunyuan-video.webp?v=1","title":"Hunyuan Video (Video-to-Video)"},{"category":"image-to-3d","description":"Transform your photos into ultra-high-resolution 3D models in seconds. Film-quality geometry with PBR textures, ready for games, e-commerce, and 3D printing.","endpoint_id":"fal-ai/hunyuan3d-v3/image-to-3d","family":"Hunyuan 3D 3","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"Optional back view image URL for better 3D reconstruction.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"back_image_url","required":false,"type":"string"},{"default":null,"description":"Optional left view image URL for better 3D reconstruction.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"left_image_url","required":false,"type":"string"},{"default":null,"description":"Optional right view image URL for better 3D reconstruction.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"right_image_url","required":false,"type":"string"},{"default":false,"description":"Whether to enable PBR material generation. Does not take effect when generate_type is Geometry.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":500000,"description":"Target face count. Range: 40000-1500000","enum":null,"is_list":false,"max":1500000,"media_kind":null,"min":40000,"multiline":false,"name":"face_count","required":false,"type":"integer"},{"default":"Normal","description":"Generation type. Normal: textured model. LowPoly: polygon reduction. Geometry: white model without texture.","enum":["Normal","LowPoly","Geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_type","required":false,"type":"enum"},{"default":"triangle","description":"Polygon type. Only takes effect when GenerateType is LowPoly.","enum":["triangle","quadrilateral"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"polygon_type","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"file","output_props":["seed","thumbnail","model_glb","model_urls"],"pricing":"Your request will cost $0.375 per generation. For $1.00, you can run this model 2 times.\nGeneration types: Normal costs $0.375, LowPoly costs $0.45, Geometry costs $0.225.\nEnabling PBR materials adds $0.15. Using multi-view images (back/left/right) adds $0.15. Custom face count adds $0.15.","published_at":"2025-12-16T22:01:39.729000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875a2d/pNNyr8z413ca7eBfcFNlT_f44881fdb61747128320f7235a43e81b.jpg","title":"Hunyuan3d V3"},{"category":"image-to-3d","description":"Create your imagined 3D models with just text. Production-ready, export-ready professional assets with realistic lighting and materials in minutes.","endpoint_id":"fal-ai/hunyuan3d-v3/sketch-to-3d","family":"Hunyuan 3D 3","inputs":[{"default":null,"description":"URL of sketch or line art image to transform into a 3D model. Image resolution must be between 128x128 and 5000x5000 pixels.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"Text prompt describing the 3D content attributes such as color, category, and material.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to enable PBR material generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":500000,"description":"Target face count. Range: 40000-1500000","enum":null,"is_list":false,"max":1500000,"media_kind":null,"min":40000,"multiline":false,"name":"face_count","required":false,"type":"integer"}],"lab":"Tencent","output_kind":"file","output_props":["model_glb","model_urls","thumbnail","seed"],"pricing":"Your request will cost $0.375 per generation. For $1.00, you can run this model 2 times.\nGeneration types: Normal costs $0.375, LowPoly costs $0.45, Geometry costs $0.225.\nEnabling PBR materials adds $0.15. Using multi-view images (back/left/right) adds $0.15. Custom face count adds $0.15.","published_at":"2025-12-16T22:12:40.672000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86970c/UWyfBY4fR6fmAiR5LKxvn_97d2566780be4f0d8aa37d5b437fb879.jpg","title":"Hunyuan3d V3"},{"category":"text-to-3d","description":"Turn simple sketches into detailed, fully-textured 3D models. Instantly convert your concept designs into formats ready for Unity, Unreal, and Blender.","endpoint_id":"fal-ai/hunyuan3d-v3/text-to-3d","family":"Hunyuan 3D 3","inputs":[{"default":null,"description":"Text description of the 3D content to generate. Supports up to 1024 UTF-8 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to enable PBR material generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":500000,"description":"Target face count. Range: 40000-1500000","enum":null,"is_list":false,"max":1500000,"media_kind":null,"min":40000,"multiline":false,"name":"face_count","required":false,"type":"integer"},{"default":"Normal","description":"Generation type. Normal: textured model. LowPoly: polygon reduction. Geometry: white model without texture.","enum":["Normal","LowPoly","Geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_type","required":false,"type":"enum"},{"default":"triangle","description":"Polygon type. Only takes effect when GenerateType is LowPoly.","enum":["triangle","quadrilateral"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"polygon_type","required":false,"type":"enum"}],"lab":"Tencent","output_kind":"file","output_props":["thumbnail","model_urls","seed","model_glb"],"pricing":"Your request will cost $0.375 per generation. For $1.00, you can run this model 2 times.\nGeneration types: Normal costs $0.375, LowPoly costs $0.45, Geometry costs $0.225.\nEnabling PBR materials adds $0.15. Using multi-view images (back/left/right) adds $0.15. Custom face count adds $0.15.","published_at":"2025-12-16T22:13:53.731000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8696b5/YaGZtFEBFL6CEXjiVxdB__dbec569fa5d4418bbbc9d77354f7c86f.jpg","title":"Hunyuan3d V3"},{"category":"image-to-3d","description":"Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/hunyuan3d/v2","family":"Hunyuan 3D 2","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for the model.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":256,"description":"Octree resolution for the model.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"octree_resolution","required":false,"type":"integer"},{"default":false,"description":"If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"textured_mesh","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["seed","model_mesh"],"pricing":"","published_at":"2025-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Hunyuan3D.webp","title":"Hunyuan3D"},{"category":"image-to-3d","description":"Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/hunyuan3d/v2/mini","family":"Hunyuan 3D 2","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for the model.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":256,"description":"Octree resolution for the model.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"octree_resolution","required":false,"type":"integer"},{"default":false,"description":"If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"textured_mesh","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["seed","model_mesh"],"pricing":"","published_at":"2025-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Hunyuan3D.webp","title":"Hunyuan3D"},{"category":"image-to-3d","description":"Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/hunyuan3d/v2/mini/turbo","family":"Hunyuan 3D 2","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for the model.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":256,"description":"Octree resolution for the model.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"octree_resolution","required":false,"type":"integer"},{"default":false,"description":"If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"textured_mesh","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["seed","model_mesh"],"pricing":"","published_at":"2025-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Hunyuan3D.webp","title":"Hunyuan3D"},{"category":"image-to-3d","description":"Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/hunyuan3d/v2/multi-view","family":"Hunyuan 3D 2","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"front_image_url","required":true,"type":"string"},{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"back_image_url","required":true,"type":"string"},{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"left_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for the model.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":256,"description":"Octree resolution for the model.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"octree_resolution","required":false,"type":"integer"},{"default":false,"description":"If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"textured_mesh","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["seed","model_mesh"],"pricing":"","published_at":"2025-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Hunyuan3D.webp","title":"Hunyuan3D"},{"category":"image-to-3d","description":"Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/hunyuan3d/v2/multi-view/turbo","family":"Hunyuan 3D 2","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"front_image_url","required":true,"type":"string"},{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"back_image_url","required":true,"type":"string"},{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"left_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for the model.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":256,"description":"Octree resolution for the model.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"octree_resolution","required":false,"type":"integer"},{"default":false,"description":"If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"textured_mesh","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["seed","model_mesh"],"pricing":"","published_at":"2025-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Hunyuan3D.webp","title":"Hunyuan3D"},{"category":"image-to-3d","description":"Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/hunyuan3d/v2/turbo","family":"Hunyuan 3D 2","inputs":[{"default":null,"description":"URL of image to use while generating the 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":50,"description":"Number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for the model.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":256,"description":"Octree resolution for the model.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"octree_resolution","required":false,"type":"integer"},{"default":false,"description":"If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"textured_mesh","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"file","output_props":["seed","model_mesh"],"pricing":"","published_at":"2025-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Hunyuan3D.webp","title":"Hunyuan3D"},{"category":"image-to-image","description":"Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles.","endpoint_id":"fal-ai/hunyuan_world","family":"Hunyuan","inputs":[{"default":null,"description":"The URL of the image to convert to a panorama.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for the panorama generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Tencent","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-07-28T09:45:58.041000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d1/Ph3WzSzDCzkbvuHCwajw1_DrbNjIwy.png","title":"Hunyuan World"},{"category":"image-to-3d","description":"Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles.","endpoint_id":"fal-ai/hunyuan_world/image-to-world","family":"Hunyuan","inputs":[{"default":null,"description":"The URL of the image to convert to a world.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Labels for the first foreground object.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"labels_fg1","required":true,"type":"string"},{"default":null,"description":"Labels for the second foreground object.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"labels_fg2","required":true,"type":"string"},{"default":null,"description":"Classes to use for the world generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"classes","required":true,"type":"string"},{"default":false,"description":"Whether to export DRC (Dynamic Resource Configuration).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"export_drc","required":false,"type":"boolean"}],"lab":"Tencent","output_kind":"json","output_props":["world_file"],"pricing":"","published_at":"2025-07-28T09:45:20.876000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d2/VxesHe5oek7mJF7KUXchL_VspxWV1k.png","title":"Hunyuan World"},{"category":"image-to-image","description":"Image editing with HY-WU. Transfer outfits, swap faces, and blend textures instantly—no finetuning needed, just describe what you want and provide reference images.","endpoint_id":"fal-ai/hy-wu-edit","family":"","inputs":[{"default":null,"description":"The text prompt describing the desired edit. Supports both English and Chinese. Use specific instructions like 'Replace the clothing on figure 1 with the outfit from figure 2'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of input images for editing. Typically 2 images: the base image and the reference image. Supports up to 3 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"auto","description":"The desired size of the generated image. If auto, image size will be determined by the model.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"Number of diffusion denoising steps.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible results. If None, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Enable thinking mode. The model reasons about the edit before generating, producing higher quality results at the cost of longer inference time. Disable for faster results on straightforward edits.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_thinking","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","seed","timings"],"pricing":"Your request will cost $0.1 per MP, thinking costs $0.15 per MP.","published_at":"2026-03-25T22:28:59.055000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a93a35a/UbYPmsk9O9i9-oWlUKVYR_4e9ae612eac3475090719209add67cfd.jpg","title":"Hy Wu Edit"},{"category":"image-to-3d","description":"Rodin by Hyper3D generates realistic and production ready 3D models from text or images.","endpoint_id":"fal-ai/hyper3d/rodin","family":"Rodin","inputs":[{"default":"","description":"A textual prompt to guide model generation. Required for Text-to-3D mode. Optional for Image-to-3D mode.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of images to use while generating the 3D model. Required for Image-to-3D mode. Optional for Text-to-3D mode.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":"concat","description":"For fuse mode, One or more images are required.It will generate a model by extracting and fusing features of objects from multiple images.For concat mode, need to upload multiple multi-view images of the same object and generate the model. (You can upload multi-view images in any order, regardless of the order of view.)","enum":["fuse","concat"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"condition_mode","required":false,"type":"enum"},{"default":null,"description":"Seed value for randomization, ranging from 0 to 65535. Optional.","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"glb","description":"Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.","enum":["glb","usdz","fbx","obj","stl"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_file_format","required":false,"type":"enum"},{"default":"PBR","description":"Material type. Possible values: PBR, Shaded. Default is PBR.","enum":["PBR","Shaded"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"material","required":false,"type":"enum"},{"default":"medium","description":"Generation quality. Possible values: high, medium, low, extra-low. Default is medium.","enum":["high","medium","low","extra-low"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":false,"description":"Whether to export the model using hyper mode. Default is false.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_hyper","required":false,"type":"boolean"},{"default":"Regular","description":"Tier of generation. For Rodin Sketch, set to Sketch. For Rodin Regular, set to Regular.","enum":["Regular","Sketch"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tier","required":false,"type":"enum"},{"default":false,"description":"When generating the human-like model, this parameter control the generation result to T/A Pose.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"TAPose","required":false,"type":"boolean"},{"default":null,"description":"An array that specifies the dimensions and scaling factor of the bounding box. Typically, this array contains 3 elements, Length(X-axis), Width(Y-axis) and Height(Z-axis).","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bbox_condition","required":false,"type":"integer"},{"default":null,"description":"Generation add-on features. Default is []. Possible values are HighPack. The HighPack option will provide 4K resolution textures instead of the default 1K, as well as models with high-poly. It will cost triple the billable units.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"addons","required":false,"type":"string"}],"lab":"Hyper3D","output_kind":"file","output_props":["model_mesh","textures","seed"],"pricing":"","published_at":"2024-12-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/hyper3d-rodin.webp","title":"Hyper3D Rodin"},{"category":"image-to-3d","description":"Rodin by Hyper3D generates realistic and production ready 3D models from text or images.","endpoint_id":"fal-ai/hyper3d/rodin/v2","family":"Rodin 2","inputs":[{"default":"","description":"A textual prompt to guide model generation. Optional for Image-to-3D mode - if empty, AI will generate a prompt based on your images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of images to use while generating the 3D model. Required for Image-to-3D mode. Up to 5 images allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":false,"description":"When enabled, preserves the transparency channel from input images during 3D generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_original_alpha","required":false,"type":"boolean"},{"default":null,"description":"Seed value for randomization, ranging from 0 to 65535. Optional.","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"glb","description":"Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.","enum":["glb","usdz","fbx","obj","stl"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_file_format","required":false,"type":"enum"},{"default":"All","description":"Material type. PBR: Physically-based materials with realistic lighting. Shaded: Simple materials with baked lighting. All: Both types included.","enum":["PBR","Shaded","All"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"material","required":false,"type":"enum"},{"default":"500K Triangle","description":"Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. These corresponds to `mesh_mode` (if the option contains 'Triangle', mesh_mode is 'Raw', otherwise 'Quad') and `quality_override` (the numeric part of the option) parameters in Hyper3D API.","enum":["4K Quad","8K Quad","18K Quad","50K Quad","2K Triangle","20K Triangle","150K Triangle","500K Triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality_mesh_option","required":false,"type":"enum"},{"default":false,"description":"Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"TAPose","required":false,"type":"boolean"},{"default":null,"description":"An array that specifies the bounding box dimensions [width, height, length].","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bbox_condition","required":false,"type":"integer"},{"default":null,"description":"The HighPack option will provide 4K resolution textures instead of the default 1K, as well as models with high-poly. It will cost **triple the billable units**.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"addons","required":false,"type":"string"},{"default":false,"description":"Generate a preview render image of the 3D model along with the model files.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preview_render","required":false,"type":"boolean"}],"lab":"Hyper3D","output_kind":"file","output_props":["model_mesh","model_meshes","seed","textures"],"pricing":"","published_at":"2025-09-26T19:59:28.021000+00:00","thumbnail":"https://v3.fal.media/files/lion/liLB7F5DWmR3CgbqjvZo3_2a3d75c59b5f4951810452fa8c27d0ba.jpg","title":"Hyper3d"},{"category":"image-to-3d","description":"Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images.","endpoint_id":"fal-ai/hyper3d/rodin/v2.5","family":"Rodin 2.5","inputs":[{"default":"","description":"A textual prompt to guide model generation. Optional for Image-to-3D mode - if empty, the model auto-generates a prompt from the images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of images to use while generating the 3D model. Required for Image-to-3D mode. Up to 5 images allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":false,"type":"string"},{"default":"Gen-2.5-High","description":"Generation tier. Higher tiers produce more detailed meshes but cost more. Extreme-High enables the highest-detail mode and bills at double the base rate. See more info in the [documentation](https://developer.hyper3d.ai/api-specification/rodin-gen2.5#use-gen-2.5-generation-with-following-gen-2.5-tiers). Selecting Gen-2.5-Minimum will automatically configure to a minimum mode, where 50K Triangle is selected, taking priority over quality_mesh_option.","enum":["Gen-2.5-Minimum","Gen-2.5-Extreme-Low","Gen-2.5-Low","Gen-2.5-Medium","Gen-2.5-High","Gen-2.5-Extreme-High"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tier","required":false,"type":"enum"},{"default":false,"description":"When enabled, preserves the transparency channel from input images during 3D generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_original_alpha","required":false,"type":"boolean"},{"default":null,"description":"Seed value for randomization, ranging from 0 to 65535. Optional.","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"glb","description":"Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.","enum":["glb","usdz","fbx","obj","stl"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_file_format","required":false,"type":"enum"},{"default":"All","description":"Material type. PBR: physically-based materials with realistic lighting. Shaded: baked lighting with no PBR maps. All: both PBR and Shaded variants. None: geometry only with no textures.","enum":["PBR","Shaded","All","None"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"material","required":false,"type":"enum"},{"default":"Auto","description":"Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. Maps to `mesh_mode` (Quad/Raw) and `quality_override` (face count) on the Hyper3D API. Valid face counts depend on the selected tier. Up to 1M Triangle is supported for tiers Extreme-Low, Low, and Medium. Up to 2M Triangle (as low as 20K Triangle) is supported for tiers High and Extreme-High. Auto option will choose the advised options for each tier:\n1. Gen-2.5-Minimum: 50K Triangle\n2. Gen-2.5-Extreme","enum":["Auto","4K Quad","8K Quad","18K Quad","50K Quad","100K Quad","200K Quad","2K Triangle","20K Triangle","50K Triangle","150K Triangle","500K Triangle","1M Triangle","2M Triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality_mesh_option","required":false,"type":"enum"},{"default":null,"description":"Texture generation quality. When unset, the API picks a default appropriate for the tier.","enum":["legacy","extreme-low","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_mode","required":false,"type":"enum"},{"default":false,"description":"If enabled, the generation will have enhanced generative robustness while ensuring output consistency. This corresponds to `geometry_instruct_mode` being equal to `creative` on the Hyper3D API.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_creative_mode","required":false,"type":"boolean"},{"default":false,"description":"Enables enhanced texture post-processing for higher visual fidelity.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hd_texture","required":false,"type":"boolean"},{"default":false,"description":"Removes baked lighting/highlights from the generated textures.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_delight","required":false,"type":"boolean"},{"default":false,"description":"Generate finer micro-scale geometric detail. Only effective with `tier=\"Gen-2.5-Extreme-High\"`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_micro","required":false,"type":"boolean"},{"default":false,"description":"Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"TAPose","required":false,"type":"boolean"},{"default":null,"description":"This is a controlnet that controls the maximum sized of the generated model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bbox_condition","required":false,"type":"json"},{"default":null,"description":"Optional add-ons. Single values are accepted as a shorthand for a list with one item.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"addons","required":false,"type":"json"},{"default":false,"description":"Generate a preview render image of the 3D model along with the model files.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preview_render","required":false,"type":"boolean"}],"lab":"Hyper3D","output_kind":"file","output_props":["model_mesh","model_meshes","seed","textures"],"pricing":"Your request will cost $0.4 per generation. Two tiers have different pricing than others:\n- Selecting `Gen-2.5-Extreme-High` will cost $0.8 per generation.\n- Selecting `Gen-2.5-Minimum`  will cost $0.1 per generation.\n\nFurthermore, if HighPack is added to the `addons`, it will cost an additional $0.8 per generation.","published_at":"2026-05-31T08:00:41.838000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c0a1e/4w033LTFt3oMtN64UMjaB_535f4f42c99240889b095fdbb92c72b7.jpg","title":"Hyper3D - Rodin V2.5 - Image to 3D"},{"category":"image-to-3d","description":"Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images. Do fast prototyping using the fast model.","endpoint_id":"fal-ai/hyper3d/rodin/v2.5/fast","family":"Rodin 2.5","inputs":[{"default":null,"description":"URL of images to use while generating the 3D model. Required for Image-to-3D mode. Up to 5 images allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":false,"type":"string"},{"default":"Gen-2.5-Extreme-Low","description":"Generation tier. See more info in the [documentation](https://developer.hyper3d.ai/api-specification/rodin-gen2.5#use-gen-2.5-generation-with-following-gen-2.5-tiers). Selecting Gen-2.5-Minimum will automatically configure to a minimum mode, where 50K Triangle is selected, taking priority over quality_mesh_option.","enum":["Gen-2.5-Minimum","Gen-2.5-Extreme-Low","Gen-2.5-Low"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tier","required":false,"type":"enum"},{"default":"","description":"A textual prompt to guide model generation. Optional for Image-to-3D mode - if empty, the model auto-generates a prompt from the images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":false,"description":"When enabled, preserves the transparency channel from input images during 3D generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_original_alpha","required":false,"type":"boolean"},{"default":null,"description":"Seed value for randomization, ranging from 0 to 65535. Optional.","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"glb","description":"Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.","enum":["glb","usdz","fbx","obj","stl"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_file_format","required":false,"type":"enum"},{"default":"Shaded","description":"Material type. PBR: physically-based materials with realistic lighting. Shaded: baked lighting with no PBR maps. All: both PBR and Shaded variants. None: geometry only with no textures.","enum":["PBR","Shaded","All","None"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"material","required":false,"type":"enum"},{"default":"Auto","description":"Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. Maps to `mesh_mode` (Quad/Raw) and `quality_override` (face count) on the Hyper3D API. Valid face counts depend on the selected tier. Up to 1M Triangle is supported for tiers Minimum, Extreme-Low, Low. For fast endpoint, this limit is up to 20K, primarily for prototyping and testing. For generating higher quality meshes, use the standard endpoint. Auto option will choose the advised options for each t","enum":["Auto","1K Quad","4K Quad","8K Quad","18K Quad","20K Quad","2K Triangle","4K Triangle","8K Triangle","10K Triangle","20K Triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality_mesh_option","required":false,"type":"enum"},{"default":null,"description":"Texture generation quality. When unset, the API picks a default appropriate for the tier.","enum":["legacy","extreme-low","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_mode","required":false,"type":"enum"},{"default":false,"description":"If enabled, the generation will have enhanced generative robustness while ensuring output consistency. This corresponds to `geometry_instruct_mode` being equal to `creative` on the Hyper3D API.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_creative_mode","required":false,"type":"boolean"},{"default":false,"description":"Enables enhanced texture post-processing for higher visual fidelity.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hd_texture","required":false,"type":"boolean"},{"default":false,"description":"Removes baked lighting/highlights from the generated textures.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_delight","required":false,"type":"boolean"},{"default":false,"description":"Generate finer micro-scale geometric detail. Only effective with `tier=\"Gen-2.5-Extreme-High\"`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_micro","required":false,"type":"boolean"},{"default":false,"description":"Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"TAPose","required":false,"type":"boolean"},{"default":null,"description":"This is a controlnet that controls the maximum sized of the generated model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bbox_condition","required":false,"type":"json"},{"default":null,"description":"Optional add-ons. Single values are accepted as a shorthand for a list with one item.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"addons","required":false,"type":"json"},{"default":false,"description":"Generate a preview render image of the 3D model along with the model files.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preview_render","required":false,"type":"boolean"}],"lab":"Hyper3D","output_kind":"file","output_props":["model_mesh","model_meshes","seed","textures"],"pricing":"Your request will cost $0.1 per generation. If HighPack is added to the `addons`, it will cost an additional $0.8 per generation.","published_at":"2026-06-19T18:08:24.070000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d154f/vAhd6ujr4i0bp9f238I9l_2901545ae364473781b3501c05e74f07.jpg","title":"Hyper3D - Rodin V2.5 - Image to 3D - Fast"},{"category":"text-to-3d","description":"Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images.","endpoint_id":"fal-ai/hyper3d/rodin/v2.5/text-to-3d","family":"Rodin 2.5","inputs":[{"default":null,"description":"A textual prompt to guide model generation. Required for Text-to-3D mode.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Gen-2.5-High","description":"Generation tier. Higher tiers produce more detailed meshes but cost more. Extreme-High enables the highest-detail mode and bills at double the base rate. See more info in the [documentation](https://developer.hyper3d.ai/api-specification/rodin-gen2.5#use-gen-2.5-generation-with-following-gen-2.5-tiers). Selecting Gen-2.5-Minimum will automatically configure to a minimum mode, where 50K Triangle is selected, taking priority over quality_mesh_option.","enum":["Gen-2.5-Minimum","Gen-2.5-Extreme-Low","Gen-2.5-Low","Gen-2.5-Medium","Gen-2.5-High","Gen-2.5-Extreme-High"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tier","required":false,"type":"enum"},{"default":null,"description":"Seed value for randomization, ranging from 0 to 65535. Optional.","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"glb","description":"Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.","enum":["glb","usdz","fbx","obj","stl"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_file_format","required":false,"type":"enum"},{"default":"All","description":"Material type. PBR: physically-based materials with realistic lighting. Shaded: baked lighting with no PBR maps. All: both PBR and Shaded variants. None: geometry only with no textures.","enum":["PBR","Shaded","All","None"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"material","required":false,"type":"enum"},{"default":"Auto","description":"Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. Maps to `mesh_mode` (Quad/Raw) and `quality_override` (face count) on the Hyper3D API. Valid face counts depend on the selected tier. Up to 1M Triangle is supported for tiers Extreme-Low, Low, and Medium. Up to 2M Triangle (as low as 20K Triangle) is supported for tiers High and Extreme-High. Auto option will choose the advised options for each tier:\n1. Gen-2.5-Minimum: 50K Triangle\n2. Gen-2.5-Extreme","enum":["Auto","4K Quad","8K Quad","18K Quad","50K Quad","100K Quad","200K Quad","2K Triangle","20K Triangle","50K Triangle","150K Triangle","500K Triangle","1M Triangle","2M Triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality_mesh_option","required":false,"type":"enum"},{"default":null,"description":"Texture generation quality. When unset, the API picks a default appropriate for the tier.","enum":["legacy","extreme-low","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_mode","required":false,"type":"enum"},{"default":false,"description":"If enabled, the generation will have enhanced generative robustness while ensuring output consistency. This corresponds to `geometry_instruct_mode` being equal to `creative` on the Hyper3D API.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_creative_mode","required":false,"type":"boolean"},{"default":false,"description":"Enables enhanced texture post-processing for higher visual fidelity.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hd_texture","required":false,"type":"boolean"},{"default":false,"description":"Removes baked lighting/highlights from the generated textures.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_delight","required":false,"type":"boolean"},{"default":false,"description":"Generate finer micro-scale geometric detail. Only effective with `tier=\"Gen-2.5-Extreme-High\"`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_micro","required":false,"type":"boolean"},{"default":false,"description":"Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"TAPose","required":false,"type":"boolean"},{"default":null,"description":"This is a controlnet that controls the maximum sized of the generated model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bbox_condition","required":false,"type":"json"},{"default":null,"description":"Optional add-ons","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"addons","required":false,"type":"json"}],"lab":"Hyper3D","output_kind":"file","output_props":["model_mesh","model_meshes","seed","textures"],"pricing":"Your request will cost $0.4 per generation. Two tiers have different pricing than others:\n- Selecting `Gen-2.5-Extreme-High` will cost $0.8 per generation.\n- Selecting `Gen-2.5-Minimum`  will cost $0.1 per generation.\n\nFurthermore, if HighPack is added to the `addons`, it will cost an additional $0.8 per generation.","published_at":"2026-05-31T08:01:11.402000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c09f7/S7oXUUqZ5T_1m_3sQIQTZ_a9493c9cafed4ba1a43db14d36c9d243.jpg","title":"Hyper3D - Rodin V2.5 - Text to 3D"},{"category":"text-to-3d","description":"Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images. Do fast prototyping using the fast model.","endpoint_id":"fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast","family":"Rodin 2.5","inputs":[{"default":null,"description":"A textual prompt to guide model generation. Required for Text-to-3D mode.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Gen-2.5-Extreme-Low","description":"Generation tier. See more info in the [documentation](https://developer.hyper3d.ai/api-specification/rodin-gen2.5#use-gen-2.5-generation-with-following-gen-2.5-tiers). Selecting Gen-2.5-Minimum will automatically configure to a minimum mode, where 50K Triangle is selected, taking priority over quality_mesh_option.","enum":["Gen-2.5-Minimum","Gen-2.5-Extreme-Low","Gen-2.5-Low"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tier","required":false,"type":"enum"},{"default":null,"description":"Seed value for randomization, ranging from 0 to 65535. Optional.","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"glb","description":"Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.","enum":["glb","usdz","fbx","obj","stl"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_file_format","required":false,"type":"enum"},{"default":"Shaded","description":"Material type. PBR: physically-based materials with realistic lighting. Shaded: baked lighting with no PBR maps. All: both PBR and Shaded variants. None: geometry only with no textures.","enum":["PBR","Shaded","All","None"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"material","required":false,"type":"enum"},{"default":"Auto","description":"Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. Maps to `mesh_mode` (Quad/Raw) and `quality_override` (face count) on the Hyper3D API. Valid face counts depend on the selected tier. Up to 1M Triangle is supported for tiers Minimum, Extreme-Low, Low. For fast endpoint, this limit is up to 20K, primarily for prototyping and testing. For generating higher quality meshes, use the standard endpoint. Auto option will choose the advised options for each t","enum":["Auto","1K Quad","4K Quad","8K Quad","18K Quad","20K Quad","2K Triangle","4K Triangle","8K Triangle","10K Triangle","20K Triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality_mesh_option","required":false,"type":"enum"},{"default":null,"description":"Texture generation quality. When unset, the API picks a default appropriate for the tier.","enum":["legacy","extreme-low","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_mode","required":false,"type":"enum"},{"default":false,"description":"If enabled, the generation will have enhanced generative robustness while ensuring output consistency. This corresponds to `geometry_instruct_mode` being equal to `creative` on the Hyper3D API.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_creative_mode","required":false,"type":"boolean"},{"default":false,"description":"Enables enhanced texture post-processing for higher visual fidelity.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hd_texture","required":false,"type":"boolean"},{"default":false,"description":"Removes baked lighting/highlights from the generated textures.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_delight","required":false,"type":"boolean"},{"default":false,"description":"Generate finer micro-scale geometric detail. Only effective with `tier=\"Gen-2.5-Extreme-High\"`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_micro","required":false,"type":"boolean"},{"default":false,"description":"Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"TAPose","required":false,"type":"boolean"},{"default":null,"description":"This is a controlnet that controls the maximum sized of the generated model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bbox_condition","required":false,"type":"json"},{"default":null,"description":"Optional add-ons","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"addons","required":false,"type":"json"}],"lab":"Hyper3D","output_kind":"file","output_props":["model_mesh","model_meshes","seed","textures"],"pricing":"Your request will cost $0.1 per generation. If HighPack is added to the `addons`, it will cost an additional $0.8 per generation.","published_at":"2026-06-19T20:15:10.273000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d156e/KgoS83QGNAiw4de9TFQGs_d1c95f9b763c452ea46048fbc905f6a2.jpg","title":"Hyper3D - Rodin V2.5 - Text to 3D - Fast"},{"category":"image-to-image","description":"An endpoint for re-lighting photos and changing their backgrounds per a given description","endpoint_id":"fal-ai/iclight-v2","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative Prompt for the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of mask to be used for ic-light conditioning image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"},{"default":0.67,"description":"Threshold for the background removal algorithm. A high threshold will produce sharper masks. Note: This parameter is currently deprecated and has no effect on the output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"background_threshold","required":false,"type":"number"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"None","description":"Provide lighting conditions for the model","enum":["None","Left","Right","Top","Bottom"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"initial_latent","required":false,"type":"enum"},{"default":false,"description":"Use HR fix","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_hr_fix","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1,"description":"The real classifier-free-guidance scale for the generation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.01,"multiline":false,"name":"cfg","required":false,"type":"number"},{"default":0.98,"description":"Strength for low-resolution pass.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"lowres_denoise","required":false,"type":"number"},{"default":0.95,"description":"Strength for high-resolution pass. Only used if enable_hr_fix is True.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"highres_denoise","required":false,"type":"number"},{"default":0.5,"description":"Hr Downscale","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"hr_downscale","required":false,"type":"number"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","seed","prompt","timings"],"pricing":"","published_at":"2024-11-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/iclight-v2/iclightv2-default-output.webp","title":"IC-Light-v2 for Image Relighting"},{"category":"image-to-image","description":"Generate consistent character appearances across multiple images. Maintain facial features, proportions, and distinctive traits for cohesive storytelling and branding","endpoint_id":"fal-ai/ideogram/character","family":"","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":"AUTO","description":"The style type to generate with. Cannot be used with style_codes.","enum":["AUTO","REALISTIC","FICTION"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The resolution of the generated image","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":true,"type":"string"},{"default":null,"description":"A set of masks to apply to the character references. Currently only 1 mask is supported, rest will be ignored. (maximum total size 10MB across all character references). The masks should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_mask_urls","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.1 with TURBO, $0.15 with BALANCED, and $0.20 with QUALITY.","published_at":"2025-08-07T15:57:16.318000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91bc/xiGs4r2UoW7L1KzJtXN45_Lq7fA5u1.png","title":"Ideogram V3 Character"},{"category":"image-to-image","description":"Modify consistent characters while preserving their core identity. Edit poses, expressions, or clothing without losing recognizable character features","endpoint_id":"fal-ai/ideogram/character/edit","family":"","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to generate an image from. MUST have the exact same dimensions (width and height) as the mask image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask URL to inpaint the image. MUST have the exact same dimensions (width and height) as the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":true,"type":"string"},{"default":null,"description":"A set of masks to apply to the character references. Currently only 1 mask is supported, rest will be ignored. (maximum total size 10MB across all character references). The masks should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_mask_urls","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.1 with TURBO, $0.15 with BALANCED, and $0.20 with QUALITY.","published_at":"2025-08-07T16:01:21.044000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9225/l6JUAF4awxWWUiUNecDp4_4R2a96Wk.png","title":"Ideogram V3 Character Edit"},{"category":"image-to-image","description":"Transform your consistent character into different art styles, settings, or scenarios while maintaining their distinctive appearance and identity","endpoint_id":"fal-ai/ideogram/character/remix","family":"","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":"AUTO","description":"The style type to generate with. Cannot be used with style_codes.","enum":["AUTO","REALISTIC","FICTION"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The prompt to remix the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to remix","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.8,"description":"Strength of the input image in the remix","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"square_hd","description":"The resolution of the generated image","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":true,"type":"string"},{"default":null,"description":"A set of masks to apply to the character references. Currently only 1 mask is supported, rest will be ignored. (maximum total size 10MB across all character references). The masks should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_mask_urls","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.1 with TURBO, $0.15 with BALANCED, and $0.20 with QUALITY.","published_at":"2025-08-07T15:52:27.577000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d9/eqDbKhjrsOA3KYzrUoApR_rdtChwG0.png","title":"Ideogram V3 Character Remix"},{"category":"training","description":"Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours","endpoint_id":"fal-ai/ideogram/custom-models","family":"","inputs":[{"default":null,"description":"URL of a ZIP archive of training images. The archive must contain between 10 and 100 images (JPEG, PNG, or WebP). You may include caption sidecar files (``<stem>.txt``) to guide training -- captions are matched to images by filename stem.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"images_data_url","required":true,"type":"string"}],"lab":"Ideogram","output_kind":"text","output_props":["custom_model_uri","model_id"],"pricing":"Your request will cost $40 per training run. For $50 you can run this model with approximately 1 times.","published_at":"2026-04-22T21:14:48.324000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a959ab4/7gbqk507YhA25ieYYgJ1C_6b6853c9b7504bab815827672a0b4727.jpg","title":"Ideogram"},{"category":"text-to-image","description":"Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours","endpoint_id":"fal-ai/ideogram/custom-models/generate","family":"","inputs":[{"default":null,"description":"The id of a trained custom model returned by /train. The model must have finished training (status COMPLETED).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_id","required":true,"type":"string"},{"default":null,"description":"Text prompt describing the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["1:3","3:1","1:2","2:1","9:16","16:9","10:16","16:10","2:3","3:2","3:4","4:3","4:5","5:4","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"","description":"Description of what to exclude from the image. Descriptions in the prompt take precedence over descriptions in the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2026-04-22T21:14:59.252000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97523a/X8mgYPEqIN_O5iBJzNxjF_bd259b2ee58d4514a4fbc2e39a1f5c4f.jpg","title":"Ideogram"},{"category":"image-to-image","description":"Remove backgrounds from existing images with Ideogram's remove background feature. Isolate subjects cleanly for compositing and creative reuse.","endpoint_id":"fal-ai/ideogram/remove-background","family":"","inputs":[{"default":null,"description":"The image URL whose background needs to be removed. The foreground subject is preserved against a transparent background. JPEG, PNG and WebP formats are supported (maximum file size 10MB).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Ideogram","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.01.","published_at":"2026-05-07T13:51:32.810000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a994224/Ges-wKqQd-Ohg9pgyRnB1_4c638022267d44ec9ae6617d3664f676.jpg","title":"Ideogram Remove Background"},{"category":"image-to-image","description":"Ideogram Upscale enhances the resolution of the reference image by up to 2X and might enhance the reference image too. Optionally refine outputs with a prompt for guided improvements.","endpoint_id":"fal-ai/ideogram/upscale","family":"","inputs":[{"default":null,"description":"The image URL to upscale","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"The prompt to upscale the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":50,"description":"The resemblance of the upscaled image to the original image","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"resemblance","required":false,"type":"integer"},{"default":50,"description":"The detail of the upscaled image","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"detail","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-02-10T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram Upscale"},{"category":"text-to-image","description":"Generate high-quality images, posters, and logos with Ideogram V2. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.","endpoint_id":"fal-ai/ideogram/v2","family":"Ideogram 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"","description":"A negative prompt to avoid in the generated image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-04T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b1/fT7LJ7aA6xdJeG3ho2KMQ_iNoBo8Fc.png","title":"Ideogram V2"},{"category":"image-to-image","description":"Transform existing images with Ideogram V2's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.","endpoint_id":"fal-ai/ideogram/v2/edit","family":"Ideogram 2","inputs":[{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask URL to inpaint the image. Needs to match the dimensions of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2 Edit"},{"category":"image-to-image","description":"Reimagine existing images with Ideogram V2's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.","endpoint_id":"fal-ai/ideogram/v2/remix","family":"Ideogram 2","inputs":[{"default":null,"description":"The prompt to remix the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to remix","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":0.8,"description":"Strength of the input image in the remix","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2 Remix"},{"category":"text-to-image","description":"Accelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.","endpoint_id":"fal-ai/ideogram/v2/turbo","family":"Ideogram 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"","description":"A negative prompt to avoid in the generated image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2 Turbo"},{"category":"image-to-image","description":"Edit images faster with Ideogram V2 Turbo. Quick modifications and adjustments while preserving the high-quality standards and realistic outputs of Ideogram.","endpoint_id":"fal-ai/ideogram/v2/turbo/edit","family":"Ideogram 2","inputs":[{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask URL to inpaint the image. Needs to match the dimensions of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2 Turbo Edit"},{"category":"image-to-image","description":"Rapidly create image variations with Ideogram V2 Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.","endpoint_id":"fal-ai/ideogram/v2/turbo/remix","family":"Ideogram 2","inputs":[{"default":null,"description":"The prompt to remix the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to remix","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":0.8,"description":"Strength of the input image in the remix","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-12-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2 Turbo Remix"},{"category":"text-to-image","description":"Generate high-quality images, posters, and logos with Ideogram V2A. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.","endpoint_id":"fal-ai/ideogram/v2a","family":"Ideogram 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9397/iYrbdLjk3df1QO8sFrCDQ_f7lKoyrT.png","title":"Ideogram V2A"},{"category":"image-to-image","description":"Create variations of existing images with Ideogram V2A Remix while maintaining creative control through prompt guidance.","endpoint_id":"fal-ai/ideogram/v2a/remix","family":"Ideogram 2","inputs":[{"default":null,"description":"The prompt to remix the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to remix","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":0.8,"description":"Strength of the input image in the remix","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2A Remix"},{"category":"text-to-image","description":"Accelerated image generation with Ideogram V2A Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.","endpoint_id":"fal-ai/ideogram/v2a/turbo","family":"Ideogram 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cd/kEbnhx2a3FrCxBo23WhQu_OYP0j4Qr.png","title":"Ideogram V2A Turbo"},{"category":"image-to-image","description":"Rapidly create image variations with Ideogram V2A Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.","endpoint_id":"fal-ai/ideogram/v2a/turbo/remix","family":"Ideogram 2","inputs":[{"default":null,"description":"The prompt to remix the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to remix","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image","enum":["10:16","16:10","9:16","16:9","4:3","3:4","1:1","1:3","3:1","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":0.8,"description":"Strength of the input image in the remix","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":true,"description":"Whether to expand the prompt with MagicPrompt functionality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The style of the generated image","enum":["auto","general","realistic","design","render_3D","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V2A Turbo Remix"},{"category":"text-to-image","description":"Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.","endpoint_id":"fal-ai/ideogram/v3","family":"Ideogram 3","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":null,"description":"The style type to generate with. Cannot be used with style_codes.","enum":["AUTO","GENERAL","REALISTIC","DESIGN"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Style preset for generation. The chosen style preset will guide the generation.","enum":["80S_ILLUSTRATION","90S_NOSTALGIA","ABSTRACT_ORGANIC","ANALOG_NOSTALGIA","ART_BRUT","ART_DECO","ART_POSTER","AURA","AVANT_GARDE","BAUHAUS","BLUEPRINT","BLURRY_MOTION","BRIGHT_ART","C4D_CARTOON","CHILDRENS_BOOK","COLLAGE","COLORING_BOOK_I","COLORING_BOOK_II","CUBISM","DARK_AURA","DOODLE","DOUBLE_EXPOSURE","DRAMATIC_CINEMA","EDITORIAL","EMOTIONAL_MINIMAL","ETHEREAL_PARTY","EXPIRED_FILM","FLAT_ART","FLAT_VECTOR","FOREST_REVERIE","GEO_MINIMALIST","GLASS_PRISM","GOLDEN_HOUR","GRAFFITI_I","GRAFFITI_II","HALFTONE_PRINT","HIGH_CONTRAST","HIPPIE_ERA","ICONIC","JAPANDI_FUSION","JAZZY","LONG_EXPOSURE","MAGAZINE_EDITORIAL","MINIMAL_ILLUSTRATION","MIXED_MEDIA","MONOCHROME","NIGHTLIFE","OIL_PAINTING","OLD_CARTOONS","PAINT_GESTURE","POP_ART","RETRO_ETCHING","RIVIERA_POP","SPOTLIGHT_80S","STYLIZED_RED","SURREAL_COLLAGE","TRAVEL_POSTER","VINTAGE_GEO","VINTAGE_POSTER","WATERCOLOR","WEIRD","WOODBLOCK_PRINT"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_preset","required":false,"type":"enum"},{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The resolution of the generated image","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2025-05-01T16:04:02.805000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91a8/JsTVqtZydplqvV_XGPvTV_5FOy6fcj.png","title":"Ideogram Text to Image"},{"category":"image-to-image","description":"Transform existing images with Ideogram V3's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.","endpoint_id":"fal-ai/ideogram/v3/edit","family":"Ideogram 3","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Style preset for generation. The chosen style preset will guide the generation.","enum":["80S_ILLUSTRATION","90S_NOSTALGIA","ABSTRACT_ORGANIC","ANALOG_NOSTALGIA","ART_BRUT","ART_DECO","ART_POSTER","AURA","AVANT_GARDE","BAUHAUS","BLUEPRINT","BLURRY_MOTION","BRIGHT_ART","C4D_CARTOON","CHILDRENS_BOOK","COLLAGE","COLORING_BOOK_I","COLORING_BOOK_II","CUBISM","DARK_AURA","DOODLE","DOUBLE_EXPOSURE","DRAMATIC_CINEMA","EDITORIAL","EMOTIONAL_MINIMAL","ETHEREAL_PARTY","EXPIRED_FILM","FLAT_ART","FLAT_VECTOR","FOREST_REVERIE","GEO_MINIMALIST","GLASS_PRISM","GOLDEN_HOUR","GRAFFITI_I","GRAFFITI_II","HALFTONE_PRINT","HIGH_CONTRAST","HIPPIE_ERA","ICONIC","JAPANDI_FUSION","JAZZY","LONG_EXPOSURE","MAGAZINE_EDITORIAL","MINIMAL_ILLUSTRATION","MIXED_MEDIA","MONOCHROME","NIGHTLIFE","OIL_PAINTING","OLD_CARTOONS","PAINT_GESTURE","POP_ART","RETRO_ETCHING","RIVIERA_POP","SPOTLIGHT_80S","STYLIZED_RED","SURREAL_COLLAGE","TRAVEL_POSTER","VINTAGE_GEO","VINTAGE_POSTER","WATERCOLOR","WEIRD","WOODBLOCK_PRINT"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_preset","required":false,"type":"enum"},{"default":null,"description":"The prompt to fill the masked part of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to generate an image from. MUST have the exact same dimensions (width and height) as the mask image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The mask URL to inpaint the image. MUST have the exact same dimensions (width and height) as the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2025-05-01T15:58:51.368000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ideogram.webp","title":"Ideogram V3 Edit"},{"category":"text-to-image","description":"Generate images with transparent backgrounds using Ideogram Transparent model","endpoint_id":"fal-ai/ideogram/v3/generate-transparent","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["1:3","3:1","1:2","2:1","9:16","16:9","10:16","16:10","2:3","3:2","3:4","4:3","4:5","5:4","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"","description":"Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2026-04-07T13:35:57.791000+00:00","thumbnail":"https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a9460fb%2FV1jBCmRURHcAj0aDFobEG_25307fd3e04d409fac27e233f89a8808.jpg/tr:w-1920,q-80/V1jBCmRURHcAj0aDFobEG_25307fd3e04d409fac27e233f89a8808.webp","title":"Ideogram Transparent"},{"category":"image-to-image","description":"Ideogram Layerize takes an existing flat graphic, removes text, and returns structured text containers you can edit/recompose in html or json format.","endpoint_id":"fal-ai/ideogram/v3/layerize-text","family":"Layerize","inputs":[{"default":null,"description":"URL of the flat graphic image to layerize. Must be JPEG, PNG, or WebP (max 10MB).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional prompt to guide the layerization.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the font file to use for h1 text. Cannot be used with font_name_h1.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"font_file_h1_url","required":false,"type":"string"},{"default":null,"description":"Name of the font to use for h1 text. Cannot be used with font_file_h1_url.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_name_h1","required":false,"type":"string"},{"default":null,"description":"URL of the font file to use for h2 text. Cannot be used with font_name_h2.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"font_file_h2_url","required":false,"type":"string"},{"default":null,"description":"Name of the font to use for h2 text. Cannot be used with font_file_h2_url.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_name_h2","required":false,"type":"string"},{"default":null,"description":"URL of the font file to use for body text. Cannot be used with font_name_body.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"font_file_body_url","required":false,"type":"string"},{"default":null,"description":"Name of the font to use for body text. Cannot be used with font_file_body_url.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_name_body","required":false,"type":"string"},{"default":null,"description":"URL of the font file to use for small text. Cannot be used with font_name_small.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"font_file_small_url","required":false,"type":"string"},{"default":null,"description":"Name of the font to use for small text. Cannot be used with font_file_small_url.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_name_small","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"image","output_props":["text_html","prompt","seed","image_layers","text_containers","image"],"pricing":"","published_at":"2026-04-07T14:26:20.671000+00:00","thumbnail":"https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a9460fc%2FqOhhsjsE6IMg_rU1F0CVn_1a3a46a9131e4cbeaacf3314339c8d35.jpg/tr:w-1920,q-80/qOhhsjsE6IMg_rU1F0CVn_1a3a46a9131e4cbeaacf3314339c8d35.webp","title":"Ideogram"},{"category":"image-to-image","description":"Extend existing images with Ideogram V3's reframe feature. Create expanded versions and adaptations while preserving main image and adding new creative directions through prompt guidance.","endpoint_id":"fal-ai/ideogram/v3/reframe","family":"Ideogram 3","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":null,"description":"The style type to generate with. Cannot be used with style_codes.","enum":["AUTO","GENERAL","REALISTIC","DESIGN"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Style preset for generation. The chosen style preset will guide the generation.","enum":["80S_ILLUSTRATION","90S_NOSTALGIA","ABSTRACT_ORGANIC","ANALOG_NOSTALGIA","ART_BRUT","ART_DECO","ART_POSTER","AURA","AVANT_GARDE","BAUHAUS","BLUEPRINT","BLURRY_MOTION","BRIGHT_ART","C4D_CARTOON","CHILDRENS_BOOK","COLLAGE","COLORING_BOOK_I","COLORING_BOOK_II","CUBISM","DARK_AURA","DOODLE","DOUBLE_EXPOSURE","DRAMATIC_CINEMA","EDITORIAL","EMOTIONAL_MINIMAL","ETHEREAL_PARTY","EXPIRED_FILM","FLAT_ART","FLAT_VECTOR","FOREST_REVERIE","GEO_MINIMALIST","GLASS_PRISM","GOLDEN_HOUR","GRAFFITI_I","GRAFFITI_II","HALFTONE_PRINT","HIGH_CONTRAST","HIPPIE_ERA","ICONIC","JAPANDI_FUSION","JAZZY","LONG_EXPOSURE","MAGAZINE_EDITORIAL","MINIMAL_ILLUSTRATION","MIXED_MEDIA","MONOCHROME","NIGHTLIFE","OIL_PAINTING","OLD_CARTOONS","PAINT_GESTURE","POP_ART","RETRO_ETCHING","RIVIERA_POP","SPOTLIGHT_80S","STYLIZED_RED","SURREAL_COLLAGE","TRAVEL_POSTER","VINTAGE_GEO","VINTAGE_POSTER","WATERCOLOR","WEIRD","WOODBLOCK_PRINT"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_preset","required":false,"type":"enum"},{"default":null,"description":"The image URL to reframe","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The resolution for the reframed output image","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":true,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2025-05-01T16:06:34.467000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b5/UMfZEO-26SBc2j_rn6AiG_pNsWS6uZ.png","title":"Ideogram"},{"category":"image-to-image","description":"Reimagine existing images with Ideogram V3's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.","endpoint_id":"fal-ai/ideogram/v3/remix","family":"Ideogram 3","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":null,"description":"The style type to generate with. Cannot be used with style_codes.","enum":["AUTO","GENERAL","REALISTIC","DESIGN"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The prompt to remix the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to remix","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.8,"description":"Strength of the input image in the remix","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"square_hd","description":"The resolution of the generated image","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2025-05-01T16:01:06.063000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922a/hQWTAUexHCA5fGGsYPWgn_APzlr9wQ.png","title":"Ideogram"},{"category":"image-to-image","description":"Replace backgrounds existing images with Ideogram V3's replace background feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.","endpoint_id":"fal-ai/ideogram/v3/replace-background","family":"Ideogram 3","inputs":[{"default":null,"description":"A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"BALANCED","description":"The rendering speed to use.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":null,"description":"A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"color_palette","required":false,"type":"json"},{"default":null,"description":"A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_codes","required":false,"type":"string"},{"default":null,"description":"The style type to generate with. Cannot be used with style_codes.","enum":["AUTO","GENERAL","REALISTIC","DESIGN"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":true,"description":"Determine if MagicPrompt should be used in generating the request or not.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Style preset for generation. The chosen style preset will guide the generation.","enum":["80S_ILLUSTRATION","90S_NOSTALGIA","ABSTRACT_ORGANIC","ANALOG_NOSTALGIA","ART_BRUT","ART_DECO","ART_POSTER","AURA","AVANT_GARDE","BAUHAUS","BLUEPRINT","BLURRY_MOTION","BRIGHT_ART","C4D_CARTOON","CHILDRENS_BOOK","COLLAGE","COLORING_BOOK_I","COLORING_BOOK_II","CUBISM","DARK_AURA","DOODLE","DOUBLE_EXPOSURE","DRAMATIC_CINEMA","EDITORIAL","EMOTIONAL_MINIMAL","ETHEREAL_PARTY","EXPIRED_FILM","FLAT_ART","FLAT_VECTOR","FOREST_REVERIE","GEO_MINIMALIST","GLASS_PRISM","GOLDEN_HOUR","GRAFFITI_I","GRAFFITI_II","HALFTONE_PRINT","HIGH_CONTRAST","HIPPIE_ERA","ICONIC","JAPANDI_FUSION","JAZZY","LONG_EXPOSURE","MAGAZINE_EDITORIAL","MINIMAL_ILLUSTRATION","MIXED_MEDIA","MONOCHROME","NIGHTLIFE","OIL_PAINTING","OLD_CARTOONS","PAINT_GESTURE","POP_ART","RETRO_ETCHING","RIVIERA_POP","SPOTLIGHT_80S","STYLIZED_RED","SURREAL_COLLAGE","TRAVEL_POSTER","VINTAGE_GEO","VINTAGE_POSTER","WATERCOLOR","WEIRD","WOODBLOCK_PRINT"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_preset","required":false,"type":"enum"},{"default":null,"description":"Cyber punk city with neon lights and skyscrappers","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL whose background needs to be replaced","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Ideogram","output_kind":"images","output_props":["images","seed"],"pricing":"Your request will cost $0.03 with TURBO, $0.06 with BALANCED, and $0.09 with QUALITY.","published_at":"2025-05-01T16:02:45.350000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922c/Dxo3RJZ-NBI-rqA3uoQZZ_uIvF8ntu.png","title":"Ideogram Replace Background"},{"category":"text-to-image","description":"Create illusions conditioned on image.","endpoint_id":"fal-ai/illusion-diffusion","family":"","inputs":[{"default":null,"description":"Input image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The scale of the ControlNet.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":0,"description":"Control Guidance Start","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_guidance_start","required":false,"type":"number"},{"default":1,"description":"Control Guidance End","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_guidance_end","required":false,"type":"number"},{"default":null,"description":"Seed of the generated Image. It will be the same value of the one passed in the\n            input or the randomly generated that was used in case none was passed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"Euler","description":"Scheduler / sampler to use for the image denoising process.","enum":["DPM++ Karras SDE","Euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":40,"description":"Increasing the amount of steps tells Stable Diffusion that it should take more steps\n            to generate your final result which can increase the amount of detail in your image.","enum":null,"is_list":false,"max":80,"media_kind":null,"min":0,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the generated image. You can choose between some presets or\n            custom height and width that **must be multiples of 8**.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["image","seed"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/illusion-diffusion.jpeg","title":"Illusion Diffusion"},{"category":"image-to-image","description":"Modify a face to look younger or older while keeping identity realistic.","endpoint_id":"fal-ai/image-apps-v2/age-modify","family":"","inputs":[{"default":null,"description":"Portrait image URL for age modification","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":30,"description":"Target Age","enum":null,"is_list":false,"max":100,"media_kind":null,"min":6,"multiline":false,"name":"target_age","required":false,"type":"integer"},{"default":true,"description":"Preserve Identity","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_identity","required":false,"type":"boolean"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for portraits)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:02:59.169000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d1/Qxw_mCwonRGWuTHeZO8ws_WLSTUVaP.png","title":"Age Modify"},{"category":"image-to-image","description":"Place a person’s photo into iconic cities worldwide.","endpoint_id":"fal-ai/image-apps-v2/city-teleport","family":"","inputs":[{"default":null,"description":"Person photo URL","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"person_image_url","required":true,"type":"string"},{"default":null,"description":"Optional city background image URL. When provided, the person will be blended into this custom scene.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"city_image_url","required":false,"type":"string"},{"default":null,"description":"City name (used when city_image_url is not provided)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"city_name","required":true,"type":"string"},{"default":"medium_shot","description":"Type of photo shot","enum":["extreme_close_up","close_up","medium_close_up","medium_shot","medium_long_shot","long_shot","extreme_long_shot","full_body"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"photo_shot","required":false,"type":"enum"},{"default":"eye_level","description":"Camera angle for the shot","enum":["eye_level","low_angle","high_angle","dutch_angle","birds_eye_view","worms_eye_view","overhead","side_angle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_angle","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:15:37.483000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a44/DmmHeOLhOrrRZ7ZkkHAiL_iIicRbwy.png","title":"City Teleport"},{"category":"image-to-image","description":"Change facial expressions in photos with realistic results.","endpoint_id":"fal-ai/image-apps-v2/expression-change","family":"","inputs":[{"default":null,"description":"Portrait image URL for expression change","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"smile","description":"Target Expression","enum":["smile","surprise","glare","panic","shyness","laugh","cry","angry","sad","happy","excited","shocked","confused","focused","dreamy","serious","playful","mysterious","confident","thoughtful"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_expression","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for portraits)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:19:36.092000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9399/1xwlPDXChlONvXBANlDA2_cr0Axu7D.png","title":"Expression Change"},{"category":"image-to-image","description":"Change hairstyles and hair colors in photos realistically.","endpoint_id":"fal-ai/image-apps-v2/hair-change","family":"","inputs":[{"default":null,"description":"Portrait image URL for hair change","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"long_hair","description":"Target Hairstyle","enum":["short_hair","medium_long_hair","long_hair","curly_hair","wavy_hair","high_ponytail","bun","bob_cut","pixie_cut","braids","straight_hair","afro","dreadlocks","buzz_cut","mohawk","bangs","side_part","middle_part"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_hairstyle","required":false,"type":"enum"},{"default":"natural","description":"Hair Color","enum":["black","dark_brown","light_brown","blonde","platinum_blonde","red","auburn","gray","silver","blue","green","purple","pink","rainbow","natural","highlights","ombre","balayage"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hair_color","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for portraits)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:21:48.130000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cc/aUmpKwGz4nPeB6JqmAyxr_pKYFLz4u.png","title":"Hair Change"},{"category":"image-to-image","description":"Generate professional headshot photos with customizable backgrounds.","endpoint_id":"fal-ai/image-apps-v2/headshot-photo","family":"","inputs":[{"default":null,"description":"Portrait image URL to convert to professional headshot","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"professional","description":"Background Style","enum":["professional","corporate","clean","gradient"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_style","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for portraits)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:24:48.033000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9397/qOgy4s7YmYEJqKtZYJXm4_2ub0fLrs.png","title":"Headshot Generator"},{"category":"image-to-image","description":"Apply realistic makeup styles with adjustable intensity.","endpoint_id":"fal-ai/image-apps-v2/makeup-application","family":"","inputs":[{"default":null,"description":"Portrait image URL for makeup application","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"natural","description":"Makeup Style","enum":["natural","glamorous","smoky_eyes","bold_lips","no_makeup","remove_makeup","dramatic","bridal","professional","korean_style","artistic"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"makeup_style","required":false,"type":"enum"},{"default":"medium","description":"Intensity","enum":["light","medium","heavy","dramatic"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"intensity","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for portraits)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T00:58:57.450000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d9/3qIFHMUe2cB8r_aGBf_rZ_qCgzTa6I.png","title":"Makeup Changer"},{"category":"image-to-image","description":"Remove unwanted objects seamlessly from any image.","endpoint_id":"fal-ai/image-apps-v2/object-removal","family":"","inputs":[{"default":null,"description":"Image URL containing object to remove","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Object to remove","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"object_to_remove","required":true,"type":"string"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:32:20.301000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a1/9e5lSoXKfkc0nB0TfzOYu_IGJ9mYAg.png","title":"Object Removal"},{"category":"image-to-image","description":"Directional outpainting. Choose edges to expand. left, right, top, or center (uniform all sides). Only expanded areas are generated; an optional zoom-out pulls the frame back by the chosen amount.","endpoint_id":"fal-ai/image-apps-v2/outpaint","family":"","inputs":[{"default":null,"description":"Image URL to outpaint","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0,"description":"Number of pixels to add as black margin on the left side (0-700).","enum":null,"is_list":false,"max":700,"media_kind":null,"min":0,"multiline":false,"name":"expand_left","required":false,"type":"integer"},{"default":0,"description":"Number of pixels to add as black margin on the right side (0-700).","enum":null,"is_list":false,"max":700,"media_kind":null,"min":0,"multiline":false,"name":"expand_right","required":false,"type":"integer"},{"default":0,"description":"Number of pixels to add as black margin on the top side (0-700).","enum":null,"is_list":false,"max":700,"media_kind":null,"min":0,"multiline":false,"name":"expand_top","required":false,"type":"integer"},{"default":0,"description":"Number of pixels to add as black margin on the bottom side (0-700).","enum":null,"is_list":false,"max":700,"media_kind":null,"min":0,"multiline":false,"name":"expand_bottom","required":false,"type":"integer"},{"default":20,"description":"Percentage to zoom out the image. If set, the image will be scaled down by this percentage and black margins will be added to maintain original size. Example: 50 means the image will be 50% of original size with black margins filling the rest.","enum":null,"is_list":false,"max":90,"media_kind":null,"min":0,"multiline":false,"name":"zoom_out_percentage","required":false,"type":"number"},{"default":"","description":"Optional prompt to guide the outpainting. If provided, it will be appended to the base outpaint instruction. Example: 'with a beautiful sunset in the background'","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image.","enum":["png","jpeg","jpg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-03T19:28:15.419000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/_JfxHHU5PSR2RsM0r9O3S_549a1d78995c4babae440a2d345e621b.jpg","title":"Image Outpaint"},{"category":"image-to-image","description":"Easily adjust the perspective of any image to different angles.","endpoint_id":"fal-ai/image-apps-v2/perspective","family":"","inputs":[{"default":null,"description":"Image URL for perspective change","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"front","description":"Target Perspective","enum":["front","left_side","right_side","back","top_down","bottom_up","birds_eye","three_quarter_left","three_quarter_right"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_perspective","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:35:34.670000+00:00","thumbnail":"https://v3.fal.media/files/rabbit/PjquFEk5HynXyIj8Z1Xke_4ef010a6c99b4fa2a1f6639c233f8b93.jpg","title":"Perspective Change"},{"category":"image-to-image","description":"Restore old or damaged photos by fixing colors, scratches, and resolution.","endpoint_id":"fal-ai/image-apps-v2/photo-restoration","family":"","inputs":[{"default":null,"description":"Old or damaged photo URL to restore","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":true,"description":"Enhance Resolution","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_resolution","required":false,"type":"boolean"},{"default":true,"description":"Fix Colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fix_colors","required":false,"type":"boolean"},{"default":true,"description":"Remove Scratches","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remove_scratches","required":false,"type":"boolean"},{"default":null,"description":"Aspect ratio for 4K output (default: 4:3 for classic photos)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:43:11.542000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/oP9mu0F1Obx0ufyEEVAgn_3f7a878f3cf54a078fa8e0d53524020a.jpg","title":"Photo Restoration"},{"category":"image-to-image","description":"Apply diverse photography styles and effects to transform your images.","endpoint_id":"fal-ai/image-apps-v2/photography-effects","family":"","inputs":[{"default":null,"description":"Image URL for photography effects","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"film","description":"Effect Type","enum":["film","vintage_film","portrait_photography","fashion_photography","street_photography","sepia_tone","film_grain","light_leaks","vignette_effect","instant_camera","golden_hour","dramatic_lighting","soft_focus","bokeh_effect","high_contrast","double_exposure"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect_type","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:38:43.720000+00:00","thumbnail":"https://v3.fal.media/files/rabbit/QHdnOcB8IwyNRSkQOeVWE_aad27ab63cee47e8b6c15254f6813ac2.jpg","title":"Photography Effects"},{"category":"image-to-image","description":"Enhance and refine portrait photos with improved clarity and detail.","endpoint_id":"fal-ai/image-apps-v2/portrait-enhance","family":"","inputs":[{"default":null,"description":"Portrait image URL to enhance","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for portraits)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:40:36.113000+00:00","thumbnail":"https://v3.fal.media/files/monkey/9kZMXV4GvRettHUuudKER_3f04e4f8fd0e4f28ad957c2a3bf9f3e5.jpg","title":"Portrait Enhance"},{"category":"image-to-image","description":"Place products naturally in a person’s hands for realistic marketing visuals.","endpoint_id":"fal-ai/image-apps-v2/product-holding","family":"","inputs":[{"default":null,"description":"Image URL of the person who will hold the product","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"person_image_url","required":true,"type":"string"},{"default":null,"description":"Image URL of the product to be held by the person","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"product_image_url","required":true,"type":"string"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-19T02:20:46.300000+00:00","thumbnail":"https://v3.fal.media/files/zebra/7dJ2m31gOP0J0m8WZJ46I_1625d9610207407292eac394cc4a3026.jpg","title":"Product Holding"},{"category":"image-to-image","description":"Generate professional product photography with realistic lighting and backgrounds.","endpoint_id":"fal-ai/image-apps-v2/product-photography","family":"","inputs":[{"default":null,"description":"Image URL of the product to create professional studio photography","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"product_image_url","required":true,"type":"string"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-19T02:20:29.618000+00:00","thumbnail":"https://v3.fal.media/files/penguin/g36T9svKmdie3DHtxJz5x_67cde98934654713bf484b258e2384f3.jpg","title":"Product Photography"},{"category":"image-to-image","description":"Adjust and enhance images with different lighting styles.","endpoint_id":"fal-ai/image-apps-v2/relighting","family":"","inputs":[{"default":null,"description":"Image URL for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"natural","description":"Lighting Style","enum":["natural","studio","golden_hour","blue_hour","dramatic","soft","hard","backlight","side_light","front_light","rim_light","sunset","sunrise","neon","candlelight","moonlight","spotlight","ambient"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"lighting_style","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:45:02.577000+00:00","thumbnail":"https://v3.fal.media/files/koala/W0d6z5pWtVwakzxtKd4K4_94f6ab5b5820440db672dce73d447bff.jpg","title":"Relighting"},{"category":"image-to-image","description":"Apply artistic styles like impressionism, cubism, or surrealism to your images.","endpoint_id":"fal-ai/image-apps-v2/style-transfer","family":"","inputs":[{"default":null,"description":"Image URL for style transfer","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional reference image URL. When provided, the style will be inferred from this image instead of the selected preset style.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"style_reference_image_url","required":false,"type":"string"},{"default":"impressionist","description":"Target Style","enum":["anime_character","cartoon_3d","hand_drawn_animation","cyberpunk_future","anime_game_style","comic_book_animation","animated_series","cartoon_animation","lofi_aesthetic","cottagecore","dark_academia","y2k","vaporwave","liminal_space","weirdcore","dreamcore","synthwave","outrun","photorealistic","hyperrealistic","digital_art","concept_art","impressionist","anime","pixel_art","claymation"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_style","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:44:34.974000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/uZNy5XjPfUQJOs0Kuw7C4_367de9bbd3034716b9432d637c3b369d.jpg","title":"Style Transfer"},{"category":"image-to-image","description":"Transform objects with different surface textures like marble, wood, or fabric.","endpoint_id":"fal-ai/image-apps-v2/texture-transform","family":"","inputs":[{"default":null,"description":"Image URL for texture transformation","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"marble","description":"Target Texture","enum":["cotton","denim","wool","felt","wood","leather","velvet","stone","marble","ceramic","concrete","brick","clay","foam","glass","metal","silk","fabric","crystal","rubber","plastic","lace"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_texture","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio for 4K output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:47:30.542000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/gzXctbp7SzO3xaVpDEqtN_97343b9e7b404a3e8f042b1d7d57a12f.jpg","title":"Texture Transform"},{"category":"image-to-image","description":"Try on clothes virtually by combining person and clothing images.","endpoint_id":"fal-ai/image-apps-v2/virtual-try-on","family":"","inputs":[{"default":null,"description":"Person photo URL","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"person_image_url","required":true,"type":"string"},{"default":null,"description":"Clothing photo URL","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"clothing_image_url","required":true,"type":"string"},{"default":true,"description":"Preserve Pose","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_pose","required":false,"type":"boolean"},{"default":null,"description":"Aspect ratio for 4K output (default: 3:4 for fashion)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"json"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-09-18T01:55:22.732000+00:00","thumbnail":"https://v3.fal.media/files/tiger/dd5748sfMpq2uZzoUA_Y3_6377b3f9ee8e49afa174da674a80b9a6.jpg","title":"Virtual Try-on"},{"category":"image-to-image","description":"See how you or others might look at different ages, from younger to older, while preserving core facial features.","endpoint_id":"fal-ai/image-editing/age-progression","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"20 years older","description":"The age change to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:28:40.116000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Age Progression"},{"category":"image-to-image","description":"Transform any person into their baby version, while preserving the original pose and expression with childlike features.","endpoint_id":"fal-ai/image-editing/baby-version","family":"","inputs":[{"default":null,"description":"URL of the image to transform into a baby version.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-03T20:07:31.667000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing"},{"category":"image-to-image","description":"Replace your photo's background with any scene you desire, from beach sunsets to urban landscapes, with perfect lighting and shadows","endpoint_id":"fal-ai/image-editing/background-change","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"beach sunset with palm trees","description":"The desired background to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:28:46.061000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Background Change"},{"category":"image-to-image","description":"Transform your character's hair into broccoli style while keeping the original characters likeness","endpoint_id":"fal-ai/image-editing/broccoli-haircut","family":"","inputs":[{"default":null,"description":"URL of the image to apply broccoli haircut style.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-26T04:41:08.203000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939b/Yh9v_6-HKHsj9x6myPznA_teDtepfT.png","title":"Image Editing Broccoli Haircut"},{"category":"image-to-image","description":"Transform your photos into vibrant cool cartoons with bold outlines and rich colors.","endpoint_id":"fal-ai/image-editing/cartoonify","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:28:53.641000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Cartoonify"},{"category":"image-to-image","description":"Perfect your photos with professional color grading, balanced tones, and vibrant yet natural colors","endpoint_id":"fal-ai/image-editing/color-correction","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:00.034000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Color Correction"},{"category":"image-to-image","description":"Change facial expressions in photos to any emotion you desire, from smiles to serious looks.","endpoint_id":"fal-ai/image-editing/expression-change","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"sad","description":"The desired facial expression to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:05.309000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Expression Change"},{"category":"image-to-image","description":"Enhance facial features with professional retouching while maintaining a natural, realistic look","endpoint_id":"fal-ai/image-editing/face-enhancement","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:10.990000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Face Enhancement"},{"category":"image-to-image","description":"Experiment with different hairstyles, from bald to any style you can imagine, while maintaining natural lighting and realistic results.","endpoint_id":"fal-ai/image-editing/hair-change","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"bald","description":"The desired hair style to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:16.914000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Hair Change"},{"category":"image-to-image","description":"Remove unwanted objects or people from your photos while seamlessly blending the background.","endpoint_id":"fal-ai/image-editing/object-removal","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"background people","description":"Specify which objects to remove from the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:21.865000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Object Removal"},{"category":"image-to-image","description":"Restore and enhance old or damaged photos by removing imperfections, adding color while preserving the original character and details of the image.","endpoint_id":"fal-ai/image-editing/photo-restoration","family":"","inputs":[{"default":null,"description":"URL of the old or damaged photo to restore.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-02T02:41:12.926000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Photo Restoration"},{"category":"image-to-image","description":"Transform your photos into cool plushies while keeping the original characters likeness","endpoint_id":"fal-ai/image-editing/plushie-style","family":"","inputs":[{"default":null,"description":"URL of the image to convert to plushie style.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-26T04:29:50.482000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Plushie Style"},{"category":"image-to-image","description":"Turn your casual photos into stunning professional studio portraits with perfect lighting and high-end photography style.","endpoint_id":"fal-ai/image-editing/professional-photo","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:27.931000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Professional Photo"},{"category":"image-to-image","description":"Add details to faces, enhance face features, remove blur.","endpoint_id":"fal-ai/image-editing/realism","family":"","inputs":[{"default":null,"description":"URL of the image to enhance with realism details.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":0.6,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-07-07T10:12:01.612000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Realism"},{"category":"image-to-image","description":"The reframe endpoint intelligently adjusts an image's aspect ratio while preserving the main subject's position, composition, pose, and perspective","endpoint_id":"fal-ai/image-editing/reframe","family":"","inputs":[{"default":null,"description":"URL of the old or damaged photo to restore.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"16:9","description":"The desired aspect ratio for the reframed image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-05T16:34:57.998000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Reframe"},{"category":"image-to-image","description":"Retouch photos of faces. Remove blemishes and improve the skin.","endpoint_id":"fal-ai/image-editing/retouch","family":"","inputs":[{"default":null,"description":"URL of the image to retouch.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-07-24T18:06:19.737000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-4.jpg","title":"Image Editing Retouch"},{"category":"image-to-image","description":"Place your subject in any scene you imagine, from enchanted forests to urban settings, with professional composition and lighting","endpoint_id":"fal-ai/image-editing/scene-composition","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"enchanted forest","description":"Describe the scene where you want to place the subject.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:34.336000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Scene Composition"},{"category":"image-to-image","description":"Transform your photos into artistic masterpieces inspired by famous styles like Van Gogh's Starry Night or any artistic style you choose.","endpoint_id":"fal-ai/image-editing/style-transfer","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"Van Gogh's Starry Night","description":"The artistic style to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:40.037000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Style Transfer"},{"category":"image-to-image","description":"Remove all text and writing from images while preserving the background and natural appearance.","endpoint_id":"fal-ai/image-editing/text-removal","family":"","inputs":[{"default":null,"description":"URL of the image containing text to be removed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-02T03:19:23.717000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Text Removal"},{"category":"image-to-image","description":"Transform your photos to any time of day, from golden hour to midnight, with appropriate lighting and atmosphere.","endpoint_id":"fal-ai/image-editing/time-of-day","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"golden hour","description":"The time of day to transform the scene to.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:47.668000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Time Of Day"},{"category":"image-to-image","description":"Add realistic weather effects like snowfall, rain, or fog to your photos while maintaining the scene's mood.","endpoint_id":"fal-ai/image-editing/weather-effect","family":"","inputs":[{"default":null,"description":"Image prompt for the omni model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"2","description":"The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The aspect ratio of the generated image.","enum":["21:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"heavy snowfall","description":"The weather effect to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-05-29T20:29:54.982000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Weather Effect"},{"category":"image-to-image","description":"Transform your photos into wojak style while keeping the original characters likeness","endpoint_id":"fal-ai/image-editing/wojak-style","family":"","inputs":[{"default":null,"description":"URL of the image to convert to wojak style.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-26T04:31:05.600000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Image Editing Wojak Style"},{"category":"image-to-image","description":"Generate YouTube thumbnails with custom text","endpoint_id":"fal-ai/image-editing/youtube-thumbnails","family":"","inputs":[{"default":null,"description":"URL of the image to convert to YouTube thumbnail style.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"Number of inference steps for sampling.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":0.5,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"Generate youtube thumbnails","description":"The text to include in the YouTube thumbnail.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-06-30T15:50:34.100000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a1/EMSvi_P8BcQaDhXWOfcu5_EMeLh4d1.png","title":"Image Editing Youtube Thumbnails"},{"category":"image-to-image","description":"Depth Anything v2 preprocessor.","endpoint_id":"fal-ai/image-preprocessors/depth-anything/v2","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"Holistically-Nested Edge Detection (HED) preprocessor.","endpoint_id":"fal-ai/image-preprocessors/hed","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"Whether to use the safe version of the HED detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safe","required":false,"type":"boolean"},{"default":false,"description":"Whether to use the scribble version of the HED detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scribble","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"Line art preprocessor.","endpoint_id":"fal-ai/image-preprocessors/lineart","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"Whether to use the coarse model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"coarse","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"MiDaS depth estimation preprocessor.","endpoint_id":"fal-ai/image-preprocessors/midas","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":6.283185307179586,"description":"A parameter for the MiDaS detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"a","required":false,"type":"number"},{"default":0.1,"description":"Background threshold for the MiDaS detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_threshold","required":false,"type":"number"}],"lab":"","output_kind":"json","output_props":["depth_map","normal_map"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"M-LSD line segment detection preprocessor.","endpoint_id":"fal-ai/image-preprocessors/mlsd","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.1,"description":"Score threshold for the MLSD detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"score_threshold","required":false,"type":"number"},{"default":0.1,"description":"Distance threshold for the MLSD detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"distance_threshold","required":false,"type":"number"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"PIDI (Pidinet) preprocessor.","endpoint_id":"fal-ai/image-preprocessors/pidi","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"Whether to use the safe version of the Pidi detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safe","required":false,"type":"boolean"},{"default":false,"description":"Whether to use the scribble version of the Pidi detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scribble","required":false,"type":"boolean"},{"default":false,"description":"Whether to apply the filter to the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_filter","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"Segment Anything Model (SAM) preprocessor.","endpoint_id":"fal-ai/image-preprocessors/sam","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"Scribble preprocessor.","endpoint_id":"fal-ai/image-preprocessors/scribble","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"HED","description":"The model to use for the Scribble detector","enum":["HED","PiDi"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":false,"description":"Whether to use the safe version of the Scribble detector","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safe","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"TEED (Temporal Edge Enhancement Detection) preprocessor.","endpoint_id":"fal-ai/image-preprocessors/teed","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"ZoeDepth preprocessor.","endpoint_id":"fal-ai/image-preprocessors/zoe","family":"","inputs":[{"default":null,"description":"URL of the image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/image-preprocessors.jpeg","title":"Image Preprocessors"},{"category":"image-to-image","description":"Turn images into pixel-perfect retro art","endpoint_id":"fal-ai/image2pixel","family":"","inputs":[{"default":null,"description":"The image URL to process into improved pixel art","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":32,"description":"Maximum number of colors in the output palette. Set None to disable limit.","enum":null,"is_list":false,"max":256,"media_kind":null,"min":1,"multiline":false,"name":"max_colors","required":false,"type":"integer"},{"default":false,"description":"Enable automatic detection of optimal number of colors.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_color_detect","required":false,"type":"boolean"},{"default":null,"description":"Optional fixed color palette as hex strings (e.g., ['#000000', '#ffffff']).","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fixed_palette","required":false,"type":"string"},{"default":"auto","description":"Scale detection method to use.","enum":["auto","runs","edge"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detect_method","required":false,"type":"enum"},{"default":null,"description":"Force a specific pixel scale. If None, auto-detect.","enum":null,"is_list":false,"max":64,"media_kind":null,"min":1,"multiline":false,"name":"scale","required":false,"type":"integer"},{"default":"dominant","description":"Downscaling method to produce the pixel-art output.","enum":["dominant","median","mode","mean","content-adaptive"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"downscale_method","required":false,"type":"enum"},{"default":false,"description":"Trim borders of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trim_borders","required":false,"type":"boolean"},{"default":false,"description":"Remove background of the image. This will check for contiguous color regions from the edges after correction and make them transparent.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparent_background","required":false,"type":"boolean"},{"default":false,"description":"Apply morphological operations to remove noise.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"cleanup_morph","required":false,"type":"boolean"},{"default":false,"description":"Remove isolated diagonal pixels (jaggy edge cleanup).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"cleanup_jaggy","required":false,"type":"boolean"},{"default":true,"description":"Align output to the pixel grid.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"snap_grid","required":false,"type":"boolean"},{"default":128,"description":"Alpha binarization threshold (0-255).","enum":null,"is_list":false,"max":255,"media_kind":null,"min":0,"multiline":false,"name":"alpha_threshold","required":false,"type":"integer"},{"default":0.05,"description":"Dominant color threshold (0.0-1.0).","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"dominant_color_threshold","required":false,"type":"number"},{"default":0,"description":"Background tolerance (0-255).","enum":null,"is_list":false,"max":255,"media_kind":null,"min":0,"multiline":false,"name":"background_tolerance","required":false,"type":"integer"},{"default":"corners","description":"Controls where to flood-fill from when removing the background.","enum":["edges","corners","midpoints"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_mode","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["palette","images","num_colors","pixel_scale"],"pricing":"","published_at":"2025-10-14T14:01:05.292000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/9MSg8Fm_djrKJ76DtwZrx_0ebf4aa3ab1540298b3fcf4593cfd606.jpg","title":"Image2Pixel"},{"category":"image-to-image","description":"Image2SVG transforms raster images into clean vector graphics, preserving visual quality while enabling scalable, customizable SVG outputs with precise control over detail levels.","endpoint_id":"fal-ai/image2svg","family":"","inputs":[{"default":null,"description":"The image to convert to SVG","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"color","description":"Choose between color or binary (black and white) output","enum":["color","binary"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colormode","required":false,"type":"enum"},{"default":"stacked","description":"Hierarchical mode: stacked or cutout","enum":["stacked","cutout"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hierarchical","required":false,"type":"enum"},{"default":"spline","description":"Mode: spline (curved) or polygon (straight lines)","enum":["spline","polygon"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":4,"description":"Filter out small speckles and noise","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"filter_speckle","required":false,"type":"integer"},{"default":6,"description":"Color quantization level","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"color_precision","required":false,"type":"integer"},{"default":16,"description":"Layer difference threshold for hierarchical mode","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"layer_difference","required":false,"type":"integer"},{"default":60,"description":"Corner detection threshold in degrees","enum":null,"is_list":false,"max":180,"media_kind":null,"min":0,"multiline":false,"name":"corner_threshold","required":false,"type":"integer"},{"default":4,"description":"Length threshold for curves/lines","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"length_threshold","required":false,"type":"number"},{"default":10,"description":"Maximum number of iterations for optimization","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"max_iterations","required":false,"type":"integer"},{"default":45,"description":"Splice threshold for joining paths","enum":null,"is_list":false,"max":90,"media_kind":null,"min":0,"multiline":false,"name":"splice_threshold","required":false,"type":"integer"},{"default":3,"description":"Decimal precision for path coordinates","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"path_precision","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-04-25T16:18:56.329000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training.jpg","title":"Image2svg"},{"category":"image-to-image","description":"Create depth maps using Midas depth estimation.","endpoint_id":"fal-ai/imageutils/depth","family":"","inputs":[{"default":null,"description":"Input image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":6.283185307179586,"description":"a","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"a","required":false,"type":"number"},{"default":0.1,"description":"bg_th","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bg_th","required":false,"type":"number"},{"default":false,"description":"depth_and_normal","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"depth_and_normal","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/depth-estimation.jpeg","title":"Midas Depth Estimation"},{"category":"image-to-image","description":"Create depth maps using Marigold depth estimation.","endpoint_id":"fal-ai/imageutils/marigold-depth","family":"","inputs":[{"default":null,"description":"Input image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":10,"description":"Number of denoising steps. Defaults to `10`. The higher the number, the more accurate the result, but the slower the inference.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":10,"description":"Number of predictions to average over. Defaults to `10`. The higher the number, the more accurate the result, but the slower the inference.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"ensemble_size","required":false,"type":"integer"},{"default":0,"description":"Maximum processing resolution. Defaults `0` which means it uses the size of the input image.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":0,"multiline":false,"name":"processing_res","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2023-12-28T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/marigold.png","title":"Marigold Depth Estimation"},{"category":"vision","description":"Predict the probability of an image being NSFW.","endpoint_id":"fal-ai/imageutils/nsfw","family":"","inputs":[{"default":null,"description":"Input image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"json","output_props":["nsfw_probability"],"pricing":"","published_at":"2024-03-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/nsfw-filter.webp","title":"NSFW Filter"},{"category":"image-to-image","description":"Remove the background from an image.","endpoint_id":"fal-ai/imageutils/rembg","family":"","inputs":[{"default":null,"description":"Input image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the resulting image be cropped to a bounding box around the subject","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_to_bbox","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2023-10-05T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91aa/pdmTi9vgamfQXR6pcroyX_YYkyUfre.png","title":"Remove Background"},{"category":"text-to-speech","description":"Generate natural, clear speeches using Index TTS 2.0 from IndexTeam","endpoint_id":"fal-ai/index-tts-2/text-to-speech","family":"","inputs":[{"default":null,"description":"The audio file to generate the speech from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"The speech prompt to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The emotional reference audio file to extract the style from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"emotional_audio_url","required":false,"type":"string"},{"default":1,"description":"The strength of the emotional style transfer. Higher values result in stronger emotional influence.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The strengths of individual emotions for fine-grained control.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"emotional_strengths","required":false,"type":"json"},{"default":false,"description":"Whether to use the `prompt` to calculate emotional strengths, if enabled it will overwrite the `emotional_strengths` values. If `emotion_prompt` is provided, it will be used to instead of `prompt` to extract the emotional style.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_use_prompt_for_emotion","required":false,"type":"boolean"},{"default":null,"description":"The emotional prompt to influence the emotional style. Must be used together with should_use_prompt_for_emotion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"emotion_prompt","required":false,"type":"string"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost 0.002 per generated audio seconds.","published_at":"2025-10-07T17:21:56.690000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/Y_c2YQvO2F3F-Q3v8cMHr_e14577c0c33b4eca81ce5ebeb2a5ca49.jpg","title":"Index TTS 2.0"},{"category":"video-to-video","description":"Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.","endpoint_id":"fal-ai/infinitalk","family":"","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":145,"description":"Number of frames to generate. Must be between 41 to 721.","enum":null,"is_list":false,"max":721,"media_kind":null,"min":41,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the video to generate. Must be either 480p or 720p.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":42,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":4294967295,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2025-08-21T13:55:42.331000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922e/tNWjozNa-y9xlpdjBp0td_xF75qcO3.png","title":"Infinitalk"},{"category":"text-to-video","description":"Infinitalk model generates a talking avatar video from a text and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.","endpoint_id":"fal-ai/infinitalk/single-text","family":"","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text input to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_input","required":true,"type":"string"},{"default":null,"description":"The voice to use for speech generation","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":145,"description":"Number of frames to generate. Must be between 41 to 721.","enum":null,"is_list":false,"max":721,"media_kind":null,"min":41,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the video to generate. Must be either 480p or 720p.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":42,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":4294967295,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2025-08-22T15:48:52.311000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9396/AGHkC8dUm_lsDNufhenrc_Z0Oiaeje.png","title":"Infinitalk"},{"category":"video-to-video","description":"Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.","endpoint_id":"fal-ai/infinitalk/video-to-video","family":"","inputs":[{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":145,"description":"Number of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":241,"media_kind":null,"min":41,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the video to generate. Must be either 480p or 720p.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":42,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":4294967295,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use for generation.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2025-09-22T20:17:35.243000+00:00","thumbnail":"https://v3.fal.media/files/lion/CKSKBDtMz0kao3Ege3oAj_0b61adf1742146f2b743efc7921003f3.jpg","title":"Infinitalk"},{"category":"text-to-video","description":"InfinityStar’s unified 8B spacetime autoregressive engine to turn any text prompt into crisp 720p videos - 10× faster than diffusion models.","endpoint_id":"fal-ai/infinity-star/text-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for generating the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to guide what to avoid in generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of inference steps","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"Guidance scale for generation","enum":null,"is_list":false,"max":40,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0.4,"description":"Tau value for video scale","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"tau_video","required":false,"type":"number"},{"default":true,"description":"Whether to use APG","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_apg","required":false,"type":"boolean"},{"default":"16:9","description":"Aspect ratio of the generated output","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. Leave empty for random generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to use an LLM to enhance the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost 0.07 $ per video.","published_at":"2025-11-07T18:46:05.330000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/aDnlxPy8aKLxo5Gfa8pQx_5da559726dfb4102b6dd32dab6fd5f04.jpg","title":"Infinity Star"},{"category":"image-to-image","description":"Inpaint images with SD and SDXL","endpoint_id":"fal-ai/inpaint","family":"","inputs":[{"default":null,"description":"URL or HuggingFace ID of the base model to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_name","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Input image for img2img or inpaint mode","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":30,"description":"Increasing the amount of steps tells Stable Diffusion that it should take more steps\n            to generate your final result which can increase the amount of detail in your image.","enum":null,"is_list":false,"max":150,"media_kind":null,"min":0,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2023-11-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/inpaint.jpeg","title":"Inpainting sdxl and sd"},{"category":"image-to-image","description":"InstantCharacter creates high-quality, consistent characters from text prompts, supporting diverse poses, styles, and appearances with strong identity control.","endpoint_id":"fal-ai/instant-character","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The scale of the subject image. Higher values will make the subject image more prominent in the generated image.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["timings","images","has_nsfw_concepts","seed","prompt"],"pricing":"","published_at":"2025-04-18T05:55:46.395000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-3.jpeg","title":"Instant Character"},{"category":"image-to-image","description":"Invisible Watermark is a model that can add an invisible watermark to an image.","endpoint_id":"fal-ai/invisible-watermark","family":"","inputs":[{"default":null,"description":"URL of image to be watermarked or decoded","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"watermark","description":"Text to use as watermark (for encoding only)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"watermark","required":false,"type":"string"},{"default":false,"description":"Whether to decode a watermark from the image instead of encoding","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"decode","required":false,"type":"boolean"},{"default":0,"description":"Length of watermark bits to decode (required when decode=True)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"length","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["length","image","extracted_watermark"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/watermark/watermark.webp","title":"Invisible Watermark"},{"category":"text-to-speech","description":"Text to Speech Endpoint for Inworld's TTS-1.5 Max.","endpoint_id":"fal-ai/inworld-tts","family":"TTS-1.5 Max","inputs":[{"default":null,"description":"The text to synthesize into speech. Maximum 2000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"Craig (en)","description":"The voice to use for synthesis.","enum":["Loretta (en)","Darlene (en)","Marlene (en)","Hank (en)","Evelyn (en)","Celeste (en)","Pippa (en)","Tessa (en)","Liam (en)","Callum (en)","Hamish (en)","Abby (en)","Graham (en)","Rupert (en)","Mortimer (en)","Snik (en)","Anjali (en)","Saanvi (en)","Arjun (en)","Claire (en)","Oliver (en)","Simon (en)","Elliot (en)","James (en)","Serena (en)","Gareth (en)","Vinny (en)","Lauren (en)","Jessica (en)","Ethan (en)","Tyler (en)","Jason (en)","Chloe (en)","Veronica (en)","Victoria (en)","Miranda (en)","Sebastian (en)","Victor (en)","Malcolm (en)","Kayla (en)","Nate (en)","Jake (en)","Brian (en)","Amina (en)","Kelsey (en)","Derek (en)","Grant (en)","Evan (en)","Alex (en)","Ashley (en)","Craig (en)","Deborah (en)","Dennis (en)","Edward (en)","Elizabeth (en)","Hades (en)","Julia (en)","Pixie (en)","Mark (en)","Olivia (en)","Priya (en)","Ronald (en)","Sarah (en)","Shaun (en)","Theodore (en)","Timothy (en)","Wendy (en)","Dominus (en)","Hana (en)","Clive (en)","Carter (en)","Blake (en)","Luna (en)","Yichen (zh)","Xiaoyin (zh)","Xinyi (zh)","Jing (zh)","Erik (nl)","Katrien (nl)","Lennart (nl)","Lore (nl)","Alain (fr)","Hélène (fr)","Mathieu (fr)","Étienne (fr)","Johanna (de)","Josef (de)","Gianni (it)","Orietta (it)","Asuka (ja)","Satoshi (ja)","Hyunwoo (ko)","Minji (ko)","Seojun (ko)","Yoona (ko)","Szymon (pl)","Wojciech (pl)","Heitor (pt)","Maitê (pt)","Diego (es)","Lupita (es)","Miguel (es)","Rafael (es)","Svetlana (ru)","Elena (ru)","Dmitry (ru)","Nikolai (ru)","Riya (hi)","Manoj (hi)","Yael (he)","Oren (he)","Nour (ar)","Omar (ar)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":48000,"description":"The sample rate in Hz for the output audio.","enum":[8000,16000,24000,32000,40000,48000],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sample_rate_hertz","required":false,"type":"enum"}],"lab":"Inworld","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.01 per 1000 character.","published_at":"2026-03-13T17:44:26.042000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9207aa/h8_GEg6YVVRdB1ne848S5_0f9db25aa60c48e692aa3193466d0c7c.jpg","title":"Inworld TTS-1.5 Max"},{"category":"image-to-image","description":"High quality zero-shot personalization","endpoint_id":"fal-ai/ip-adapter-face-id","family":"","inputs":[{"default":"1_5-v1","description":"The model type to use. 1_5 is the default and is recommended for most use cases.","enum":["1_5-v1","1_5-v1-plus","1_5-v2-plus","SDXL-v1","SDXL-v2-plus","1_5-auraface-v1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"An image of a face to match. If an image with a size of 640x640 is not provided, it will be scaled and cropped to that size.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"face_image_url","required":false,"type":"string"},{"default":null,"description":"URL to zip archive with images of faces. The images embedding will be averaged to\n            create a more accurate face id.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"face_images_data_url","required":false,"type":"string"},{"default":"blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"The number of inference steps to use for generating the image. The more steps\n            the better the image will be but it will also take longer to generate.","enum":null,"is_list":false,"max":200,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The number of samples for face id. The more samples the better the image will\n            be but it will also take longer to generate. Default is 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":512,"description":"The width of the generated image.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":512,"multiline":false,"name":"width","required":false,"type":"integer"},{"default":512,"description":"The height of the generated image.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":512,"multiline":false,"name":"height","required":false,"type":"integer"},{"default":640,"description":"The size of the face detection model. The higher the number the more accurate\n            the detection will be but it will also take longer to run. The higher the number the more\n            likely it will fail to find a face as well. Lower it if you are having trouble\n            finding a face in the image.","enum":null,"is_list":false,"max":640,"media_kind":null,"min":64,"multiline":false,"name":"face_id_det_size","required":false,"type":"integer"},{"default":"SG161222/Realistic_Vision_V4.0_noVAE","description":"The URL to the base 1.5 model. Default is SG161222/Realistic_Vision_V4.0_noVAE","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"base_1_5_model_repo","required":false,"type":"string"},{"default":"SG161222/RealVisXL_V3.0","description":"The URL to the base SDXL model. Default is SG161222/RealVisXL_V3.0","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"base_sdxl_model_repo","required":false,"type":"string"}],"lab":"","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2024-04-22T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ip-adapter-face-id.jpeg","title":"IP Adapter Face ID"},{"category":"text-to-image","description":"DeepSeek Janus-Pro is a novel text-to-image model that unifies multimodal understanding and generation through an autoregressive framework","endpoint_id":"fal-ai/janus","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Controls randomness in the generation. Higher values make output more random.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.1,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":5,"description":"Classifier Free Guidance scale - how closely to follow the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"cfg_weight","required":false,"type":"number"},{"default":1,"description":"Number of images to generate in parallel.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","timings","seed","prompt","has_nsfw_concepts"],"pricing":"","published_at":"2025-01-28T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/janus/januspro.webp","title":"DeepSeek Janus-Pro"},{"category":"image-to-image","description":"All-in-one image AI with JoyAI-Image. Understand, create, and edit images through natural language—the model's deep visual understanding powers more accurate generation and precise editing in a unified system.","endpoint_id":"fal-ai/joyai-image-edit","family":"","inputs":[{"default":null,"description":"The edit instruction describing what changes to make to the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"Text describing what should not appear in the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"Number of denoising steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Controls how closely the output follows the edit instruction.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Enable safety checking on input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output image format.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images"],"pricing":"Your requests will cost $0.1 per megapixel.","published_at":"2026-04-06T16:48:57.132000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a953059/bfImJQZtXkls-wBK0KygM_53b12b979f5a4746bbcf0cca92ee1601.jpg","title":"Joyai Image Edit"},{"category":"image-to-video","description":"Kandinsky 5.0 Pro is a diffusion model for fast, high-quality image-to-video generation.","endpoint_id":"fal-ai/kandinsky5-pro/image-to-video","family":"Pro 5","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"512P","description":"Video resolution: 512p or 1024p.","enum":["512P","1024P"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"Video duration.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":28,"description":"Num Inference Steps","enum":null,"is_list":false,"max":40,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for faster generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Kandinsky","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.04 per 512P video second and $0.12 per 1024P video second.","published_at":"2025-12-23T13:42:41.411000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a877601/AN-bEqsfOmQj46SKwy4Ms_5288905eb5e744f99cb3ac61339a2bd9.jpg","title":"Kandinsky5 Pro"},{"category":"text-to-video","description":"Kandinsky 5.0 Pro is a diffusion model for fast, high-quality text-to-video generation.","endpoint_id":"fal-ai/kandinsky5-pro/text-to-video","family":"Pro 5","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"512P","description":"Video resolution: 512p or 1024p.","enum":["512P","1024P"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"3:2","description":"Aspect ratio of the generated video. One of (3:2, 1:1, 2:3).","enum":["3:2","1:1","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5s","description":"The length of the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":28,"description":"The number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for faster generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Kandinsky","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.04 per 512P video second and $0.12 per 1024P video second.","published_at":"2025-12-23T13:40:22.639000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8775f2/Z3ul8R1t-mF0RUH6Z36v9_ae12c69d675b4a1794890ce3cb7b6b49.jpg","title":"Kandinsky5 Pro"},{"category":"text-to-video","description":"Kandinsky 5.0 is a diffusion model for fast, high-quality text-to-video  generation.","endpoint_id":"fal-ai/kandinsky5/text-to-video","family":"Standard 5","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"768x512","description":"Resolution of the generated video in W:H format. Will be calculated based on the aspect ratio(768x512, 512x512, 512x768).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"resolution","required":false,"type":"string"},{"default":"3:2","description":"Aspect ratio of the generated video. One of (3:2, 1:1, 2:3).","enum":["3:2","1:1","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5s","description":"The length of the video to generate (5s or 10s)","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"Kandinsky","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.08 for a 5-second video and $0.16 for a 10-second video, regardless of resolution.","published_at":"2025-10-13T14:43:38.479000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/F-LagExgsZASG2uyIcj6X_093dccc7417c47e593e245767017f251.jpg","title":"Kandinsky5"},{"category":"text-to-video","description":"Kandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation.","endpoint_id":"fal-ai/kandinsky5/text-to-video/distill","family":"Standard 5","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"768x512","description":"Resolution of the generated video in W:H format. Will be calculated based on the aspect ratio(768x512, 512x512, 512x768).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"resolution","required":false,"type":"string"},{"default":"3:2","description":"Aspect ratio of the generated video. One of (3:2, 1:1, 2:3).","enum":["3:2","1:1","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5s","description":"The length of the video to generate (5s or 10s)","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kandinsky","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.05 for a 5-second video and $0.10 for a 10-second video, regardless of resolution.","published_at":"2025-10-13T14:45:27.847000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/TyHaKAdxHRg3VIjUlKZPI_674ee5ee1f2d467e9f3806531f85dee2.jpg","title":"Kandinsky5"},{"category":"image-to-image","description":"Perform precise image edits using strong reference control, transforming subjects, styles, and local details while preserving visual consistency.","endpoint_id":"fal-ai/kling-image/o1","family":"Standard O1 Omni","inputs":[{"default":null,"description":"Text prompt for image generation. Reference images using @Image1, @Image2, etc. (or @Image if only one image). Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"List of reference images. Reference images in prompt using @Image1, @Image2, etc. (1-indexed). Max 10 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include in the image. Reference in prompt as @Element1, @Element2, etc. Maximum 10 total (elements + reference images).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"1K","description":"Image generation resolution. 1K: standard, 2K: high-res.","enum":["1K","2K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9).","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"auto","description":"Aspect ratio of generated images. 'auto' intelligently determines based on input content.","enum":["auto","16:9","9:16","1:1","4:3","3:4","3:2","2:3","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Kling","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-12-01T10:04:03.443000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8495e0/GVuCh0RsGXpLIlUsJMrNX_f4fe5943ad804aaab441629241777417.jpg","title":"Kling O1 Image"},{"category":"image-to-image","description":"Kling Omni 3: Top-tier image-to-image with flawless consistency.","endpoint_id":"fal-ai/kling-image/o3/image-to-image","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for image generation. Reference images using @Image1, @Image2, etc. (or @Image if only one image). Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"List of reference images. Reference images in prompt using @Image1, @Image2, etc. (1-indexed). Max 10 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Optional: Elements (characters/objects) for face control. Reference in prompt as @Element1, @Element2, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"1K","description":"Image generation resolution. 1K: standard, 2K: high-res, 4K: ultra high-res.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"single","description":"Result type. 'single' for one image, 'series' for a series of related images.","enum":["single","series"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"result_type","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9). Only used when result_type is 'single'.","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Number of images in series (2-9). Only used when result_type is 'series'.","enum":null,"is_list":false,"max":9,"media_kind":null,"min":2,"multiline":false,"name":"series_amount","required":false,"type":"integer"},{"default":"auto","description":"Aspect ratio of generated images. 'auto' intelligently determines based on input content.","enum":["16:9","9:16","1:1","4:3","3:4","3:2","2:3","21:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Kling","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.028 per image for 1K/2K, price will be double for 4K","published_at":"2026-02-03T18:26:40.782000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d24a0/FX4gbFjRsBJPDJ2WkPMFa_9f3aa39f5fd84be395b5ce3dee7e4dd1.jpg","title":"Kling Image"},{"category":"text-to-image","description":"Kling Omni 3: Top-tier text-to-image with flawless consistency.","endpoint_id":"fal-ai/kling-image/o3/text-to-image","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for image generation. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional: Elements (characters/objects) for face control. Reference in prompt as @Element1, @Element2, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"1K","description":"Image generation resolution. 1K: standard, 2K: high-res, 4K: ultra high-res.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"single","description":"Result type. 'single' for one image, 'series' for a series of related images.","enum":["single","series"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"result_type","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9). Only used when result_type is 'single'.","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Number of images in series (2-9). Only used when result_type is 'series'.","enum":null,"is_list":false,"max":9,"media_kind":null,"min":2,"multiline":false,"name":"series_amount","required":false,"type":"integer"},{"default":"16:9","description":"Aspect ratio of generated images.","enum":["16:9","9:16","1:1","4:3","3:4","3:2","2:3","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Kling","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.028 per image for 1K/2K, price will be double for 4K","published_at":"2026-02-03T18:13:12.085000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfcbc/DK-poq8omK9dUDtf0KCbr_41eb518e86be4c40ac1864a4a4fba2be.jpg","title":"Kling Image"},{"category":"image-to-image","description":"Kling Image V3: Latest kling image model","endpoint_id":"fal-ai/kling-image/v3/image-to-image","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for image generation. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference image for image-to-image generation.\n\nMax file size: 10.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional: Elements (characters/objects) to include in the image for face control.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"1K","description":"Image generation resolution. 1K: standard, 2K: high-res.","enum":["1K","2K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9).","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"16:9","description":"Aspect ratio of generated images.","enum":["16:9","9:16","1:1","4:3","3:4","3:2","2:3","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Kling","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-02-03T18:30:19.013000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfd13/t6TSkWzl6cFAzvO1PCdDu_f38263f637d245929f03881454951540.jpg","title":"Kling Image"},{"category":"text-to-image","description":"Kling V3: Latest Kling Image model","endpoint_id":"fal-ai/kling-image/v3/text-to-image","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for image generation. Max 2500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative text prompt. It is recommended to supplement negative prompt information through negative sentences directly within positive prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Optional: Elements (characters/objects) to include in the image for face control. Each element can have a frontal image and optionally reference images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"1K","description":"Image generation resolution. 1K: standard, 2K: high-res.","enum":["1K","2K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9).","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"16:9","description":"Aspect ratio of generated images.","enum":["16:9","9:16","1:1","4:3","3:4","3:2","2:3","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Kling","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-02-03T18:31:23.485000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfd08/Ji4e0i6Afbeql3Wr5UTz6_ab60b14661424612bf19059e97e996a5.jpg","title":"Kling Image"},{"category":"image-to-video","description":"Kling AI Avatar v2 Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters","endpoint_id":"fal-ai/kling-video/ai-avatar/v2/pro","family":"Pro Avatar 2","inputs":[{"default":null,"description":"The URL of the image to use as your avatar","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":".","description":"The prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video","duration"],"pricing":"","published_at":"2025-12-04T12:58:48.770000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84f36f/CYuWetfKsuQC0MR6G4EG8_cd62fa685e9844aaaf086c293eddb2ee.jpg","title":"Kling AI Avatar v2 Pro"},{"category":"image-to-video","description":"Kling AI Avatar v2 Standard:  Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters","endpoint_id":"fal-ai/kling-video/ai-avatar/v2/standard","family":"Standard Avatar 2","inputs":[{"default":null,"description":"The URL of the image to use as your avatar","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":".","description":"The prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video","duration"],"pricing":"","published_at":"2025-12-04T12:58:33.998000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84f39a/V_Zy58fLpOlS1jN3balTm_bf4c62c984b34a1597340c007fac8fe8.jpg","title":"Kling AI Avatar v2 Standard"},{"category":"audio-to-audio","description":"Create Voices to be used with Kling Models Voice Control","endpoint_id":"fal-ai/kling-video/create-voice","family":"Audio","inputs":[{"default":null,"description":"URL of the voice audio file. Supports .mp3/.wav audio or .mp4/.mov video. Duration must be 5-30 seconds with clean, single-voice audio.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"voice_url","required":true,"type":"string"}],"lab":"Kling","output_kind":"text","output_props":["voice_id"],"pricing":"","published_at":"2025-12-16T15:32:04.208000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a868c52/jCucNmpNTg7UQ2WYGJHAr_36ad5b9439824f5e9f8fd7f1ed297d27.jpg","title":"Kling Video Create Voice"},{"category":"text-to-video","description":"Kling LipSync is an audio-to-video model that generates realistic lip movements from audio input.","endpoint_id":"fal-ai/kling-video/lipsync/audio-to-video","family":"Lipsync","inputs":[{"default":null,"description":"The URL of the video to generate the lip sync for. Supports .mp4/.mov, ≤100MB, 2–10s, 720p/1080p only, width/height 720–1920px.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the lip sync for. Minimum duration is 2s and maximum duration is 60s. Maximum file size is 5MB.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"Your request will be priced $0.014 per input video seconds, rolling up to closest 5 second increment. For example, if your video's duration is 3 seconds, it will be billed as a 5 second video","published_at":"2025-03-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/njNipNC0TkA9fJguiS1NB_c75b090e2ebb4d9581d21d66cfc4a0d3.jpg","title":"Kling LipSync Audio-to-Video"},{"category":"text-to-video","description":"Kling LipSync is a text-to-video model that generates realistic lip movements from text input.","endpoint_id":"fal-ai/kling-video/lipsync/text-to-video","family":"Lipsync","inputs":[{"default":null,"description":"The URL of the video to generate the lip sync for. Supports .mp4/.mov, ≤100MB, 2-60s, 720p/1080p only, width/height 720–1920px. If validation fails, an error is returned.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Text content for lip-sync video generation. Max 120 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Voice ID to use for speech synthesis","enum":["genshin_vindi2","zhinen_xuesheng","AOT","ai_shatang","genshin_klee2","genshin_kirara","ai_kaiya","oversea_male1","ai_chenjiahao_712","girlfriend_4_speech02","chat1_female_new-3","chat_0407_5-1","cartoon-boy-07","uk_boy1","cartoon-girl-01","PeppaPig_platform","ai_huangzhong_712","ai_huangyaoshi_712","ai_laoguowang_712","chengshu_jiejie","you_pingjing","calm_story1","uk_man2","laopopo_speech02","heainainai_speech02","reader_en_m-v1","commercial_lady_en_f-v1","tiyuxi_xuedi","tiexin_nanyou","girlfriend_1_speech02","girlfriend_2_speech02","zhuxi_speech02","uk_oldman3","dongbeilaotie_speech02","chongqingxiaohuo_speech02","chuanmeizi_speech02","chaoshandashu_speech02","ai_taiwan_man2_speech02","xianzhanggui_speech02","tianjinjiejie_speech02","diyinnansang_DB_CN_M_04-v2","yizhipiannan-v1","guanxiaofang-v2","tianmeixuemei-v1","daopianyansang-v1","mengwa-v1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_id","required":true,"type":"enum"},{"default":"en","description":"The voice language corresponding to the Voice ID","enum":["zh","en"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_language","required":false,"type":"enum"},{"default":1,"description":"Speech rate for Text to Video generation","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.8,"multiline":false,"name":"voice_speed","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"Your request will be priced $0.014 per input video seconds, rolling up to closest 5 second increment. For example, if your video's duration is 3 seconds, it will be billed as a 5 second video","published_at":"2025-03-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92e2/Xxa6mNP6nf210FA10wNqJ_e8YUdiKZ.png","title":"Kling LipSync Text-to-Video"},{"category":"image-to-video","description":"Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.","endpoint_id":"fal-ai/kling-video/o1/image-to-video","family":"Pro O1 Omni","inputs":[{"default":null,"description":"Use @Image1 to reference the start frame, @Image2 to reference the end frame.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image to use as the first frame of the video.\n\nMax file size: 10.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"Image to use as the last frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds.","enum":["3","4","5","6","7","8","9","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-01T11:39:20.265000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/fPJwa1EtpB5bYyqS2u7us_ddd5fec670b149288123785cd5ee6e54.jpg","title":"Kling O1 First Frame Last Frame to Video [Pro]"},{"category":"image-to-video","description":"Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.","endpoint_id":"fal-ai/kling-video/o1/reference-to-video","family":"Pro O1 Omni","inputs":[{"default":null,"description":"Take @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Additional reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images + start image).","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include in the video. Reference in prompt as @Element1, @Element2, etc. Maximum 7 total (elements + reference images + start image).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"5","description":"Video duration in seconds.","enum":["3","4","5","6","7","8","9","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-01T11:37:01.777000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/L7EgH8_I_ZIngBtpKaL-Y_ca0bcf7b2c8f4319b8af7dc386bdb3d9.jpg","title":"Kling O1 Reference Image to Video [Pro]"},{"category":"image-to-video","description":"Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.","endpoint_id":"fal-ai/kling-video/o1/standard/image-to-video","family":"Standard O1 Omni","inputs":[{"default":null,"description":"Use @Image1 to reference the start frame, @Image2 to reference the end frame.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image to use as the first frame of the video.\n\nMax file size: 10.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"Image to use as the last frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds.","enum":["3","4","5","6","7","8","9","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-15T09:37:41.280000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86000e/kN3PH-dHrMpnHW9OlNlTQ_813cef4c332f4a6c9120e6890b013b91.jpg","title":"Kling O1 First Frame Last Frame to Video [Standard]"},{"category":"image-to-video","description":"Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.","endpoint_id":"fal-ai/kling-video/o1/standard/reference-to-video","family":"Standard O1 Omni","inputs":[{"default":null,"description":"Take @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Additional reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images + start image).","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include in the video. Reference in prompt as @Element1, @Element2, etc. Maximum 7 total (elements + reference images + start image).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"5","description":"Video duration in seconds.","enum":["3","4","5","6","7","8","9","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-15T09:39:25.599000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a860024/IeH4LL0fTNCVBiDW7YTyc_48485917433c4e6ebe9a042112c8147f.jpg","title":"Kling O1 Reference Image to Video [Standard]"},{"category":"video-to-video","description":"Edit an existing video using natural-language instructions, transforming subjects, settings, and style while retaining the original motion structure.","endpoint_id":"fal-ai/kling-video/o1/standard/video-to-video/edit","family":"Standard O1 Omni","inputs":[{"default":null,"description":"Use @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats supported, 3-10 seconds duration, 720-2160px resolution, max 200MB.\n\nMax file size: 200.0MB, Min width: 720px, Min height: 720px, Max width: 2160px, Max height: 2160px, Min duration: 3.0s, Max duration: 10.05s, Min FPS: 24.0, Max FPS: 60.0, Timeout: 30.0s","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"Whether to keep the original audio from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-15T09:34:39.306000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a866155/Hj1G7kFqvg9zFnWunTT3V_6ac8815e9a52404f82016084def66f34.jpg","title":"Kling O1 Edit Video [Standard]"},{"category":"video-to-video","description":"Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.","endpoint_id":"fal-ai/kling-video/o1/standard/video-to-video/reference","family":"Standard O1 Omni","inputs":[{"default":null,"description":"Use @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats supported, 3-10 seconds duration, 720-2160px resolution, max 200MB.\n\nMax file size: 200.0MB, Min width: 720px, Min height: 720px, Max width: 2160px, Max height: 2160px, Min duration: 3.0s, Max duration: 10.05s, Min FPS: 24.0, Max FPS: 60.0, Timeout: 30.0s","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"Whether to keep the original audio from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"auto","description":"The aspect ratio of the generated video frame. If 'auto', the aspect ratio will be determined automatically based on the input video, and the closest aspect ratio to the input video will be used.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5","description":"Video duration in seconds.","enum":["3","4","5","6","7","8","9","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-15T09:36:27.690000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86615a/KJdMDK3gyg1EI_R6Hw1S2_d70d13f9a3e74c18b228654ea81a7077.jpg","title":"Kling O1 Reference Video to Video [Standard]"},{"category":"video-to-video","description":"Edit an existing video using natural-language instructions, transforming subjects, settings, and style while retaining the original motion structure.","endpoint_id":"fal-ai/kling-video/o1/video-to-video/edit","family":"Pro O1 Omni","inputs":[{"default":null,"description":"Use @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats supported, 3-10 seconds duration, 720-2160px resolution, max 200MB.\n\nMax file size: 200.0MB, Min width: 720px, Min height: 720px, Max width: 2160px, Max height: 2160px, Min duration: 3.0s, Max duration: 10.05s, Min FPS: 24.0, Max FPS: 60.0, Timeout: 30.0s","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"Whether to keep the original audio from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-01T11:29:19.531000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/KSlUBiWApJEK5TS53lmB1_a9ac938f625f4d5789681706620b9868.jpg","title":"Kling O1 Edit Video [Pro]"},{"category":"video-to-video","description":"Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.","endpoint_id":"fal-ai/kling-video/o1/video-to-video/reference","family":"Pro O1 Omni","inputs":[{"default":null,"description":"Use @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats supported, 3-10 seconds duration, 720-2160px resolution, max 200MB.\n\nMax file size: 200.0MB, Min width: 720px, Min height: 720px, Max width: 2160px, Max height: 2160px, Min duration: 3.0s, Max duration: 10.05s, Min FPS: 24.0, Max FPS: 60.0, Timeout: 30.0s","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"Whether to keep the original audio from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"auto","description":"The aspect ratio of the generated video frame. If 'auto', the aspect ratio will be determined automatically based on the input video, and the closest aspect ratio to the input video will be used.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5","description":"Video duration in seconds.","enum":["3","4","5","6","7","8","9","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-01T11:25:09.487000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/W2rN6g_nAeMqlL1W3IdOA_3cf3388f038944deabb311d5ccd584ba.jpg","title":"Kling O1 Reference Video to Video [Pro]"},{"category":"image-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","endpoint_id":"fal-ai/kling-video/o3/4k/image-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the start frame image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the end frame image (optional).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.42 regardless of whether audio is on or off. For example, a 5s video will cost $2.10.","published_at":"2026-04-23T14:59:13.919000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9740be/nUTPtoiXouNNHisPlCKB6_4c0365b62d0c413dbd5c12152b7d1fc5.jpg","title":"Kling Video"},{"category":"image-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","endpoint_id":"fal-ai/kling-video/o3/4k/reference-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"Image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":false,"type":"string"},{"default":null,"description":"Image to use as the last frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images) is allowed.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.42 regardless of whether audio is on or off. For example, a 5s video will cost $2.10.","published_at":"2026-04-23T14:59:16.350000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9740db/W8nvw836T_PoFZvZSKaHF_24c88000032c446ab22f4824a9b09a66.jpg","title":"Kling Video"},{"category":"text-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","endpoint_id":"fal-ai/kling-video/o3/4k/text-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Required unless multi_prompt is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.42 regardless of whether audio is on or off. For example, a 5s video will cost $2.10.","published_at":"2026-04-23T14:59:12.100000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9740a0/uJcikAkIJZE8L06x0HY5R_78d7451cfa254ef7bbd247305bc1b84c.jpg","title":"Kling Video"},{"category":"image-to-video","description":"Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.","endpoint_id":"fal-ai/kling-video/o3/pro/image-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the start frame image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the end frame image (optional).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.112 (audio off) or $0.14 (audio on). For example, a 5s video with audio on will cost $0.70","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfcae/X9YwYvvnjSHOx_K4G8s69_395daf17841f4097a7cff719154bfad4.jpg","title":"Kling O3 Image to Video [Pro]"},{"category":"image-to-video","description":"Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.","endpoint_id":"fal-ai/kling-video/o3/pro/reference-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"Image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":false,"type":"string"},{"default":null,"description":"Image to use as the last frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.112 (audio off) or $0.14 (audio on). For example, a 5s video with audio on will cost $0.70","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfcbc/DK-poq8omK9dUDtf0KCbr_41eb518e86be4c40ac1864a4a4fba2be.jpg","title":"Kling O3 Reference to Video [Pro]"},{"category":"text-to-video","description":"Generate realistic videos using Kling O3 from Kling Team!","endpoint_id":"fal-ai/kling-video/o3/pro/text-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Required unless multi_prompt is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.112 (audio off) or $0.14 (audio on). For example, a 5s video with audio on will cost $0.70","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c3ad2/Z4ZRnSwVTn1ZsiXuSVpE-_ee73b123ab38450684f4902430914242.jpg","title":"Kling O3 Text to Video [Pro]"},{"category":"video-to-video","description":"Edit videos using Kling O3 from Kling Team!","endpoint_id":"fal-ai/kling-video/o3/pro/video-to-video/edit","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Reference video as @Video1.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats, 3-15s duration, 720-3840px resolution, max 200MB.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":true,"description":"Whether to keep the original audio from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated you will be charged $0.168  For example, a 5s video will cost $0.84.","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfcd0/jgn9feXep4nJXWf0tg1cf_6867c6921b6a4015a1906c8e02a7ef9d.jpg","title":"Kling O3 Edit Video [Pro]"},{"category":"video-to-video","description":"Kling O3 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.","endpoint_id":"fal-ai/kling-video/o3/pro/video-to-video/reference","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Reference video as @Video1.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats, 3-15s duration, 720-3840px resolution, max 200MB.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":true,"description":"Whether to keep the original audio from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"string"},{"default":"auto","description":"Aspect ratio.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Video duration in seconds (3-15s for reference video).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated you will be charged $0.168  For example, a 5s video will cost $0.84.","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfcc6/nZEmuKTIwd_QfJiUrK_Sj_54b1357c30cf425ba1811908f7085dfc.jpg","title":"Kling O3 Reference Video to Video [Pro]"},{"category":"image-to-video","description":"Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.","endpoint_id":"fal-ai/kling-video/o3/standard/image-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the start frame image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the end frame image (optional).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.084 (audio off) or $0.112 (audio on). For example, a 5s video with audio on will cost $0.56.","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d2007/gV_LMXNrguqRaDB9sLqir_b5d36b36de5a40bdb5cb2cd3f8af29d7.jpg","title":"Kling O3 Image to Video [Pro]"},{"category":"image-to-video","description":"Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.","endpoint_id":"fal-ai/kling-video/o3/standard/reference-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"Image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":false,"type":"string"},{"default":null,"description":"Image to use as the last frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.084 (audio off) or $0.112 (audio on). For example, a 5s video with audio on will cost $0.56.","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d1fe9/PkQKfXd6hVfEW3ckzhBep_2bab784ff390459d971d45c8da8f6a8c.jpg","title":"Kling O3 Reference to Video [Standard]"},{"category":"text-to-video","description":"Generate realistic videos using Kling O3 from Kling Team!","endpoint_id":"fal-ai/kling-video/o3/standard/text-to-video","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Required unless multi_prompt is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"5","description":"Video duration in seconds (3-15s).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether to generate native audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"List of prompts for multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.084 (audio off) or $0.112 (audio on). For example, a 5s video with audio on will cost $0.56","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfce0/-uK5wEuvOst_sCRKg3PqO_0e1bf50a5a624877b395523e43c3fcc0.jpg","title":"Kling O3 Text to Video [Standard]"},{"category":"video-to-video","description":"Edit videos using Kling O3 from Kling Team!","endpoint_id":"fal-ai/kling-video/o3/standard/video-to-video/edit","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Reference video as @Video1.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats, 3-15s duration, 720-3840px resolution, max 200MB.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":true,"description":"Whether to keep the original audio from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.126. For example, a 5s video with will cost $0.63","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d1ffc/H9d8t0iQBUbd25VuiN81d_c6fd32a039bc4078b02b14a65a7b1b13.jpg","title":"Kling O3 Edit Video [Standard]"},{"category":"video-to-video","description":"Kling O3 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.","endpoint_id":"fal-ai/kling-video/o3/standard/video-to-video/reference","family":"Kling O3","inputs":[{"default":null,"description":"Text prompt for video generation. Reference video as @Video1.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference video URL. Only .mp4/.mov formats, 3-15s duration, 720-3840px resolution, max 200MB.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":true,"description":"Whether to keep the original audio from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_audio","required":false,"type":"boolean"},{"default":null,"description":"Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"string"},{"default":"auto","description":"Aspect ratio.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Video duration in seconds (3-15s for reference video).","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.126. For example, a 5s video will cost $0.63.","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d1ff4/ctJ5X4rUretNOyhNP7kef_c20445da1a384304ade796a9301891bf.jpg","title":"Kling O3 Reference Video to Video [Standard]"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.5 (pro)","endpoint_id":"fal-ai/kling-video/v1.5/pro/effects","family":"Pro 1.5","inputs":[{"default":null,"description":"URL of images to be used for hug, kiss or heart_gesture video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":null,"description":"The effect scene to use for the video generation","enum":["hug","kiss","heart_gesture","squish","expansion","fuzzyfuzzy","bloombloom","dizzydizzy","jelly_press","jelly_slice","jelly_squish","jelly_jiggle","pixelpixel","yearbook","instant_film","anime_figure","rocketrocket","fly_fly","disappear","lightning_power","bullet_time","bullet_time_360","media_interview","day_to_night","let's_ride","jumpdrop","swish_swish","running_man","jazz_jazz","swing_swing","skateskate","building_sweater","pure_white_wings","black_wings","golden_wing","pink_pink_wings","rampage_ape","a_list_look","countdown_teleport","firework_2026","instant_christmas","birthday_star","firework","celebration","tiger_hug_pro","pet_lion_pro","guardian_spirit","squeeze_scream","inner_voice","memory_alive","guess_what","eagle_snatch","hug_from_past","instant_kid","dollar_rain","cry_cry","building_collapse","mushroom","jesus_hug","shark_alert","lie_flat","polar_bear_hug","brown_bear_hug","office_escape_plow","watermelon_bomb","boss_coming","wig_out","car_explosion","tiger_hug","siblings","construction_worker","snatched","felt_felt","plushcut","drunk_dance","drunk_dance_pet","daoma_dance","bouncy_dance","smooth_sailing_dance","new_year_greeting","lion_dance","prosperity","great_success","golden_horse_fortune","red_packet_box","lucky_horse_year","lucky_red_packet","lucky_money_come","lion_dance_pet","dumpling_making_pet","fish_making_pet","pet_red_packet","lantern_glow","expression_challenge","overdrive","heart_gesture_dance","poping","martial_arts","running","nezha","motorcycle_dance","subject_3_dance","ghost_step_dance","phantom_jewel","zoom_out","cheers_2026","kiss_pro","fight_pro","hug_pro","heart_gesture_pro","dollar_rain_pro","pet_bee_pro","santa_random_surprise","magic_match_tree","happy_birthday","thumbs_up_pro","surprise_bouquet","bouquet_drop","3d_cartoon_1_pro","glamour_photo_shoot","box_of_joy","first_toast_of_the_year","my_santa_pic","santa_gift","steampunk_christmas","snowglobe","christmas_photo_shoot","ornament_crash","santa_express","particle_santa_surround","coronation_of_frost","spark_in_the_snow","scarlet_and_snow","cozy_toon_wrap","bullet_time_lite","magic_cloak","balloon_parade","jumping_ginger_joy","c4d_cartoon_pro","venomous_spider","throne_of_king","luminous_elf","woodland_elf","japanese_anime_1","american_comics","snowboarding","witch_transform","vampire_transform","pumpkin_head_transform","demon_transform","mummy_transform","zombie_transform","cute_pumpkin_transform","cute_ghost_transform","knock_knock_halloween","halloween_escape","baseball","korean_baseball","trampoline","trampoline_night","pucker_up","feed_mooncake","flyer","dishwasher","pet_chinese_opera","magic_fireball","gallery_ring","pet_moto_rider","muscle_pet","pet_delivery","mythic_style","steampunk","3d_cartoon_2","pet_chef","santa_gifts","santa_hug","girlfriend","boyfriend","heart_gesture_1","pet_wizard","smoke_smoke","gun_shot","double_gun","pet_warrior","long_hair","pet_dance","wool_curly","pet_bee","marry_me","piggy_morph","ski_ski","magic_broom","splashsplash","surfsurf","fairy_wing","angel_wing","dark_wing","emoji"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect_scene","required":true,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-06T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9399/sEgsBCvuBnVOAWlS6W59j_2Zfw94le.png","title":"Kling 1.5"},{"category":"image-to-video","description":"Generate video clips from your images using Kling 1.5 (pro)","endpoint_id":"fal-ai/kling-video/v1.5/pro/image-to-video","family":"Pro 1.5","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"tail_image_url","required":false,"type":"string"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":null,"description":"URL of the image for Static Brush Application Area (Mask image created by users using the motion brush)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"static_mask_url","required":false,"type":"string"},{"default":null,"description":"List of dynamic masks","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dynamic_masks","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-10-04T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922c/kF8kD9o8szfQp_My2ee-H_bg6Yukvk.png","title":"Kling 1.5"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.5 (pro)","endpoint_id":"fal-ai/kling-video/v1.5/pro/text-to-video","family":"Pro 1.5","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-11-25T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d6/663MNKQ9o49-5ojFBsOUf_GD3XfyPP.png","title":"Kling 1.5"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.6 (pro)","endpoint_id":"fal-ai/kling-video/v1.6/pro/effects","family":"Pro 1.6","inputs":[{"default":null,"description":"URL of images to be used for hug, kiss or heart_gesture video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":null,"description":"The effect scene to use for the video generation","enum":["hug","kiss","heart_gesture","squish","expansion","fuzzyfuzzy","bloombloom","dizzydizzy","jelly_press","jelly_slice","jelly_squish","jelly_jiggle","pixelpixel","yearbook","instant_film","anime_figure","rocketrocket","fly_fly","disappear","lightning_power","bullet_time","bullet_time_360","media_interview","day_to_night","let's_ride","jumpdrop","swish_swish","running_man","jazz_jazz","swing_swing","skateskate","building_sweater","pure_white_wings","black_wings","golden_wing","pink_pink_wings","rampage_ape","a_list_look","countdown_teleport","firework_2026","instant_christmas","birthday_star","firework","celebration","tiger_hug_pro","pet_lion_pro","guardian_spirit","squeeze_scream","inner_voice","memory_alive","guess_what","eagle_snatch","hug_from_past","instant_kid","dollar_rain","cry_cry","building_collapse","mushroom","jesus_hug","shark_alert","lie_flat","polar_bear_hug","brown_bear_hug","office_escape_plow","watermelon_bomb","boss_coming","wig_out","car_explosion","tiger_hug","siblings","construction_worker","snatched","felt_felt","plushcut","drunk_dance","drunk_dance_pet","daoma_dance","bouncy_dance","smooth_sailing_dance","new_year_greeting","lion_dance","prosperity","great_success","golden_horse_fortune","red_packet_box","lucky_horse_year","lucky_red_packet","lucky_money_come","lion_dance_pet","dumpling_making_pet","fish_making_pet","pet_red_packet","lantern_glow","expression_challenge","overdrive","heart_gesture_dance","poping","martial_arts","running","nezha","motorcycle_dance","subject_3_dance","ghost_step_dance","phantom_jewel","zoom_out","cheers_2026","kiss_pro","fight_pro","hug_pro","heart_gesture_pro","dollar_rain_pro","pet_bee_pro","santa_random_surprise","magic_match_tree","happy_birthday","thumbs_up_pro","surprise_bouquet","bouquet_drop","3d_cartoon_1_pro","glamour_photo_shoot","box_of_joy","first_toast_of_the_year","my_santa_pic","santa_gift","steampunk_christmas","snowglobe","christmas_photo_shoot","ornament_crash","santa_express","particle_santa_surround","coronation_of_frost","spark_in_the_snow","scarlet_and_snow","cozy_toon_wrap","bullet_time_lite","magic_cloak","balloon_parade","jumping_ginger_joy","c4d_cartoon_pro","venomous_spider","throne_of_king","luminous_elf","woodland_elf","japanese_anime_1","american_comics","snowboarding","witch_transform","vampire_transform","pumpkin_head_transform","demon_transform","mummy_transform","zombie_transform","cute_pumpkin_transform","cute_ghost_transform","knock_knock_halloween","halloween_escape","baseball","korean_baseball","trampoline","trampoline_night","pucker_up","feed_mooncake","flyer","dishwasher","pet_chinese_opera","magic_fireball","gallery_ring","pet_moto_rider","muscle_pet","pet_delivery","mythic_style","steampunk","3d_cartoon_2","pet_chef","santa_gifts","santa_hug","girlfriend","boyfriend","heart_gesture_1","pet_wizard","smoke_smoke","gun_shot","double_gun","pet_warrior","long_hair","pet_dance","wool_curly","pet_bee","marry_me","piggy_morph","ski_ski","magic_broom","splashsplash","surfsurf","fairy_wing","angel_wing","dark_wing","emoji"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect_scene","required":true,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-06T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d3/mVFKfkp_tpskWA8TMobUu_I1nGUw87.png","title":"Kling 1.6"},{"category":"image-to-video","description":"Generate video clips from your multiple image references using Kling 1.6 (pro)","endpoint_id":"fal-ai/kling-video/v1.6/pro/elements","family":"Pro 1.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"List of image URLs to use for video generation. Supports up to 4 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-05-20T14:31:12.908000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kling-1-6-image-to-video.webp","title":"Kling 1.6 Elements"},{"category":"image-to-video","description":"Generate video clips from your images using Kling 1.6 (pro)","endpoint_id":"fal-ai/kling-video/v1.6/pro/image-to-video","family":"Pro 1.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"tail_image_url","required":false,"type":"string"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-01-07T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kling-1-6-image-to-video.webp","title":"Kling 1.6"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.6 (pro)","endpoint_id":"fal-ai/kling-video/v1.6/pro/text-to-video","family":"Pro 1.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-02-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b6/nA7fI1yIGllusi5Qk_2-K_zbj3Tfnu.png","title":"Kling 1.6"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.6 (std)","endpoint_id":"fal-ai/kling-video/v1.6/standard/effects","family":"Standard 1.6","inputs":[{"default":null,"description":"URL of images to be used for hug, kiss or heart_gesture video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":null,"description":"The effect scene to use for the video generation","enum":["hug","kiss","heart_gesture","squish","expansion","fuzzyfuzzy","bloombloom","dizzydizzy","jelly_press","jelly_slice","jelly_squish","jelly_jiggle","pixelpixel","yearbook","instant_film","anime_figure","rocketrocket","fly_fly","disappear","lightning_power","bullet_time","bullet_time_360","media_interview","day_to_night","let's_ride","jumpdrop","swish_swish","running_man","jazz_jazz","swing_swing","skateskate","building_sweater","pure_white_wings","black_wings","golden_wing","pink_pink_wings","rampage_ape","a_list_look","countdown_teleport","firework_2026","instant_christmas","birthday_star","firework","celebration","tiger_hug_pro","pet_lion_pro","guardian_spirit","squeeze_scream","inner_voice","memory_alive","guess_what","eagle_snatch","hug_from_past","instant_kid","dollar_rain","cry_cry","building_collapse","mushroom","jesus_hug","shark_alert","lie_flat","polar_bear_hug","brown_bear_hug","office_escape_plow","watermelon_bomb","boss_coming","wig_out","car_explosion","tiger_hug","siblings","construction_worker","snatched","felt_felt","plushcut","drunk_dance","drunk_dance_pet","daoma_dance","bouncy_dance","smooth_sailing_dance","new_year_greeting","lion_dance","prosperity","great_success","golden_horse_fortune","red_packet_box","lucky_horse_year","lucky_red_packet","lucky_money_come","lion_dance_pet","dumpling_making_pet","fish_making_pet","pet_red_packet","lantern_glow","expression_challenge","overdrive","heart_gesture_dance","poping","martial_arts","running","nezha","motorcycle_dance","subject_3_dance","ghost_step_dance","phantom_jewel","zoom_out","cheers_2026","kiss_pro","fight_pro","hug_pro","heart_gesture_pro","dollar_rain_pro","pet_bee_pro","santa_random_surprise","magic_match_tree","happy_birthday","thumbs_up_pro","surprise_bouquet","bouquet_drop","3d_cartoon_1_pro","glamour_photo_shoot","box_of_joy","first_toast_of_the_year","my_santa_pic","santa_gift","steampunk_christmas","snowglobe","christmas_photo_shoot","ornament_crash","santa_express","particle_santa_surround","coronation_of_frost","spark_in_the_snow","scarlet_and_snow","cozy_toon_wrap","bullet_time_lite","magic_cloak","balloon_parade","jumping_ginger_joy","c4d_cartoon_pro","venomous_spider","throne_of_king","luminous_elf","woodland_elf","japanese_anime_1","american_comics","snowboarding","witch_transform","vampire_transform","pumpkin_head_transform","demon_transform","mummy_transform","zombie_transform","cute_pumpkin_transform","cute_ghost_transform","knock_knock_halloween","halloween_escape","baseball","korean_baseball","trampoline","trampoline_night","pucker_up","feed_mooncake","flyer","dishwasher","pet_chinese_opera","magic_fireball","gallery_ring","pet_moto_rider","muscle_pet","pet_delivery","mythic_style","steampunk","3d_cartoon_2","pet_chef","santa_gifts","santa_hug","girlfriend","boyfriend","heart_gesture_1","pet_wizard","smoke_smoke","gun_shot","double_gun","pet_warrior","long_hair","pet_dance","wool_curly","pet_bee","marry_me","piggy_morph","ski_ski","magic_broom","splashsplash","surfsurf","fairy_wing","angel_wing","dark_wing","emoji"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect_scene","required":true,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-06T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d5/yDlKh1ALP5JpLxc3GNe_T_VNGQo4Bj.png","title":"Kling 1.6"},{"category":"image-to-video","description":"Generate video clips from your multiple image references using Kling 1.6 (standard)","endpoint_id":"fal-ai/kling-video/v1.6/standard/elements","family":"Standard 1.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"List of image URLs to use for video generation. Supports up to 4 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-05-20T14:33:48.560000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kling-1-6-image-to-video.webp","title":"Kling 1.6 Elements"},{"category":"image-to-video","description":"Generate video clips from your images using Kling 1.6 (std)","endpoint_id":"fal-ai/kling-video/v1.6/standard/image-to-video","family":"Standard 1.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-01-07T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ac/TE1jDriwZqy03ekC_hvcA_0KFRPl9z.png","title":"Kling 1.6"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.6 (std)","endpoint_id":"fal-ai/kling-video/v1.6/standard/text-to-video","family":"Standard 1.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-01-07T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a49/zA1f-FF6UCKdZwaTCuXEc_CKdX9mN4.png","title":"Kling 1.6"},{"category":"image-to-video","description":"Kling AI Avatar Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters","endpoint_id":"fal-ai/kling-video/v1/pro/ai-avatar","family":"Pro 1","inputs":[{"default":null,"description":"The URL of the image to use as your avatar","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":".","description":"The prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video","duration"],"pricing":"","published_at":"2025-09-13T07:23:01.405000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9229/3XhAorXk_J0ZalO2fpf6c_GVGG0NLz.png","title":"Kling AI Avatar Pro"},{"category":"image-to-video","description":"Kling AI Avatar Standard:  Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters","endpoint_id":"fal-ai/kling-video/v1/standard/ai-avatar","family":"Standard 1","inputs":[{"default":null,"description":"The URL of the image to use as your avatar","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":".","description":"The prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video","duration"],"pricing":"","published_at":"2025-09-13T07:34:07.280000+00:00","thumbnail":"https://v3.fal.media/files/rabbit/me_wmKnQJJevTKvSLGMF7_2948b05301c24578b9d28acb927f9c5c.jpg","title":"Kling AI Avatar"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.0","endpoint_id":"fal-ai/kling-video/v1/standard/effects","family":"Standard 1","inputs":[{"default":null,"description":"URL of images to be used for hug, kiss or heart_gesture video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":null,"description":"The effect scene to use for the video generation","enum":["hug","kiss","heart_gesture","squish","expansion","fuzzyfuzzy","bloombloom","dizzydizzy","jelly_press","jelly_slice","jelly_squish","jelly_jiggle","pixelpixel","yearbook","instant_film","anime_figure","rocketrocket","fly_fly","disappear","lightning_power","bullet_time","bullet_time_360","media_interview","day_to_night","let's_ride","jumpdrop","swish_swish","running_man","jazz_jazz","swing_swing","skateskate","building_sweater","pure_white_wings","black_wings","golden_wing","pink_pink_wings","rampage_ape","a_list_look","countdown_teleport","firework_2026","instant_christmas","birthday_star","firework","celebration","tiger_hug_pro","pet_lion_pro","guardian_spirit","squeeze_scream","inner_voice","memory_alive","guess_what","eagle_snatch","hug_from_past","instant_kid","dollar_rain","cry_cry","building_collapse","mushroom","jesus_hug","shark_alert","lie_flat","polar_bear_hug","brown_bear_hug","office_escape_plow","watermelon_bomb","boss_coming","wig_out","car_explosion","tiger_hug","siblings","construction_worker","snatched","felt_felt","plushcut","drunk_dance","drunk_dance_pet","daoma_dance","bouncy_dance","smooth_sailing_dance","new_year_greeting","lion_dance","prosperity","great_success","golden_horse_fortune","red_packet_box","lucky_horse_year","lucky_red_packet","lucky_money_come","lion_dance_pet","dumpling_making_pet","fish_making_pet","pet_red_packet","lantern_glow","expression_challenge","overdrive","heart_gesture_dance","poping","martial_arts","running","nezha","motorcycle_dance","subject_3_dance","ghost_step_dance","phantom_jewel","zoom_out","cheers_2026","kiss_pro","fight_pro","hug_pro","heart_gesture_pro","dollar_rain_pro","pet_bee_pro","santa_random_surprise","magic_match_tree","happy_birthday","thumbs_up_pro","surprise_bouquet","bouquet_drop","3d_cartoon_1_pro","glamour_photo_shoot","box_of_joy","first_toast_of_the_year","my_santa_pic","santa_gift","steampunk_christmas","snowglobe","christmas_photo_shoot","ornament_crash","santa_express","particle_santa_surround","coronation_of_frost","spark_in_the_snow","scarlet_and_snow","cozy_toon_wrap","bullet_time_lite","magic_cloak","balloon_parade","jumping_ginger_joy","c4d_cartoon_pro","venomous_spider","throne_of_king","luminous_elf","woodland_elf","japanese_anime_1","american_comics","snowboarding","witch_transform","vampire_transform","pumpkin_head_transform","demon_transform","mummy_transform","zombie_transform","cute_pumpkin_transform","cute_ghost_transform","knock_knock_halloween","halloween_escape","baseball","korean_baseball","trampoline","trampoline_night","pucker_up","feed_mooncake","flyer","dishwasher","pet_chinese_opera","magic_fireball","gallery_ring","pet_moto_rider","muscle_pet","pet_delivery","mythic_style","steampunk","3d_cartoon_2","pet_chef","santa_gifts","santa_hug","girlfriend","boyfriend","heart_gesture_1","pet_wizard","smoke_smoke","gun_shot","double_gun","pet_warrior","long_hair","pet_dance","wool_curly","pet_bee","marry_me","piggy_morph","ski_ski","magic_broom","splashsplash","surfsurf","fairy_wing","angel_wing","dark_wing","emoji"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect_scene","required":true,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-06T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a4/n5OqI6CfAidZeBLj6ITKi_HFadrX5v.png","title":"Kling 1.0"},{"category":"image-to-video","description":"Generate video clips from your images using Kling 1.0","endpoint_id":"fal-ai/kling-video/v1/standard/image-to-video","family":"Standard 1","inputs":[{"default":null,"description":"The prompt for the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"tail_image_url","required":false,"type":"string"},{"default":null,"description":"URL of the image for Static Brush Application Area (Mask image created by users using the motion brush)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"static_mask_url","required":false,"type":"string"},{"default":null,"description":"List of dynamic masks","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dynamic_masks","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-10-04T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91bb/tJp178VyGxzmj4KQOFiXS_TGheIeta.png","title":"Kling 1.0"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.0","endpoint_id":"fal-ai/kling-video/v1/standard/text-to-video","family":"Standard 1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":null,"description":"Camera control parameters","enum":["down_back","forward_up","right_turn_forward","left_turn_forward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_control","required":false,"type":"enum"},{"default":null,"description":"Advanced Camera control parameters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"advanced_camera_control","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-12-03T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f921f/WDNkZmrJ4Moo9N-ftGI0L_OCVWcwr8.png","title":"Kling 1.0"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the Kling TTS model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/kling-video/v1/tts","family":"Audio","inputs":[{"default":null,"description":"The text to be converted to speech","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"genshin_vindi2","description":"The voice ID to use for speech synthesis","enum":["genshin_vindi2","zhinen_xuesheng","AOT","ai_shatang","genshin_klee2","genshin_kirara","ai_kaiya","oversea_male1","ai_chenjiahao_712","girlfriend_4_speech02","chat1_female_new-3","chat_0407_5-1","cartoon-boy-07","uk_boy1","cartoon-girl-01","PeppaPig_platform","ai_huangzhong_712","ai_huangyaoshi_712","ai_laoguowang_712","chengshu_jiejie","you_pingjing","calm_story1","uk_man2","laopopo_speech02","heainainai_speech02","reader_en_m-v1","commercial_lady_en_f-v1","tiyuxi_xuedi","tiexin_nanyou","girlfriend_1_speech02","girlfriend_2_speech02","zhuxi_speech02","uk_oldman3","dongbeilaotie_speech02","chongqingxiaohuo_speech02","chuanmeizi_speech02","chaoshandashu_speech02","ai_taiwan_man2_speech02","xianzhanggui_speech02","tianjinjiejie_speech02","diyinnansang_DB_CN_M_04-v2","yizhipiannan-v1","guanxiaofang-v2","tianmeixuemei-v1","daopianyansang-v1","mengwa-v1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_id","required":false,"type":"enum"},{"default":1,"description":"Rate of speech","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.8,"multiline":false,"name":"voice_speed","required":false,"type":"number"}],"lab":"Kling","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-09-13T07:45:11.363000+00:00","thumbnail":"https://v3.fal.media/files/zebra/kuLfhOkVceXDTcdBxGQAf_2011e640a3aa4acab55d01d69f3a6e16.jpg","title":"Kling TTS"},{"category":"image-to-video","description":"Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","endpoint_id":"fal-ai/kling-video/v2.1/master/image-to-video","family":"Master 2.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $1.40. For every additional second you will be charged $0.28.","published_at":"2025-05-29T00:01:10.593000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-5.jpeg","title":"Kling 2.1 Master"},{"category":"text-to-video","description":"Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","endpoint_id":"fal-ai/kling-video/v2.1/master/text-to-video","family":"Master 2.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $1.40. For every aditional second you will be charged $0.28.","published_at":"2025-05-29T00:34:10.450000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-5.jpeg","title":"Kling 2.1 Master"},{"category":"image-to-video","description":"Kling 2.1 Pro is an advanced endpoint for the Kling 2.1 model, offering professional-grade videos with enhanced visual fidelity, precise camera movements, and dynamic motion control, perfect for cinematic storytelling.","endpoint_id":"fal-ai/kling-video/v2.1/pro/image-to-video","family":"Pro 2.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"tail_image_url","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.49. For every additional second you will be charged $0.098.","published_at":"2025-05-28T21:01:03.267000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"Kling 2.1 (pro)"},{"category":"image-to-video","description":"Kling 2.1 Standard is a cost-efficient endpoint for the Kling 2.1 model, delivering high-quality image-to-video generation","endpoint_id":"fal-ai/kling-video/v2.1/standard/image-to-video","family":"Standard 2.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.28. For every additional second you will be charged $0.056.","published_at":"2025-05-28T20:59:07.301000+00:00","thumbnail":"https://v3.fal.media/files/elephant/5Yt8D9tl-IaGQ-6czSXL1_HHQ_VCby6xP_DFLkQQLpV_3c8622214c4c4ac29b4b64e157746507.jpg","title":"Kling 2.1 (standard)"},{"category":"image-to-video","description":"Kling 2.5 Turbo Pro: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","endpoint_id":"fal-ai/kling-video/v2.5-turbo/pro/image-to-video","family":"Turbo Pro 2.5","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"tail_image_url","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.35. For every additional second you will be charged $0.07.","published_at":"2025-09-22T22:51:16.379000+00:00","thumbnail":"https://v3.fal.media/files/rabbit/2KNBk1qkmEBXK0FLgfHCl_ee4bb1ada254433bbab296893a8636e3.jpg","title":"Kling Video"},{"category":"text-to-video","description":"Kling 2.5 Turbo Pro: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","endpoint_id":"fal-ai/kling-video/v2.5-turbo/pro/text-to-video","family":"Turbo Pro 2.5","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.35. For every aditional second you will be charged $0.07.","published_at":"2025-09-22T22:48:44.637000+00:00","thumbnail":"https://v3.fal.media/files/panda/6YaK9lV7ySsUA9I3dUp5r_8a807b0c8e2641db9e345107ab8a809e.jpg","title":"Kling v2.5 Text to Video"},{"category":"image-to-video","description":"Kling 2.5 Turbo Standard: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","endpoint_id":"fal-ai/kling-video/v2.5-turbo/standard/image-to-video","family":"Turbo Standard 2.5","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.21. For every additional second you will be charged $0.042.","published_at":"2025-10-22T05:04:22.392000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/BJ1ZIdeClgqnUTW9XgEUS_d00e816ad20849ae9f92b735358d610d.jpg","title":"Kling Video"},{"category":"image-to-video","description":"Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation.","endpoint_id":"fal-ai/kling-video/v2.6/pro/image-to-video","family":"Pro 2.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"Optional Voice IDs for video generation. Reference voices in your prompt with <<<voice_1>>> and <<<voice_2>>> (maximum 2 voices per task). Get voice IDs from the kling video create-voice endpoint: https://fal.ai/models/fal-ai/kling-video/create-voice","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"voice_ids","required":false,"type":"string"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"Videos generated without audio cost $0.07 per second. Videos with native audio cost $0.14 per second, and videos with native audio and voice control cost $0.168 per second. For example, a 5-second video with audio costs $0.70, while a 10-second video with audio and voice control costs $1.68","published_at":"2025-12-02T09:01:46.898000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84aa9c/tRb6fibztV71jrhSPfdqP_3359db6ee74a4e4e9fb408a00b02e114.jpg","title":"Kling Video v2.6 Image to Video"},{"category":"video-to-video","description":"Transfer movements from a reference video to any character image. Pro mode delivers higher quality output, ideal for complex dance moves and gestures.","endpoint_id":"fal-ai/kling-video/v2.6/pro/motion-control","family":"Pro 2.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Reference image URL. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Reference video URL. The character actions in the generated video will be consistent with this reference video. Should contain a realistic style character with entire body or upper body visible, including head, without obstruction. Duration limit depends on character_orientation: 10s max for 'image', 30s max for 'video'.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"Whether to keep the original sound from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_sound","required":false,"type":"boolean"},{"default":null,"description":"Controls whether the output character's orientation matches the reference image or video. 'video': orientation matches reference video - better for complex motions (max 30s). 'image': orientation matches reference image - better for following camera movements (max 10s).","enum":["image","video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"character_orientation","required":true,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-21T20:50:54.254000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875735/LCSvFM3dgniinh9_nqgJX_99d6d4ec0be146c1a1e0899474b1c2ce.jpg","title":"Kling Video v2.6 Motion Control [Pro]"},{"category":"text-to-video","description":"Kling 2.6 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation.","endpoint_id":"fal-ai/kling-video/v2.6/pro/text-to-video","family":"Standard 2.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.07 (audio off) or $0.14 (audio on). For example, a 5s video with audio on will cost $0.70","published_at":"2025-12-02T09:03:38.171000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84aab6/uMErfUYxq7gJBJ0-MOKS7_2640fde44b6049a59bc34adf72e38ed7.jpg","title":"Kling Video v2.6 Text to Video"},{"category":"video-to-video","description":"Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.","endpoint_id":"fal-ai/kling-video/v2.6/standard/motion-control","family":"Standard 2.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Reference image URL. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Reference video URL. The character actions in the generated video will be consistent with this reference video. Should contain a realistic style character with entire body or upper body visible, including head, without obstruction. Duration limit depends on character_orientation: 10s max for 'image', 30s max for 'video'.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"Whether to keep the original sound from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_sound","required":false,"type":"boolean"},{"default":null,"description":"Controls whether the output character's orientation matches the reference image or video. 'video': orientation matches reference video - better for complex motions (max 30s). 'image': orientation matches reference image - better for following camera movements (max 10s).","enum":["image","video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"character_orientation","required":true,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-21T20:50:57.333000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875717/JVmIsgjXggpbFC-Szsr7q_8e01139cd9a1445facec60b125ca32c9.jpg","title":"Kling Video v2.6 Motion Control [Standard]"},{"category":"image-to-video","description":"Generate video clips from your images using Kling 2.0 Master","endpoint_id":"fal-ai/kling-video/v2/master/image-to-video","family":"Master 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $1.40. For every aditional second you will be charged $0.28.","published_at":"2025-04-14T21:50:19.724000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos.jpg","title":"Kling 2.0 Master"},{"category":"text-to-video","description":"Generate video clips from your prompts using Kling 2.0 Master","endpoint_id":"fal-ai/kling-video/v2/master/text-to-video","family":"Master 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $1.40. For every aditional second you will be charged $0.28.","published_at":"2025-04-14T21:47:18.476000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-5.jpeg","title":"Kling 2.0 Master"},{"category":"image-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","endpoint_id":"fal-ai/kling-video/v3/4k/image-to-video","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of prompts for multi-shot video generation. If provided, divides the video into multiple shots.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.42 regardless of whether audio is on or off. For example, a 5s video will cost $2.10.","published_at":"2026-04-23T14:59:09.550000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9740b3/ctjfWfLHCPzYgYUcWgTAz_ea95e9bfce584107b6937050fa127cca.jpg","title":"Kling Video"},{"category":"text-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","endpoint_id":"fal-ai/kling-video/v3/4k/text-to-video","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.42 regardless of whether audio is on or off. For example, a 5s video will cost $2.10.","published_at":"2026-04-23T14:59:05.287000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a970c17/m0f2ooX6jkF2UDw8yeU7w_0478d228dd9b4f58b26d5c833644465d.jpg","title":"Kling Video V3 Text to Video 4K"},{"category":"image-to-video","description":"Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.","endpoint_id":"fal-ai/kling-video/v3/pro/image-to-video","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of prompts for multi-shot video generation. If provided, divides the video into multiple shots.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.112 (audio off) or $0.168 (audio on), if voice control is used while generating audio you will be charged $0.196. For example, a 5s video with audio on and voice control will cost $0.98","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fb3/yPzcdzINnY5RdSoEqHc8G_382d4ec9337344ccaacf5599057f6cd0.jpg","title":"Kling Video v3 Image to Video [Pro]"},{"category":"video-to-video","description":"Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.","endpoint_id":"fal-ai/kling-video/v3/pro/motion-control","family":"Kling v3","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Reference image URL. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Reference video URL. The character actions in the generated video will be consistent with this reference video. Should contain a realistic style character with entire body or upper body visible, including head, without obstruction. Duration limit depends on character_orientation: 10s max for 'image', 30s max for 'video'.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"Whether to keep the original sound from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_sound","required":false,"type":"boolean"},{"default":null,"description":"Controls whether the output character's orientation matches the reference image or video. 'video': orientation matches reference video - better for complex motions (max 30s). 'image': orientation matches reference image - better for following camera movements (max 10s).","enum":["image","video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"character_orientation","required":true,"type":"enum"},{"default":null,"description":"Optional element for facial consistency binding. Upload a facial element to enhance identity preservation in the generated video. Only 1 element is supported. Reference in prompt as @Element1. Element binding is only supported when character_orientation is 'video'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-03-05T10:04:10.677000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90eee3/9FBKg0W0qDGikoxwCWZ7P_9328cc2a34f044b29591eb247e8f2ee4.jpg","title":"Kling Video"},{"category":"text-to-video","description":"Kling 3.0 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.","endpoint_id":"fal-ai/kling-video/v3/pro/text-to-video","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.112 (audio off) or $0.168 (audio on), if voice control is used while generating audio you will be charged $0.196. For example, a 5s video with audio on and voice control will cost $0.98","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfd13/t6TSkWzl6cFAzvO1PCdDu_f38263f637d245929f03881454951540.jpg","title":"Kling Video v3 Text to Video [Pro]"},{"category":"image-to-video","description":"Kling 3.0 Standard: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.","endpoint_id":"fal-ai/kling-video/v3/standard/image-to-video","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of prompts for multi-shot video generation. If provided, divides the video into multiple shots.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"URL of the image to be used for the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to be used for the end of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.084 (audio off) or $0.126 (audio on), if voice control is used while generating audio you will be charged $0.154. For example, a 5s video with audio on and voice control will cost $0.77","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfcdb/TywpxxNj5_vDG8AUw3Yum_e2172b5c00e64a91a434ab5a38e496f0.jpg","title":"Kling Video v3 Image to Video [Standard]"},{"category":"video-to-video","description":"Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations.","endpoint_id":"fal-ai/kling-video/v3/standard/motion-control","family":"Kling v3","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Reference image URL. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Reference video URL. The character actions in the generated video will be consistent with this reference video. Should contain a realistic style character with entire body or upper body visible, including head, without obstruction. Duration limit depends on character_orientation: 10s max for 'image', 30s max for 'video'.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"Whether to keep the original sound from the reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_original_sound","required":false,"type":"boolean"},{"default":null,"description":"Controls whether the output character's orientation matches the reference image or video. 'video': orientation matches reference video - better for complex motions (max 30s). 'image': orientation matches reference image - better for following camera movements (max 10s).","enum":["image","video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"character_orientation","required":true,"type":"enum"},{"default":null,"description":"Optional element for facial consistency binding. Upload a facial element to enhance identity preservation in the generated video. Only 1 element is supported. Reference in prompt as @Element1. Element binding is only supported when character_orientation is 'video'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"elements","required":false,"type":"json"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-03-05T10:06:48.803000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90eef3/th2aftqszI2TrC_TinR9E_da2a2fbd43d7461dbf2ad1e8865411d6.jpg","title":"Kling Video"},{"category":"text-to-video","description":"Kling 3.0 Standard: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.","endpoint_id":"fal-ai/kling-video/v3/standard/text-to-video","family":"Kling v3","inputs":[{"default":null,"description":"Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"5","description":"The duration of the generated video in seconds","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":true,"description":"Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"customize","description":"The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.","enum":["customize","intelligent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shot_type","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video frame","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"blur, distort, and low quality","description":"Negative Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.084 (audio off) or $0.126 (audio on), if voice control is used while generating audio you will be charged $0.154. For example, a 5s video with audio on and voice control will cost $0.77","published_at":"2026-02-04T15:48:44.935000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8cfc9f/dei5OqFRB9HK8AgSHwk8f_9a5eea197b3045d1be55aedb0213f6f9.jpg","title":"Kling Video v3 Text to Video [Standard]"},{"category":"image-to-video","description":"Generate high quality 1080p videos from images using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.","endpoint_id":"fal-ai/kling-video/v3/turbo/pro/image-to-video","family":"Kling v3 Turbo","inputs":[{"default":null,"description":"Optional text prompt. For best results keep the prompt under 2500 characters. Mutually exclusive with `multi_prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Multi-shot storyboard (1-6 shots). Each shot has its own prompt and duration; the total duration must not exceed 15s. Mutually exclusive with `prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"First-frame reference image. Formats: .jpg/.jpeg/.png; max 50MB; min 300px per side; aspect ratio within 1:2.5 to 2.5:1.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"Video length in seconds.","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate, you will be charged $0.14. For example, a 5s video will cost $0.70.","published_at":"2026-06-17T10:35:25.920000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e8d44/5jNAG5z5SIpJ3reiFLvE9_0dd9aa0ccefd417db62e1249cd258693.jpg","title":"Kling Video V3 Turbo Pro Image to Video"},{"category":"text-to-video","description":"Generate high quality 1080p videos using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.","endpoint_id":"fal-ai/kling-video/v3/turbo/pro/text-to-video","family":"Kling v3 Turbo","inputs":[{"default":null,"description":"Text prompt to generate the video with. For best results keep the prompt under 2500 characters. Mutually exclusive with `multi_prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Multi-shot storyboard (1-6 shots). Each shot has its own prompt and duration; the total duration must not exceed 15s. Mutually exclusive with `prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"16:9","description":"The aspect ratio (width:height) of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5","description":"Video length in seconds.","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate, you will be charged $0.14 . For example, a 5s video will cost $0.70.","published_at":"2026-06-17T10:35:32.502000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e8d77/SDWDZwZ_Rz7vgKlPopK8x_be12e85845f242deb7a652ef22831bfa.jpg","title":"Kling Video V3 Turbo Pro Text to Video"},{"category":"image-to-video","description":"Kling 3.0 Turbo Standard animates a first and last frame reference image into 720P video with native audio, delivering quick, affordable image-driven motion for fast turnaround","endpoint_id":"fal-ai/kling-video/v3/turbo/standard/image-to-video","family":"Kling v3 Turbo","inputs":[{"default":null,"description":"Optional text prompt. For best results keep the prompt under 2500 characters. Mutually exclusive with `multi_prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Multi-shot storyboard (1-6 shots). Each shot has its own prompt and duration; the total duration must not exceed 15s. Mutually exclusive with `prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":null,"description":"First-frame reference image. Formats: .jpg/.jpeg/.png; max 50MB; min 300px per side; aspect ratio within 1:2.5 to 2.5:1.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"5","description":"Video length in seconds.","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate, you will be charged $0.112. For example, a 5s video will cost $0.56","published_at":"2026-06-17T10:35:41.867000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e8d71/TxBCnKdpvigMDNbGcyta-_75938bbec6fe473e85a8d89094378c1e.jpg","title":"Kling Video V3 Standard Turbo Image to Video"},{"category":"text-to-video","description":"Kling 3.0 Turbo Standard is a fast, cost-efficient video generation model that turns text prompts directly into 720P video with native audio, optimized for rapid iteration and high-volume production","endpoint_id":"fal-ai/kling-video/v3/turbo/standard/text-to-video","family":"Kling v3 Turbo","inputs":[{"default":null,"description":"Text prompt to generate the video with. For best results keep the prompt under 2500 characters. Mutually exclusive with `multi_prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Multi-shot storyboard (1-6 shots). Each shot has its own prompt and duration; the total duration must not exceed 15s. Mutually exclusive with `prompt`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_prompt","required":false,"type":"json"},{"default":"16:9","description":"The aspect ratio (width:height) of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5","description":"Video length in seconds.","enum":["3","4","5","6","7","8","9","10","11","12","13","14","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Kling","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate, you will be charged $0.112 . For example, a 5s video will cost $0.56.","published_at":"2026-06-17T10:35:11.236000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e8d89/LDScfQJoDfPCdVK2OWRky_c8428cc1efc84391b93c08e4a2529c35.jpg","title":"Kling Video V3 Standard Turbo Text to Video"},{"category":"video-to-audio","description":"Generate audio from input videos using Kling","endpoint_id":"fal-ai/kling-video/video-to-audio","family":"Audio","inputs":[{"default":null,"description":"The video URL to extract audio from. Only .mp4/.mov formats are supported. File size does not exceed 100MB. Video duration between 3.0s and 20.0s.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":"Car tires screech as they accelerate in a drag race","description":"Sound effect prompt. Cannot exceed 200 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sound_effect_prompt","required":false,"type":"string"},{"default":"intense car race","description":"Background music prompt. Cannot exceed 200 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_music_prompt","required":false,"type":"string"},{"default":false,"description":"Enable ASMR mode. This mode enhances detailed sound effects and is suitable for highly immersive content scenarios.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"asmr_mode","required":false,"type":"boolean"}],"lab":"Kling","output_kind":"video","output_props":["video","audio"],"pricing":"Your video request will cost $0.035 per video.","published_at":"2025-10-09T17:25:52.059000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/UcIrV8sk1rLDIZAkPoW75_32e8d2d3f8de429aa32f3f35b595d5ac.jpg","title":"Kling Video"},{"category":"image-to-image","description":"Kling Kolors Virtual TryOn v1.5 is a high quality image based Try-On endpoint which can be used for commercial try on.","endpoint_id":"fal-ai/kling/v1-5/kolors-virtual-try-on","family":"Kolors Virtual Try On","inputs":[{"default":null,"description":"Url for the human image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"human_image_url","required":true,"type":"string"},{"default":null,"description":"Url to the garment image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"garment_image_url","required":true,"type":"string"}],"lab":"Kling","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-01-23T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kling-tryon.webp","title":"Kling Kolors Virtual TryOn v1.5"},{"category":"text-to-audio","description":"Kokoro is a lightweight text-to-speech model that delivers comparable quality to larger models while being significantly faster and more cost-efficient.","endpoint_id":"fal-ai/kokoro/american-english","family":"Korokoro","inputs":[{"default":"","description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"af_heart","description":"Voice ID for the desired voice.","enum":["af_heart","af_alloy","af_aoede","af_bella","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS"},{"category":"text-to-audio","description":"A natural and expressive Brazilian Portuguese text-to-speech model optimized for clarity and fluency.","endpoint_id":"fal-ai/kokoro/brazilian-portuguese","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["pf_dora","pm_alex","pm_santa"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (Brazilian Portuguese)"},{"category":"text-to-audio","description":"A high-quality British English text-to-speech model offering natural and expressive voice synthesis.","endpoint_id":"fal-ai/kokoro/british-english","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (British English)"},{"category":"text-to-audio","description":"An expressive and natural French text-to-speech model for both European and Canadian French.","endpoint_id":"fal-ai/kokoro/french","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"string"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (French)"},{"category":"text-to-audio","description":"A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.","endpoint_id":"fal-ai/kokoro/hindi","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["hf_alpha","hf_beta","hm_omega","hm_psi"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (Hindi)"},{"category":"text-to-audio","description":"A high-quality Italian text-to-speech model delivering smooth and expressive speech synthesis.","endpoint_id":"fal-ai/kokoro/italian","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["if_sara","im_nicola"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (Italian)"},{"category":"text-to-audio","description":"A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.","endpoint_id":"fal-ai/kokoro/japanese","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (Japanese)"},{"category":"text-to-audio","description":"A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.","endpoint_id":"fal-ai/kokoro/mandarin-chinese","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (Mandarin Chinese)"},{"category":"text-to-audio","description":"A natural-sounding Spanish text-to-speech model optimized for Latin American and European Spanish.","endpoint_id":"fal-ai/kokoro/spanish","family":"Korokoro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Voice ID for the desired voice.","enum":["ef_dora","em_alex","em_santa"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":true,"type":"enum"},{"default":1,"description":"Speed of the generated audio. Default is 1.0.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"speed","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/kokoro.webp","title":"Kokoro TTS (Spanish)"},{"category":"text-to-image","description":"Photorealistic Text-to-Image","endpoint_id":"fal-ai/kolors","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible\n            for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small\n            details (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show\n            you.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":150,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Seed","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"EulerDiscreteScheduler","description":"The scheduler to use for the model.","enum":["EulerDiscreteScheduler","EulerAncestralDiscreteScheduler","DPMSolverMultistepScheduler","DPMSolverMultistepScheduler_SDE_karras","UniPCMultistepScheduler","DEISMultistepScheduler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images"],"pricing":"","published_at":"2024-07-24T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cd/sOwGvXGzXxHg31dstN4iM_raE5iVKB.png","title":"Kolors"},{"category":"image-to-image","description":"Photorealistic Image-to-Image","endpoint_id":"fal-ai/kolors/image-to-image","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small\n            details (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show\n            you.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":150,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Seed","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"EulerDiscreteScheduler","description":"The scheduler to use for the model.","enum":["EulerDiscreteScheduler","EulerAncestralDiscreteScheduler","DPMSolverMultistepScheduler","DPMSolverMultistepScheduler_SDE_karras","UniPCMultistepScheduler","DEISMultistepScheduler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for image to image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for image-to-image. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images"],"pricing":"","published_at":"2024-11-19T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92db/QGrbu5ZzbaoLnYBiEOfP-_NnWzLRTm.png","title":"Kolors Image to Image"},{"category":"training","description":"Train a custom LoRA on your own images to teach Krea 2 a new subject, character, or style. Provide a set of training images (and an optional trigger word), and the trainer outputs LoRA weights you can use for inference with the Krea 2 LoRA endpoint.","endpoint_id":"fal-ai/krea-2-trainer","family":"Krea 2","inputs":[{"default":null,"description":"URL to a .zip archive of training images (PNG/JPG/JPEG/WebP). Each image may carry a same-stem caption: an image named ROOT.EXT (e.g. 001.jpg) pairs with a caption file named ROOT.txt (e.g. 001.txt). Images with no caption file fall back to `trigger_phrase`, so each image must have either a caption file or a non-empty `trigger_phrase` — otherwise the request is rejected (422).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"images_data_url","required":true,"type":"string"},{"default":"","description":"Instance phrase used as the caption for any image that ships no .txt caption file (DreamBooth-style); also seeds the default validation prompts. Required when some images have no caption file.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"trigger_phrase","required":false,"type":"string"},{"default":100,"description":"Number of LoRA training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":50,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":0.0005,"description":"Learning rate for the LoRA B factor (and for A when lora_a_lr_multiplier=1). Krea recommends 3e-4–7e-4 (constant schedule). For muon this is the match_rms_adamw-scaled (AdamW-equivalent) rate.","enum":null,"is_list":false,"max":0.01,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":768,"description":"Training resolution (images are cover-resized + center-cropped to a square). 768 trains ~1.7x faster at lower VRAM with near-identical style quality; 1024 maximizes fine detail.","enum":[768,1024],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"Krea","output_kind":"json","output_props":["lora_file","config_file"],"pricing":"Your request will cost $0.003 per step (minimum of 100 steps is charged). For $3.00 you can fine-tune a LoRA for 1000 steps.","published_at":"2026-06-23T15:01:58.782000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ef656/Ov0Byfl71Sas_ciPWfIME_c44dbe42b1b5457284c6e3ede2aa48af.jpg","title":"Krea 2 Trainer"},{"category":"text-to-image","description":"Generate high-fidelity images from text in seconds with Krea 2 Turbo, the speed-optimized open-source version of Krea 2, preserving its aesthetic range for rapid ideation.","endpoint_id":"fal-ai/krea-2/turbo","family":"Krea 2","inputs":[{"default":null,"description":"Base text description of the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation. Image *i* uses `seed + i`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"If true, the prompt is expanded with an LLM into a more detailed image-generation prompt for higher quality results. On failure, the original prompt is used unchanged.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If true, the output safety checker is enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image. Default value: \"png\".","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Krea","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images","actual_prompt"],"pricing":"","published_at":"2026-06-23T15:01:52.708000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ec8c9/8GzWPYzjnpIp9l_nVysti_51daab936c734a849698a7fee8718d5e.jpg","title":"Krea 2 Turbo"},{"category":"text-to-image","description":"Generate high-fidelity images from text with Krea 2 using a custom-trained LoRA. Apply your LoRA weights to carry a learned subject, character, or style into new generations, with aspect ratio, creativity, and seed controls.","endpoint_id":"fal-ai/krea-2/turbo/lora","family":"","inputs":[{"default":null,"description":"Base text description of the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation. Image *i* uses `seed + i`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"If true, the prompt is expanded with an LLM into a more detailed image-generation prompt for higher quality results. On failure, the original prompt is used unchanged.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If true, the output safety checker is enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image. Default value: \"png\".","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Krea 2","output_kind":"images","output_props":["has_nsfw_concepts","prompt","seed","timings","images","actual_prompt"],"pricing":"","published_at":"2026-06-23T15:01:46.384000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ef641/oqnroPiZGVS7bvCi0AW5b_4644ed5f7c5d429683842d2707edfdc6.jpg","title":"Krea 2 Text to Image Turbo LoRA"},{"category":"text-to-video","description":"Fast Text-to-Video endpoint for Krea's Wan 14b model.","endpoint_id":"fal-ai/krea-wan-14b/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt for the video-to-video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":78,"description":"Number of frames to generate. Must be a multiple of 12 plus 6, for example 6, 18, 30, 42, etc.","enum":null,"is_list":false,"max":162,"media_kind":null,"min":18,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Seed for the video-to-video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Generation will cost $0.025 per output video second. Video seconds are calculated at 16 frames per second.","published_at":"2025-10-20T17:24:26.630000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/n7SozOMd7d9UiTYhyZ4w3_99e21d49333f47b9be7e834d73a16d8a.jpg","title":"Krea Wan 14b- Text to Video"},{"category":"video-to-video","description":"Superfast video model based on Wan 2.1 14b by Krea, excelling at real-time video-editing.","endpoint_id":"fal-ai/krea-wan-14b/video-to-video","family":"","inputs":[{"default":null,"description":"Prompt for the video-to-video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.85,"description":"Denoising strength for the video-to-video generation. 0.0 preserves the original, 1.0 completely remakes the video.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of the input video. Currently, only outputs of 16:9 aspect ratio and 480p resolution are supported. Video duration should be less than 1000 frames at 16fps, and output frames will be 6 plus a multiple of 12, for example 18, 30, 42, etc.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Seed for the video-to-video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Generation will cost $0.025 per output video second. Video seconds are calculated at 16 frames per second.","published_at":"2025-10-14T16:06:51.280000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/3KnxV95bno9CU_SVwV0t8_aff74947261f49b4bf8a51a050881c86.jpg","title":"Krea Wan 14B"},{"category":"video-to-video","description":"LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.","endpoint_id":"fal-ai/latentsync","family":"","inputs":[{"default":null,"description":"The URL of the video to generate the lip sync for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the lip sync for.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":1,"description":"Guidance scale for the model inference","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for generation. If None, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Video loop mode when audio is longer than video. Options: pingpong, loop","enum":["pingpong","loop"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.2 for videos up to 40 seconds. For longer videos, you will be charged $0.005 per second of output video.","published_at":"2025-03-25T10:24:14.332000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/latentsync/latentsync-3.jpg","title":"LatentSync"},{"category":"image-to-image","description":"Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.","endpoint_id":"fal-ai/lcm-sd15-i2i","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image to use as a base.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Mask URL for compatibility with generic LCM processing.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":0.8,"description":"The strength of the image.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"The number of inference steps to use for generating the image. The more steps\n            the better the image will be but it will also take longer to generate.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate. The function will return a list of images\n            with the same prompt and negative prompt but different seeds.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the resulting image will be checked whether it includes any\n            potentially unsafe content. If it does, it will be replaced with a black\n            image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checks","required":false,"type":"boolean"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["nsfw_content_detected","images","timings","seed","num_inference_steps","request_id"],"pricing":"","published_at":"2023-11-09T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d5/EcYi47KYeG4fd29mNN0tO_o39MWrcR.png","title":"Optimized Latent Consistency (SDv1.5)"},{"category":"image-to-image","description":"Leffa Pose Transfer is an endpoint for changing pose of an image with a reference image.","endpoint_id":"fal-ai/leffa/pose-transfer","family":"","inputs":[{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same input given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your input when generating the image.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Url for the human image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"pose_image_url","required":true,"type":"string"},{"default":null,"description":"Url to the garment image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"person_image_url","required":true,"type":"string"}],"lab":"","output_kind":"image","output_props":["has_nsfw_concepts","image","seed"],"pricing":"","published_at":"2024-12-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/leffa-pose-transfer.webp","title":"Leffa Pose Transfer"},{"category":"image-to-image","description":"Leffa Virtual TryOn is a high quality image based Try-On endpoint which can be used for commercial try on.","endpoint_id":"fal-ai/leffa/virtual-tryon","family":"","inputs":[{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same input given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your input when generating the image.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Url for the human image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"human_image_url","required":true,"type":"string"},{"default":null,"description":"Url to the garment image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"garment_image_url","required":true,"type":"string"},{"default":null,"description":"The type of the garment used for virtual try-on.","enum":["upper_body","lower_body","dresses"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"garment_type","required":true,"type":"enum"}],"lab":"","output_kind":"image","output_props":["has_nsfw_concepts","image","seed"],"pricing":"","published_at":"2024-12-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/leffa-vitrual-tryon.webp","title":"Leffa Virtual TryOn"},{"category":"video-to-video","description":"Use the capabilities of lightx to relight and recamera your videos.","endpoint_id":"fal-ai/lightx/recamera","family":"","inputs":[{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional text prompt. If omitted, Light-X will auto-caption the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"traj","description":"Camera control mode.","enum":["traj","target"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera","required":false,"type":"enum"},{"default":"gradual","description":"Camera motion mode.","enum":["gradual","bullet","direct","dolly-zoom"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Camera trajectory parameters (required for recamera mode).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trajectory","required":false,"type":"json"},{"default":null,"description":"Target camera pose [theta, phi, radius, x, y] (required when camera='target').","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_pose","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video","input_video","seed","viz_video"],"pricing":"Your request will cost 0.1$ per output video second.","published_at":"2025-12-22T08:40:57.122000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875717/n43lZ8MEY6tF-23JFWuT7_21bfd358f8d747d2bffa37ac97e4c781.jpg","title":"Lightx"},{"category":"video-to-video","description":"Use tlightx capabilities to relight and recamera your videos.","endpoint_id":"fal-ai/lightx/relight","family":"","inputs":[{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional text prompt. If omitted, Light-X will auto-caption the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"ic","description":"Relight condition type.","enum":["ic","ref","hdr","bg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"relit_cond_type","required":false,"type":"enum"},{"default":null,"description":"Relighting parameters (required for relight_condition_type='ic'). Not used for 'bg' (which expects a background image URL instead).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"relight_parameters","required":false,"type":"json"},{"default":null,"description":"URL of conditioning image. Required for relight_condition_type='ref'/'hdr'. Also required for relight_condition_type='bg' (background image).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"relit_cond_img_url","required":false,"type":"string"},{"default":0,"description":"Frame index to use as reference to relight the video with reference. Must be less than the number of generated frames (default 49).","enum":null,"is_list":false,"max":48,"media_kind":null,"min":0,"multiline":false,"name":"ref_id","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video","input_video","seed","viz_video"],"pricing":"Your request will cost 0.1$ per output video second.","published_at":"2025-12-22T08:41:53.484000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875717/5px7bRzEoq58JtxruJDKL_dd06f08a34c6477cbac929a55b2825ad.jpg","title":"Lightx"},{"category":"image-to-video","description":"Transfer expression from a video to a portrait.","endpoint_id":"fal-ai/live-portrait","family":"","inputs":[{"default":null,"description":"URL of the video to drive the lip syncing.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to be animated","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0,"description":"Amount to blink the eyes","enum":null,"is_list":false,"max":30,"media_kind":null,"min":-30,"multiline":false,"name":"blink","required":false,"type":"number"},{"default":0,"description":"Amount to raise or lower eyebrows","enum":null,"is_list":false,"max":30,"media_kind":null,"min":-30,"multiline":false,"name":"eyebrow","required":false,"type":"number"},{"default":0,"description":"Amount to wink","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"wink","required":false,"type":"number"},{"default":0,"description":"Amount to move pupils horizontally","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"pupil_x","required":false,"type":"number"},{"default":0,"description":"Amount to move pupils vertically","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"pupil_y","required":false,"type":"number"},{"default":0,"description":"Amount to open mouth in 'aaa' shape","enum":null,"is_list":false,"max":200,"media_kind":null,"min":-200,"multiline":false,"name":"aaa","required":false,"type":"number"},{"default":0,"description":"Amount to shape mouth in 'eee' position","enum":null,"is_list":false,"max":40,"media_kind":null,"min":-40,"multiline":false,"name":"eee","required":false,"type":"number"},{"default":0,"description":"Amount to shape mouth in 'woo' position","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"woo","required":false,"type":"number"},{"default":0,"description":"Amount to smile","enum":null,"is_list":false,"max":2,"media_kind":null,"min":-2,"multiline":false,"name":"smile","required":false,"type":"number"},{"default":true,"description":"Whether to set the lip to closed state before animation. Only takes effect when flag_eye_retargeting and flag_lip_retargeting are False.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_lip_zero","required":false,"type":"boolean"},{"default":0,"description":"Amount to rotate the face in pitch","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"rotate_pitch","required":false,"type":"number"},{"default":0,"description":"Amount to rotate the face in yaw","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"rotate_yaw","required":false,"type":"number"},{"default":0,"description":"Amount to rotate the face in roll","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"rotate_roll","required":false,"type":"number"},{"default":false,"description":"Whether to enable eye retargeting.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_eye_retargeting","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable lip retargeting.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_lip_retargeting","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable stitching. Recommended to set to True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_stitching","required":false,"type":"boolean"},{"default":true,"description":"Whether to use relative motion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_relative","required":false,"type":"boolean"},{"default":true,"description":"Whether to paste-back/stitch the animated face cropping from the face-cropping space to the original image space.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_pasteback","required":false,"type":"boolean"},{"default":true,"description":"Whether to crop the source portrait to the face-cropping space.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_do_crop","required":false,"type":"boolean"},{"default":true,"description":"Whether to conduct the rotation when flag_do_crop is True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_do_rot","required":false,"type":"boolean"},{"default":512,"description":"Size of the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dsize","required":false,"type":"integer"},{"default":2.3,"description":"Scaling factor for the face crop.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":0,"description":"Horizontal offset ratio for face crop.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"vx_ratio","required":false,"type":"number"},{"default":-0.125,"description":"Vertical offset ratio for face crop. Positive values move up, negative values move down.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"vy_ratio","required":false,"type":"number"},{"default":32,"description":"Batch size for the model. The larger the batch size, the faster the model will run, but the more memory it will consume.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"batch_size","required":false,"type":"integer"},{"default":false,"description":"Whether to enable the safety checker. If enabled, the model will check if the input image contains a face before processing it.\n        The safety checker will process the input image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-07-09T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/live-portrait/XKEmk3mAzGHUjK3qqH-UL.jpeg","title":"Live Portrait"},{"category":"image-to-image","description":"Transfer expression from a video to a portrait.","endpoint_id":"fal-ai/live-portrait/image","family":"","inputs":[{"default":null,"description":"URL of the image to be animated","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0,"description":"Amount to blink the eyes","enum":null,"is_list":false,"max":30,"media_kind":null,"min":-30,"multiline":false,"name":"blink","required":false,"type":"number"},{"default":0,"description":"Amount to raise or lower eyebrows","enum":null,"is_list":false,"max":30,"media_kind":null,"min":-30,"multiline":false,"name":"eyebrow","required":false,"type":"number"},{"default":0,"description":"Amount to wink","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"wink","required":false,"type":"number"},{"default":0,"description":"Amount to move pupils horizontally","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"pupil_x","required":false,"type":"number"},{"default":0,"description":"Amount to move pupils vertically","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"pupil_y","required":false,"type":"number"},{"default":0,"description":"Amount to open mouth in 'aaa' shape","enum":null,"is_list":false,"max":200,"media_kind":null,"min":-200,"multiline":false,"name":"aaa","required":false,"type":"number"},{"default":0,"description":"Amount to shape mouth in 'eee' position","enum":null,"is_list":false,"max":40,"media_kind":null,"min":-40,"multiline":false,"name":"eee","required":false,"type":"number"},{"default":0,"description":"Amount to shape mouth in 'woo' position","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"woo","required":false,"type":"number"},{"default":0,"description":"Amount to smile","enum":null,"is_list":false,"max":2,"media_kind":null,"min":-2,"multiline":false,"name":"smile","required":false,"type":"number"},{"default":0,"description":"Amount to rotate the face in pitch","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"rotate_pitch","required":false,"type":"number"},{"default":0,"description":"Amount to rotate the face in yaw","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"rotate_yaw","required":false,"type":"number"},{"default":0,"description":"Amount to rotate the face in roll","enum":null,"is_list":false,"max":45,"media_kind":null,"min":-45,"multiline":false,"name":"rotate_roll","required":false,"type":"number"},{"default":true,"description":"Whether to paste-back/stitch the animated face cropping from the face-cropping space to the original image space.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_pasteback","required":false,"type":"boolean"},{"default":true,"description":"Whether to crop the source portrait to the face-cropping space.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_do_crop","required":false,"type":"boolean"},{"default":true,"description":"Whether to conduct the rotation when flag_do_crop is True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_do_rot","required":false,"type":"boolean"},{"default":true,"description":"Whether to set the lip to closed state before animation. Only takes effect when flag_eye_retargeting and flag_lip_retargeting are False.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"flag_lip_zero","required":false,"type":"boolean"},{"default":512,"description":"Size of the output image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dsize","required":false,"type":"integer"},{"default":2.3,"description":"Scaling factor for the face crop.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scale","required":false,"type":"number"},{"default":0,"description":"Horizontal offset ratio for face crop.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"vx_ratio","required":false,"type":"number"},{"default":-0.125,"description":"Vertical offset ratio for face crop. Positive values move up, negative values move down.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"vy_ratio","required":false,"type":"number"},{"default":false,"description":"Whether to enable the safety checker. If enabled, the model will check if the input image contains a face before processing it.\n        The safety checker will process the input image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"Output format","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-10-01T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/live-portrait/XKEmk3mAzGHUjK3qqH-UL.jpeg","title":"Live Portrait"},{"category":"vision","description":"Vision","endpoint_id":"fal-ai/llava-next","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt to be used for the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":64,"description":"Maximum number of tokens to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.2,"description":"Temperature for sampling","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1,"description":"Top P for sampling","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"","output_kind":"json","output_props":["output","partial"],"pricing":"","published_at":"2024-02-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92ce/Qoz1WSnGLXw-DmP0gx_Qe_pbbY0ZnI.png","title":"LLaVA v1.6 34B"},{"category":"text-to-image","description":"LongCat image is a 6B parameter model excelling at multilingual text rendering, photorealism and deployment efficiency.","endpoint_id":"fal-ai/longcat-image","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4.5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["timings","prompt","has_nsfw_concepts","images","seed"],"pricing":"","published_at":"2025-12-05T17:12:42.231000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a851b6e/FRYO5MwzWRxk8dt0FR5Ib_bb0a8072b65d4af59dbb8fccdd52b02b.jpg","title":"Longcat Image"},{"category":"image-to-image","description":"LongCat image Edit is a 6B parameter image editing model excelling at multilingual text rendering, photorealism and deployment efficiency.","endpoint_id":"fal-ai/longcat-image/edit","family":"","inputs":[{"default":null,"description":"The prompt to edit the image with.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4.5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"The URL of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["timings","prompt","has_nsfw_concepts","images","seed"],"pricing":"","published_at":"2025-12-05T19:51:05.485000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a859c1b/mdsG5LYIfadIqFJkLMWbo_b0fd88a073a64e0eb378a3f1ba907087.jpg","title":"Longcat Image"},{"category":"audio-to-video","description":"LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.","endpoint_id":"fal-ai/longcat-single-avatar/audio-to-video","family":"","inputs":[{"default":null,"description":"The URL of the audio file to drive the avatar.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"A person is talking naturally with natural expressions and movements.","description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"Close-up, Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"The negative prompt to avoid in the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The text guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"text_guidance_scale","required":false,"type":"number"},{"default":4,"description":"The audio guidance scale. Higher values may lead to exaggerated mouth movements.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"audio_guidance_scale","required":false,"type":"number"},{"default":"480p","description":"Resolution of the generated video (480p or 720p). Billing is per video-second (16 frames): 480p is 1 unit per second and 720p is 4 units per second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Number of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_segments","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion using an LLM to enhance the prompt for better video quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"Your request will cost $0.3 per video second for 720p, $0.15 per video second for 480p.","published_at":"2025-12-30T17:00:38.944000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8866d6/omvktK-AVCuPF0QU33P4A_8b2b938566bf4a85830f5b90b84180cf.jpg","title":"Longcat Single Avatar"},{"category":"audio-to-video","description":"LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.","endpoint_id":"fal-ai/longcat-single-avatar/image-audio-to-video","family":"","inputs":[{"default":null,"description":"The URL of the image to animate.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file to drive the avatar.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"A person is talking naturally with natural expressions and movements.","description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"Close-up, Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"The negative prompt to avoid in the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The text guidance scale for classifier-free guidance.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"text_guidance_scale","required":false,"type":"number"},{"default":4,"description":"The audio guidance scale. Higher values may lead to exaggerated mouth movements.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"audio_guidance_scale","required":false,"type":"number"},{"default":"480p","description":"Resolution of the generated video (480p or 720p). Billing is per video-second (16 frames): 480p is 1 unit per second and 720p is 4 units per second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Number of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_segments","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion using an LLM to enhance the prompt for better video quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"Your request will cost $0.3 per video second for 720p, $0.15 per video second for 480p.","published_at":"2025-12-30T17:14:46.673000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a88673c/x25WUIBOLHSgnJqo5Ph6C_cbcdeb6ce3844dc79c98760e44c071c2.jpg","title":"Longcat Single Avatar"},{"category":"image-to-video","description":"Generate long videos from images using LongCat Video Distilled","endpoint_id":"fal-ai/longcat-video/distilled/image-to-video/480p","family":"","inputs":[{"default":null,"description":"The URL of the image to generate a video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"First-person view from the cockpit of a Formula 1 car. The driver's gloved hands firmly grip the intricate, carbon-fiber steering wheel adorned with numerous colorful buttons and a vibrant digital display showing race data. Beyond the windshield, a sun-drenched racetrack stretches ahead, lined with cheering spectators in the grandstands. Several rival cars are visible in the distance, creating a dynamic sense of competition. The sky above is a clear, brilliant blue, reflecting the exhilarating atmosphere of a high-speed race. high resolution 4k","description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":12,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":15,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.005 per generated second of video. Generated seconds are calculated at 15 frames per second.","published_at":"2025-10-29T00:26:46.200000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/iOwf_UFypDFAPX27ciX7N_03c77dfefc0a4e82a7f500216b609240.jpg","title":"LongCat Video Distilled"},{"category":"image-to-video","description":"Generate long videos in 720p/30fps from images using LongCat Video Distilled","endpoint_id":"fal-ai/longcat-video/distilled/image-to-video/720p","family":"","inputs":[{"default":null,"description":"The URL of the image to generate a video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"First-person view from the cockpit of a Formula 1 car. The driver's gloved hands firmly grip the intricate, carbon-fiber steering wheel adorned with numerous colorful buttons and a vibrant digital display showing race data. Beyond the windshield, a sun-drenched racetrack stretches ahead, lined with cheering spectators in the grandstands. Several rival cars are visible in the distance, creating a dynamic sense of competition. The sky above is a clear, brilliant blue, reflecting the exhilarating atmosphere of a high-speed race. high resolution 4k","description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":12,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":12,"description":"The number of inference steps to use for refinement.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":2,"multiline":false,"name":"num_refine_inference_steps","required":false,"type":"integer"},{"default":30,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.01 per generated second of video. Generated seconds are calculated at 30 frames per second.","published_at":"2025-10-30T14:43:43.650000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/PlEcqdZVUsm3jFXpUPvvT_5da6319dbf674dffbea088eaa87a979c.jpg","title":"LongCat Video Distilled"},{"category":"text-to-video","description":"Generate long videos from text using LongCat Video Distilled","endpoint_id":"fal-ai/longcat-video/distilled/text-to-video/480p","family":"","inputs":[{"default":null,"description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":12,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":15,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.005 per generated second of video. Generated seconds are calculated at 15 frames per second.","published_at":"2025-10-28T23:29:22.398000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/wjjJyktF2Y8GLxCDR9XsW_11eea2cee7e94b67aa89b3fc28ee55e1.jpg","title":"LongCat Video Distilled"},{"category":"text-to-video","description":"Generate long videos in 720p/30fps from text using LongCat Video Distilled","endpoint_id":"fal-ai/longcat-video/distilled/text-to-video/720p","family":"","inputs":[{"default":null,"description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":12,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":12,"description":"The number of inference steps to use for refinement.","enum":null,"is_list":false,"max":16,"media_kind":null,"min":2,"multiline":false,"name":"num_refine_inference_steps","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.01 per generated second of video. Generated seconds are calculated at 30 frames per second.","published_at":"2025-10-30T14:41:43.380000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/Xh3L9IfiYFQpDx1WpQH8T_e0057041856c45b1ab31a267f8132455.jpg","title":"LongCat Video Distilled"},{"category":"image-to-video","description":"Generate long videos from images using LongCat Video","endpoint_id":"fal-ai/longcat-video/image-to-video/480p","family":"","inputs":[{"default":null,"description":"The URL of the image to generate a video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"First-person view from the cockpit of a Formula 1 car. The driver's gloved hands firmly grip the intricate, carbon-fiber steering wheel adorned with numerous colorful buttons and a vibrant digital display showing race data. Beyond the windshield, a sun-drenched racetrack stretches ahead, lined with cheering spectators in the grandstands. Several rival cars are visible in the distance, creating a dynamic sense of competition. The sky above is a clear, brilliant blue, reflecting the exhilarating atmosphere of a high-speed race. high resolution 4k","description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"The negative prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":40,"description":"The number of inference steps to use for the video generation.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":15,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the video generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.025 per generated second of video. Generated seconds are calculated at 15 frames per second.","published_at":"2025-10-30T14:54:52.837000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/kqIypfhdZ87GT5n4t5mx__a7a61a1a39ec4ef2af632def10db2776.jpg","title":"LongCat Video"},{"category":"image-to-video","description":"Generate long videos in 720p/30fps from images using LongCat Video","endpoint_id":"fal-ai/longcat-video/image-to-video/720p","family":"","inputs":[{"default":null,"description":"The URL of the image to generate a video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"First-person view from the cockpit of a Formula 1 car. The driver's gloved hands firmly grip the intricate, carbon-fiber steering wheel adorned with numerous colorful buttons and a vibrant digital display showing race data. Beyond the windshield, a sun-drenched racetrack stretches ahead, lined with cheering spectators in the grandstands. Several rival cars are visible in the distance, creating a dynamic sense of competition. The sky above is a clear, brilliant blue, reflecting the exhilarating atmosphere of a high-speed race. high resolution 4k","description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"The negative prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":40,"description":"The number of inference steps to use for the video generation.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":40,"description":"The number of inference steps to use for refinement.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_refine_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the video generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.04 per generated second of video. Generated seconds are calculated at 30 frames per second.","published_at":"2025-10-30T16:23:09.789000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/s_V-U5ax-L7FjU5Ua0Jmk_723a0755259f44d492e6cf825608804c.jpg","title":"LongCat Video"},{"category":"text-to-video","description":"Generate long videos from text using LongCat Video","endpoint_id":"fal-ai/longcat-video/text-to-video/480p","family":"","inputs":[{"default":null,"description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"The negative prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":40,"description":"The number of inference steps to use for the video generation.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":15,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the video generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.025 per generated second of video. Generated seconds are calculated at 15 frames per second.","published_at":"2025-10-30T14:50:01.405000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/rYYa2jpouP8HP5sofxQjq_194c767959414548bff2c3f04fedbe0f.jpg","title":"LongCat Video"},{"category":"text-to-video","description":"Generate long videos in 720p/30fps from text using LongCat Video","endpoint_id":"fal-ai/longcat-video/text-to-video/720p","family":"","inputs":[{"default":null,"description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards","description":"The negative prompt to use for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":162,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":961,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":40,"description":"The number of inference steps to use for the video generation.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":40,"description":"The number of inference steps to use for refinement.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_refine_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"The frame rate of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use for the video generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.04 per generated second of video. Generated seconds are calculated at 30 frames per second.","published_at":"2025-10-30T16:24:45.138000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/yE1r-CAPmdJnlspqz6rJf_520c6560105249e1a1720c47f830c299.jpg","title":"LongCat Video"},{"category":"text-to-image","description":"Run Any Stable Diffusion model with customizable LoRA weights.","endpoint_id":"fal-ai/lora","family":"","inputs":[{"default":null,"description":"URL or HuggingFace ID of the base model to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_name","required":true,"type":"string"},{"default":null,"description":"URL or HuggingFace ID of the custom U-Net model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"unet_name","required":false,"type":"string"},{"default":null,"description":"The variant of the model to use for huggingface models, e.g. 'fp16'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"variant","required":false,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt weighting syntax will be used.\n            Additionally, this will lift the 77 token limit by averaging embeddings.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_weighting","required":false,"type":"boolean"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The embeddings to use for the image generation. Only a single embedding is supported at the moment.\n            The embeddings will be used to map the tokens in the prompt to the embedding weights.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"[]","description":"The control nets to use for the image generation. You can use any number of control nets\n            and they will be applied to the image at the specified timesteps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":false,"description":"If set to true, the controlnet will be applied to only the conditional predictions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_guess_mode","required":false,"type":"boolean"},{"default":"[]","description":"The IP adapter to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapter","required":false,"type":"json"},{"default":null,"description":"The path to the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_path","required":false,"type":"string"},{"default":null,"description":"The subfolder of the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_subfolder","required":false,"type":"string"},{"default":"pytorch_model.bin","description":"The weight name of the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_weight_name","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ic_light_model_url","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model background image to use for the image generation.\n            Make sure to use a background compatible with the model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"ic_light_model_background_image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model image to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ic_light_image_url","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square_hd","description":"The size of the generated image. You can choose between some presets or custom height and width\n            that **must be multiples of 8**.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"Increasing the amount of steps tells Stable Diffusion that it should take more steps\n            to generate your final result which can increase the amount of detail in your image.","enum":null,"is_list":false,"max":150,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0,"description":"Skips part of the image generation process, leading to slightly different results.\n            This means the image renders faster, too.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"clip_skip","required":false,"type":"integer"},{"default":null,"description":"Scheduler / sampler to use for the image denoising process.","enum":["DPM++ 2M","DPM++ 2M Karras","DPM++ 2M SDE","DPM++ 2M SDE Karras","Euler","Euler A","Euler (trailing timesteps)","LCM","LCM (trailing timesteps)","DDIM","TCD"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"{\"array\": [], \"method\": \"default\"}","description":"Optionally override the timesteps to use for the denoising process. Only works with schedulers which support the `timesteps` argument in their `set_timesteps` method.\n            Defaults to not overriding, in which case the scheduler automatically sets the timesteps based on the `num_inference_steps` parameter.\n            If set to a custom timestep schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `sigmas` is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"timesteps","required":false,"type":"json"},{"default":"{\"array\": [], \"method\": \"default\"}","description":"Optionally override the sigmas to use for the denoising process. Only works with schedulers which support the `sigmas` argument in their `set_sigmas` method.\n            Defaults to not overriding, in which case the scheduler automatically sets the sigmas based on the `num_inference_steps` parameter.\n            If set to a custom sigma schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `timesteps` is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigmas","required":false,"type":"json"},{"default":"epsilon","description":"The type of prediction to use for the image generation.\n            The `epsilon` is the default.","enum":["v_prediction","epsilon"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prediction_type","required":false,"type":"enum"},{"default":false,"description":"Whether to set the rescale_betas_snr_zero option or not for the sampler","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rescale_betas_snr_zero","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate in one request. Note that the higher the batch size,\n            the longer it will take to generate the images.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":4096,"description":"The size of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":128,"multiline":false,"name":"tile_width","required":false,"type":"integer"},{"default":4096,"description":"The size of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":128,"multiline":false,"name":"tile_height","required":false,"type":"integer"},{"default":2048,"description":"The stride of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_stride_width","required":false,"type":"integer"},{"default":2048,"description":"The stride of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_stride_height","required":false,"type":"integer"},{"default":0,"description":"The eta value to be used for the image generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"eta","required":false,"type":"number"},{"default":false,"description":"If set to true, the latents will be saved for debugging.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_latents","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the latents will be saved for debugging per pass.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_per_pass_latents","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","debug_per_pass_latents","debug_latents"],"pricing":"","published_at":"2023-09-26T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sd-loras.jpeg","title":"Stable Diffusion with LoRAs"},{"category":"image-to-image","description":"Run Any Stable Diffusion model with customizable LoRA weights.","endpoint_id":"fal-ai/lora/image-to-image","family":"","inputs":[{"default":null,"description":"URL or HuggingFace ID of the base model to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_name","required":true,"type":"string"},{"default":null,"description":"URL or HuggingFace ID of the custom U-Net model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"unet_name","required":false,"type":"string"},{"default":null,"description":"The variant of the model to use for huggingface models, e.g. 'fp16'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"variant","required":false,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt weighting syntax will be used.\n            Additionally, this will lift the 77 token limit by averaging embeddings.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_weighting","required":false,"type":"boolean"},{"default":null,"description":"URL of image to use for image to image/inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":0.5,"description":"The amount of noise to add to noise image for image. Only used if the image_url is provided. 1.0 is complete noise and values near 0 are minimal noise.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"noise_strength","required":false,"type":"number"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The embeddings to use for the image generation. Only a single embedding is supported at the moment.\n            The embeddings will be used to map the tokens in the prompt to the embedding weights.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"[]","description":"The control nets to use for the image generation. You can use any number of control nets\n            and they will be applied to the image at the specified timesteps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":false,"description":"If set to true, the controlnet will be applied to only the conditional predictions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_guess_mode","required":false,"type":"boolean"},{"default":"[]","description":"The IP adapter to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapter","required":false,"type":"json"},{"default":null,"description":"The path to the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_path","required":false,"type":"string"},{"default":null,"description":"The subfolder of the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_subfolder","required":false,"type":"string"},{"default":"pytorch_model.bin","description":"The weight name of the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_weight_name","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ic_light_model_url","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model background image to use for the image generation.\n            Make sure to use a background compatible with the model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"ic_light_model_background_image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model image to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ic_light_image_url","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"Increasing the amount of steps tells Stable Diffusion that it should take more steps\n            to generate your final result which can increase the amount of detail in your image.","enum":null,"is_list":false,"max":150,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0,"description":"Skips part of the image generation process, leading to slightly different results.\n            This means the image renders faster, too.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"clip_skip","required":false,"type":"integer"},{"default":null,"description":"Scheduler / sampler to use for the image denoising process.","enum":["DPM++ 2M","DPM++ 2M Karras","DPM++ 2M SDE","DPM++ 2M SDE Karras","Euler","Euler A","Euler (trailing timesteps)","LCM","LCM (trailing timesteps)","DDIM","TCD"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"{\"array\": [], \"method\": \"default\"}","description":"Optionally override the timesteps to use for the denoising process. Only works with schedulers which support the `timesteps` argument in their `set_timesteps` method.\n            Defaults to not overriding, in which case the scheduler automatically sets the timesteps based on the `num_inference_steps` parameter.\n            If set to a custom timestep schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `sigmas` is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"timesteps","required":false,"type":"json"},{"default":"{\"array\": [], \"method\": \"default\"}","description":"Optionally override the sigmas to use for the denoising process. Only works with schedulers which support the `sigmas` argument in their `set_sigmas` method.\n            Defaults to not overriding, in which case the scheduler automatically sets the sigmas based on the `num_inference_steps` parameter.\n            If set to a custom sigma schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `timesteps` is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigmas","required":false,"type":"json"},{"default":"epsilon","description":"The type of prediction to use for the image generation.\n            The `epsilon` is the default.","enum":["v_prediction","epsilon"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prediction_type","required":false,"type":"enum"},{"default":false,"description":"Whether to set the rescale_betas_snr_zero option or not for the sampler","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rescale_betas_snr_zero","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate in one request. Note that the higher the batch size,\n            the longer it will take to generate the images.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":4096,"description":"The size of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":128,"multiline":false,"name":"tile_width","required":false,"type":"integer"},{"default":4096,"description":"The size of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":128,"multiline":false,"name":"tile_height","required":false,"type":"integer"},{"default":2048,"description":"The stride of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_stride_width","required":false,"type":"integer"},{"default":2048,"description":"The stride of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_stride_height","required":false,"type":"integer"},{"default":0,"description":"The eta value to be used for the image generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"eta","required":false,"type":"number"},{"default":false,"description":"If set to true, the latents will be saved for debugging.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_latents","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the latents will be saved for debugging per pass.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_per_pass_latents","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","debug_per_pass_latents","debug_latents"],"pricing":"","published_at":"2024-04-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sd-loras.jpeg","title":"Stable Diffusion with LoRAs"},{"category":"image-to-image","description":"Run Any Stable Diffusion model with customizable LoRA weights.","endpoint_id":"fal-ai/lora/inpaint","family":"","inputs":[{"default":null,"description":"URL or HuggingFace ID of the base model to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_name","required":true,"type":"string"},{"default":null,"description":"URL or HuggingFace ID of the custom U-Net model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"unet_name","required":false,"type":"string"},{"default":null,"description":"The variant of the model to use for huggingface models, e.g. 'fp16'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"variant","required":false,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt weighting syntax will be used.\n            Additionally, this will lift the 77 token limit by averaging embeddings.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_weighting","required":false,"type":"boolean"},{"default":null,"description":"URL of image to use for image to image/inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"URL of black-and-white image to use as mask during inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":0.5,"description":"The amount of noise to add to noise image for image. Only used if the image_url is provided. 1.0 is complete noise and values near 0 are minimal noise.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"noise_strength","required":false,"type":"number"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"[]","description":"The embeddings to use for the image generation. Only a single embedding is supported at the moment.\n            The embeddings will be used to map the tokens in the prompt to the embedding weights.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"[]","description":"The control nets to use for the image generation. You can use any number of control nets\n            and they will be applied to the image at the specified timesteps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnets","required":false,"type":"json"},{"default":false,"description":"If set to true, the controlnet will be applied to only the conditional predictions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet_guess_mode","required":false,"type":"boolean"},{"default":"[]","description":"The IP adapter to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapter","required":false,"type":"json"},{"default":null,"description":"The path to the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_path","required":false,"type":"string"},{"default":null,"description":"The subfolder of the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_subfolder","required":false,"type":"string"},{"default":"pytorch_model.bin","description":"The weight name of the image encoder model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_encoder_weight_name","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ic_light_model_url","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model background image to use for the image generation.\n            Make sure to use a background compatible with the model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"ic_light_model_background_image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the IC Light model image to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ic_light_image_url","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"Increasing the amount of steps tells Stable Diffusion that it should take more steps\n            to generate your final result which can increase the amount of detail in your image.","enum":null,"is_list":false,"max":150,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0,"description":"Skips part of the image generation process, leading to slightly different results.\n            This means the image renders faster, too.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"clip_skip","required":false,"type":"integer"},{"default":null,"description":"Scheduler / sampler to use for the image denoising process.","enum":["DPM++ 2M","DPM++ 2M Karras","DPM++ 2M SDE","DPM++ 2M SDE Karras","Euler","Euler A","Euler (trailing timesteps)","LCM","LCM (trailing timesteps)","DDIM","TCD"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"{\"array\": [], \"method\": \"default\"}","description":"Optionally override the timesteps to use for the denoising process. Only works with schedulers which support the `timesteps` argument in their `set_timesteps` method.\n            Defaults to not overriding, in which case the scheduler automatically sets the timesteps based on the `num_inference_steps` parameter.\n            If set to a custom timestep schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `sigmas` is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"timesteps","required":false,"type":"json"},{"default":"{\"array\": [], \"method\": \"default\"}","description":"Optionally override the sigmas to use for the denoising process. Only works with schedulers which support the `sigmas` argument in their `set_sigmas` method.\n            Defaults to not overriding, in which case the scheduler automatically sets the sigmas based on the `num_inference_steps` parameter.\n            If set to a custom sigma schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `timesteps` is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sigmas","required":false,"type":"json"},{"default":"epsilon","description":"The type of prediction to use for the image generation.\n            The `epsilon` is the default.","enum":["v_prediction","epsilon"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prediction_type","required":false,"type":"enum"},{"default":false,"description":"Whether to set the rescale_betas_snr_zero option or not for the sampler","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rescale_betas_snr_zero","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate in one request. Note that the higher the batch size,\n            the longer it will take to generate the images.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":4096,"description":"The size of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":128,"multiline":false,"name":"tile_width","required":false,"type":"integer"},{"default":4096,"description":"The size of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":128,"multiline":false,"name":"tile_height","required":false,"type":"integer"},{"default":2048,"description":"The stride of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_stride_width","required":false,"type":"integer"},{"default":2048,"description":"The stride of the tiles to be used for the image generation.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":64,"multiline":false,"name":"tile_stride_height","required":false,"type":"integer"},{"default":0,"description":"The eta value to be used for the image generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"eta","required":false,"type":"number"},{"default":false,"description":"If set to true, the latents will be saved for debugging.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_latents","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the latents will be saved for debugging per pass.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_per_pass_latents","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","has_nsfw_concepts","images","debug_per_pass_latents","debug_latents"],"pricing":"","published_at":"2024-04-18T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sd-loras.jpeg","title":"Stable Diffusion with LoRAs"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2","endpoint_id":"fal-ai/ltx-2-19b/audio-to-video","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0018 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2016.","published_at":"2026-01-27T15:45:06.060000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1622/piILEBJ9YqZhIb837h1Uf_a0f40e99111e4eb4a271fdc262185bee.jpg","title":"LTX-2 19B"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2 and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/audio-to-video/lora","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.002 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.224.","published_at":"2026-01-27T15:48:53.065000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1636/onmCWQl-29GfB5lZT9WDP_c65a4309ad1e4023b6450e6daadf12e5.jpg","title":"LTX-2 19B"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2 Distilled","endpoint_id":"fal-ai/ltx-2-19b/distilled/audio-to-video","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0008 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.0896.","published_at":"2026-01-27T15:46:47.750000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c162d/9Wm-zXtwe1rQzPnRcO57x_5ec4f4b1bc7f4dd48e4f08e1271ae8a2.jpg","title":"LTX-2 19B Distilled"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/distilled/audio-to-video/lora","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.001 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.112.","published_at":"2026-01-27T15:50:42.658000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1644/1iD97rwiiAmVKyzTmnxUC_23ec1d178dcc4b43a8d19c9bbc747179.jpg","title":"LTX-2 19B Distilled"},{"category":"video-to-video","description":"Extend videos with audio using LTX-2 Distilled","endpoint_id":"fal-ai/ltx-2-19b/distilled/extend-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to extend.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the extended video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"forward","description":"Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extend_direction","required":false,"type":"enum"},{"default":25,"description":"The number of frames to use as context for the extension.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":0,"multiline":false,"name":"num_context_frames","required":false,"type":"integer"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0008 per megapixel of context frames plus generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.0896.","published_at":"2026-01-05T21:09:00.536000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a893735/sSRmRNUM6b01I-BJwDDcj_791bb2fc54584ea1a1240085da9060f5.jpg","title":"LTX-2 19B Distilled"},{"category":"video-to-video","description":"Extend videos with audio using LTX-2 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/distilled/extend-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to extend.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the extended video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":"forward","description":"Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extend_direction","required":false,"type":"enum"},{"default":25,"description":"The number of frames to use as context for the extension.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":0,"multiline":false,"name":"num_context_frames","required":false,"type":"integer"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.001 per megapixel of context frames plus generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.112.","published_at":"2026-01-05T21:12:22.324000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a893747/pnWfH_gpzQ7JkJ97o1roZ_a1b45e9a99364b168af93a34728a9464.jpg","title":"LTX-2 19B Distilled"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2 Distilled","endpoint_id":"fal-ai/ltx-2-19b/distilled/image-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0008 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.0896.","published_at":"2026-01-05T21:00:40.069000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8936e5/XvktxWU-OjPy48InEFQEs_bd9da8a5712846b694091a93ff5b1df0.jpg","title":"LTX-2 19B Distilled"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/distilled/image-to-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.001 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.112.","published_at":"2026-01-05T21:02:29.284000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8936e5/-h8aDgobm8qIgSCkOXrcN_6f4888dc7dee4cc9a61ba27199f64c9a.jpg","title":"LTX-2 19B Distilled"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2 Distilled","endpoint_id":"fal-ai/ltx-2-19b/distilled/text-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0008 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.0896.","published_at":"2026-01-05T20:55:11.318000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8936f6/lAxk4cHPDAO8Vi-zFWrYF_79d59ee30f374e16a7d2a2a2daa87e71.jpg","title":"LTX-2 19B Distilled"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/distilled/text-to-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.001 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.112.","published_at":"2026-01-05T20:56:37.306000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8936f9/MqecW0ic5_aJ01aOHjOt__da41267b8c59467bbbbaa3d80016ec07.jpg","title":"LTX-2 19B Distilled"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2 Distilled","endpoint_id":"fal-ai/ltx-2-19b/distilled/video-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"none","description":"The preprocessor to use for the video. When a preprocessor is used and `ic_lora_type` is set to `match_preprocessor`, the IC-LoRA will be loaded based on the preprocessor type.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"},{"default":"match_preprocessor","description":"The type of IC-LoRA to load. In-Context LoRA weights are used to condition the video based on edge, depth, or pose videos. Only change this from `match_preprocessor` if your videos are already preprocessed (or you are using the detailer.)","enum":["match_preprocessor","canny","depth","pose","detailer","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ic_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the IC-LoRA to use. This allows you to control the strength of the IC-LoRA.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ic_lora_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0008 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.0896.","published_at":"2026-01-07T03:38:57.274000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a896215/eDZD0zp44dBtoK1K3YPd7_258cf5dc4d47429fa90ca3d625da76cc.jpg","title":"LTX-2 19B Distilled"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/distilled/video-to-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":"none","description":"The preprocessor to use for the video. When a preprocessor is used and `ic_lora_type` is set to `match_preprocessor`, the IC-LoRA will be loaded based on the preprocessor type.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"},{"default":"match_preprocessor","description":"The type of IC-LoRA to load. In-Context LoRA weights are used to condition the video based on edge, depth, or pose videos. Only change this from `match_preprocessor` if your videos are already preprocessed (or you are using the detailer.)","enum":["match_preprocessor","canny","depth","pose","detailer","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ic_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the IC-LoRA to use. This allows you to control the strength of the IC-LoRA.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ic_lora_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.001 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.112.","published_at":"2026-01-07T03:40:29.284000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a896226/KeZEHWnM6_hr12pAHKWyQ_2ece2ad4736345abb7cbe3e0e404729d.jpg","title":"LTX-2 19B Distilled"},{"category":"video-to-video","description":"Extend video with audio using LTX-2","endpoint_id":"fal-ai/ltx-2-19b/extend-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to extend.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the extended video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"forward","description":"Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extend_direction","required":false,"type":"enum"},{"default":25,"description":"The number of frames to use as context for the extension.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":0,"multiline":false,"name":"num_context_frames","required":false,"type":"integer"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"","published_at":"2026-01-05T20:27:27.462000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a893642/HexMym-GfrSQ1RbH2DZjj_f150a074b33f45b6b95a2dc39624dd69.jpg","title":"LTX-2 19B"},{"category":"video-to-video","description":"Extend video with audio using LTX-2 and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/extend-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to extend.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the extended video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":"forward","description":"Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extend_direction","required":false,"type":"enum"},{"default":25,"description":"The number of frames to use as context for the extension.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":0,"multiline":false,"name":"num_context_frames","required":false,"type":"integer"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.002 per megapixel of context frames plus generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.224.","published_at":"2026-01-05T20:38:54.203000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a89367e/r31DU9uN4dWdHIBJvD-gC_ed11b6e0ebc649688c7ed39cb6f74b6e.jpg","title":"LTX-2 19B"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2","endpoint_id":"fal-ai/ltx-2-19b/image-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0018 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2016.","published_at":"2026-01-05T20:18:20.548000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8935fe/Ezbvf27opeW6gEoDS4nlw_da7064399f9c4342b5e118f6875ec389.jpg","title":"LTX-2 19B"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2 and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/image-to-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.002 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.224.","published_at":"2026-01-05T20:33:07.281000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a89365f/rZwl5Yceudvyc6Cd3Y_KN_eb6ff726b82948398bb475dca6cd1b9d.jpg","title":"LTX-2 19B"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2","endpoint_id":"fal-ai/ltx-2-19b/text-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0018 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2016.","published_at":"2026-01-05T20:21:49.298000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a893615/SMsOPqZ6266qmhio8-GEf_22814884373a42bcadb19dbe083d2cfe.jpg","title":"LTX-2 19B"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2 and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/text-to-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_4_3","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.002 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.224.","published_at":"2026-01-05T20:35:44.742000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8936e2/Ys99LaAscUTgLjNHdoXe9_2d41aa966d6b473c9a63abb61cb65d38.jpg","title":"LTX-2 19B"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2","endpoint_id":"fal-ai/ltx-2-19b/video-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"none","description":"The preprocessor to use for the video. When a preprocessor is used and `ic_lora_type` is set to `match_preprocessor`, the IC-LoRA will be loaded based on the preprocessor type.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"},{"default":"match_preprocessor","description":"The type of IC-LoRA to load. In-Context LoRA weights are used to condition the video based on edge, depth, or pose videos. Only change this from `match_preprocessor` if your videos are already preprocessed (or you are using the detailer.)","enum":["match_preprocessor","canny","depth","pose","detailer","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ic_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the IC-LoRA to use. This allows you to control the strength of the IC-LoRA.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ic_lora_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.0018 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2016.","published_at":"2026-01-07T03:32:57.344000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8961f3/1XEMGDaYbwvev5g0UU3DG_e6cfe8e5c1ee4472af89f76d0309eb8c.jpg","title":"LTX-2 19B"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2 and custom LoRA","endpoint_id":"fal-ai/ltx-2-19b/video-to-video/lora","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio,incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":"none","description":"The preprocessor to use for the video. When a preprocessor is used and `ic_lora_type` is set to `match_preprocessor`, the IC-LoRA will be loaded based on the preprocessor type.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"},{"default":"match_preprocessor","description":"The type of IC-LoRA to load. In-Context LoRA weights are used to condition the video based on edge, depth, or pose videos. Only change this from `match_preprocessor` if your videos are already preprocessed (or you are using the detailer.)","enum":["match_preprocessor","canny","depth","pose","detailer","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ic_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the IC-LoRA to use. This allows you to control the strength of the IC-LoRA.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ic_lora_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.002 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.224.","published_at":"2026-01-07T03:35:30.708000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a896206/sXN9s121dM9wB94qRWi55_782e4ad62c7b4df680bdc590ca736c94.jpg","title":"LTX-2 19B"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2","endpoint_id":"fal-ai/ltx-2.3-22b/audio-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001605 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.179.","published_at":"2026-04-14T21:34:51.240000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a921323/45pdd5xpCCM553MqtszME_d527a44501b14ac1b02a23ffe9ba6898.jpg","title":"LTX-2.3 22B"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/audio-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001805 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2013","published_at":"2026-04-14T21:33:59.520000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d0/e9YEqZvZOVchNPjjZxDKH__tmp_b094-velv-prism.jpg","title":"LTX-2.3 22B"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2 Distilled","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/audio-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001205 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1344.","published_at":"2026-04-14T21:40:15.488000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a921379/PSJsS-py9Xj61wt0olw0L_5ac0e2534f9d42f8b17ba6ac1d932ef2.jpg","title":"LTX-2.3 22B Distilled"},{"category":"audio-to-video","description":"Generate video with audio from audio, text and images using LTX-2.3 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/audio-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video. Use 'auto' to match the input image dimensions if provided.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the audio before using it as conditioning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001405 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1567.","published_at":"2026-04-14T21:41:19.575000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d0/g70rVpbtPifTT-59jRJHi__tmp_music-generation.jpg","title":"LTX-2.3 22B Distilled"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2.3 Distilled","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/image-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001205 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1344.","published_at":"2026-04-14T21:40:04.601000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289cb/yE3z6Q_sJBywhLxYsyNnB__tmp_b047-ice--phoenix.jpg","title":"LTX-2.3 22B Distilled"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2.3 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/image-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001405 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1567.","published_at":"2026-04-14T21:41:05.964000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289ce/20zCxq0nC6akyUyph0bID__tmp_b066-silk-cactus-bloom.jpg","title":"LTX-2.3 22B Distilled"},{"category":"video-to-video","description":"Generate video with audio from reference videos using LTX-2.3 Distilled","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/reference-video-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":"none","description":"The preprocessor to use for the generation.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"},{"default":"union","description":"The IC LoRA type to use for the generation.","enum":["match_preprocessor","union","detailer","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ic_lora_type","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001205 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1344.","published_at":"2026-04-14T21:57:09.934000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a96459c/BB9kNn7VmClukweOXpb1s_113a491ad3a84d529fdcfa276540b253.jpg","title":"LTX-2.3 22B Distilled"},{"category":"video-to-video","description":"Generate video with audio from reference videos using LTX-2.3 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/reference-video-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":"none","description":"The preprocessor to use for the generation.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"},{"default":"union","description":"The IC LoRA type to use for the generation.","enum":["match_preprocessor","union","detailer","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ic_lora_type","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001405 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1567.","published_at":"2026-04-14T21:59:15.691000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9645a4/fNXUGpQSf_aEEqHrJSW4N_ab8750f39fb24e26852f9d5b42f58584.jpg","title":"LTX-2.3 22B Distilled"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2.3 Distilled","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/text-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001205 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1344.","published_at":"2026-04-14T21:39:49.554000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289be/bEbjXj3FMaublu4e4WsLD__tmp_b006-ice--samurai-helm.jpg","title":"LTX-2.3 22B Distilled"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2.3 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/text-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001405 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1567.","published_at":"2026-04-14T21:40:50.336000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289c8/LTuVAXvjFXgOAPWrKCFCL__tmp_b028-gold-jellyfish.jpg","title":"LTX-2.3 22B Distilled"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2.3 Distilled","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/video-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":0.01,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":0.01,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001205 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1344.","published_at":"2026-04-14T21:40:33.888000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d4/3iFG-lvPKSRI16ykm2PEA__tmp_training-v2.jpg","title":"LTX-2.3 22B Distilled"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2.3 Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/distilled/video-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":0.01,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":0.01,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001405 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.1567.","published_at":"2026-04-14T21:41:39.207000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d6/7PgL8G-qF1wBtCxRyz6eD__tmp_v3-frost-butterfly.jpg","title":"LTX-2.3 22B Distilled"},{"category":"video-to-video","description":"Extend video with audio using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-22b/extend-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to extend.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the extended video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":"forward","description":"Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extend_direction","required":false,"type":"enum"},{"default":25,"description":"The number of frames to use as context for the extension.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":0,"multiline":false,"name":"num_context_frames","required":false,"type":"integer"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001605 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.179.","published_at":"2026-04-14T21:45:35.478000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d7/UPJhpRXw48uHO-Ykk7Ina_v3-wire-dragon.png","title":"LTX-2.3 22B"},{"category":"video-to-video","description":"Extend video with audio using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/extend-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to extend.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the extended video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":"forward","description":"Direction to extend the video. 'forward' extends from the end of the video, 'backward' extends from the beginning.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"extend_direction","required":false,"type":"enum"},{"default":25,"description":"The number of frames to use as context for the extension.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":0,"multiline":false,"name":"num_context_frames","required":false,"type":"integer"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001805 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2013","published_at":"2026-04-14T21:46:39.588000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d9/0iFpMxqck_JKrwb8rWAC4__tmp_v4-whale-mint.jpg","title":"LTX-2.3 22B"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-22b/image-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001605 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.179.","published_at":"2026-04-14T21:34:34.101000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289c9/kEEMVVpXrSdQAUe8zVqbg__tmp_b046-liqu-phoenix.jpg","title":"LTX-2.3 22B"},{"category":"image-to-video","description":"Generate video with audio from images using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/image-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt used for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":"forward","description":"The direction to interpolate the image sequence in. 'Forward' goes from the start image to the end image, 'Backward' goes from the end image to the start image.","enum":["forward","backward"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolation_direction","required":false,"type":"enum"},{"default":1,"description":"The strength of the image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"The strength of the end image to use for the video generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"end_image_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001805 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2013","published_at":"2026-04-14T21:35:37.444000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289ce/XPxxPt7YTRFqdahRCUEa1__tmp_b057-chro-origami-cran.jpg","title":"LTX-2.3 22B"},{"category":"video-to-video","description":"Generate video with audio from reference video, text and images using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-22b/reference-video-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"},{"default":"none","description":"The preprocessor to use for the generation.","enum":["depth","canny","pose","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocessor","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001605 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.179.","published_at":"2026-04-14T21:51:07.849000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a96456f/JbntZrZ_sQXFMjtflnhry_d049da50946f41bcb302947f48d5271f.jpg","title":"LTX-2.3 22B"},{"category":"video-to-video","description":"Generate video with audio from reference video, text and images using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/reference-video-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":null,"description":"An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"An optional URL of an image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the end of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":1,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001805 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2013","published_at":"2026-04-14T21:53:07.442000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a96457d/oZRIC5thIPeDo1WVUr0mK_27a0177b479b4a5a9e78b409f5780c7c.jpg","title":"LTX 2.3 22B"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-22b/text-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001605 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.179.","published_at":"2026-04-14T21:34:24.413000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289be/SGtOOBIRqFPtmKPSmoNzE__tmp_avatar-v2.jpg","title":"LTX-2.3 22B"},{"category":"text-to-video","description":"Generate video with audio from text using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/text-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001805 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2013","published_at":"2026-04-14T21:35:12.608000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289c7/bS0a9Lmjo40XfRJfTOEOX__tmp_b008-gold-spiral-stair.jpg","title":"LTX-2.3 22B"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-22b/video-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":0.01,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":0.01,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001605 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.179.","published_at":"2026-04-14T21:35:01.860000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d1/8br7G9kBdCk9AMgYu5U6R__tmp_music-v2.jpg","title":"LTX-2.3 22B"},{"category":"video-to-video","description":"Generate video with audio from videos using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-22b/video-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":true,"description":"When enabled, the number of frames will be calculated based on the video duration and FPS. When disabled, use the specified num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_video_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_size","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":true,"description":"Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_multiscale","required":false,"type":"boolean"},{"default":true,"description":"When true, match the output FPS to the input video's FPS instead of using the default target FPS.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_fps","required":false,"type":"boolean"},{"default":24,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to use.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"video_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"video_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the video. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"video_modality_scale","required":false,"type":"number"},{"default":7,"description":"The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"audio_cfg_scale","required":false,"type":"number"},{"default":0,"description":"The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"audio_stg_scale","required":false,"type":"number"},{"default":0.7,"description":"The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_rescaling_scale","required":false,"type":"number"},{"default":3,"description":"The modality scale for the audio. Controls the ratio between video and audio modalities.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"audio_modality_scale","required":false,"type":"number"},{"default":2,"description":"The gamma of gradient estimation during denoising. Set to 0 to disable.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"gradient_estimation_gamma","required":false,"type":"number"},{"default":false,"description":"Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_restart_sampling","required":false,"type":"boolean"},{"default":"ltx2","description":"The scheduler to use.","enum":["ltx2","linear_quadratic","beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"none","description":"The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":["dolly_in","dolly_out","dolly_left","dolly_right","jib_up","jib_down","static","none"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_lora","required":false,"type":"enum"},{"default":1,"description":"The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"camera_lora_scale","required":false,"type":"number"},{"default":"news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"The LoRAs to use for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"},{"default":0.2,"description":"The scale of the distill LoRA to use for the first pass. Set to 0 to disable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_first_pass_scale","required":false,"type":"number"},{"default":0.5,"description":"The scale of the distill LoRA to use for the second and subsequent passes.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"distill_lora_second_pass_scale","required":false,"type":"number"},{"default":0.01,"description":"Video conditioning strength. Lower values represent more freedom given to the model to change the video content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":0.01,"description":"Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"audio_strength","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["seed","prompt","video"],"pricing":"Your request will cost $0.001805 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2013","published_at":"2026-04-14T21:35:59.520000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9289d5/EYhMz3JWP3LoS_xksorP7__tmp_v3-amber-fox.jpg","title":"LTX-2.3 22B"},{"category":"audio-to-video","description":"Generate high-quality video with audio from audio, text and images using LTX-2","endpoint_id":"fal-ai/ltx-2.3-quality/audio-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the audio-driven video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio track that drives generation.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame. When omitted, generation runs from text and audio only.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, derives the number of frames from the audio duration and frames_per_second. When disabled, uses num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"Final output size. 'auto' matches the input image aspect ratio when image_url is provided; otherwise it uses a landscape fallback.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":0.7,"description":"Conditioning strength for the optional first frame. 1.0 keeps the image more strictly; lower values give the model more freedom.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-01T22:48:48.610000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c98bb/iw0BzMm847Vjzh0MWLarh_25gBsW6V.png","title":"Ltx 2.3 Quality"},{"category":"audio-to-video","description":"Generate high-quality video with audio from audio, text and images using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-quality/audio-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the audio-driven video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the audio track that drives generation.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the first frame. When omitted, generation runs from text and audio only.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":true,"description":"When enabled, derives the number of frames from the audio duration and frames_per_second. When disabled, uses num_frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_audio_length","required":false,"type":"boolean"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"Final output size. 'auto' matches the input image aspect ratio when image_url is provided; otherwise it uses a landscape fallback.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":0.7,"description":"Conditioning strength for the optional first frame. 1.0 keeps the image more strictly; lower values give the model more freedom.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0027075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.3032.","published_at":"2026-06-01T22:48:58.267000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c991b/QHVV6y5vXz0ol1UvSoUe5_rBEl8ZKG.png","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Colorize high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/colorization","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"","published_at":"2026-06-25T18:02:09.611000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa3f3/Cg3WNa26ZICfMgTvAmz-v.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Cross-eyes for high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/cross-eyed","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-25T18:02:50.230000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa7a6/vn85nQwU5m2Efmi2_41Kw.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Day to Night for high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/day-to-night","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-25T18:01:51.789000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa74f/dl2bSo_PCRgWzfKFWD08E.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Deblur high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/deblur","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-25T18:02:17.431000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa3d4/tCnFuQo2tIi9p4jnrzk6j.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Decompression / Denoise high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/decompression","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-25T18:02:27.440000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa693/2CjsYdbNrOdsSfcy-N9yE.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Generate HDR from reference video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/hdr","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"SDR input video to lift into HDR. This mode is video-conditioned.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"Output video size. The output is generated at up to ~720p (shorter side capped at 704px); larger requested sizes are scaled down, preserving the aspect ratio.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"json","output_props":["prompt","preview_video","seed","exr_frames_url"],"pricing":"Your request will cost $0.0027075 per megapixel of generated HDR video data (width × height × frames), rounded up. For example, if you generate 121 HDR frames at 1280 × 720, your total generated output is ≈112 MP, and your request will cost $0.3032.","published_at":"2026-06-01T22:49:25.618000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c9a11/ErBSalpW_8n6_kZj5l9-u_wUkBp49e.png","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Generate HDR from reference video using LTX-2.3 with lora","endpoint_id":"fal-ai/ltx-2.3-quality/hdr/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"SDR input video to lift into HDR. This mode is video-conditioned.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"Output video size. The output is generated at up to ~720p (shorter side capped at 704px); larger requested sizes are scaled down, preserving the aspect ratio.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"json","output_props":["prompt","preview_video","seed","exr_frames_url"],"pricing":"Your request will cost $0.0027075 per megapixel of generated HDR video data (width × height × frames), rounded up. For example, if you generate 121 HDR frames at 1280 × 720, your total generated output is ≈112 MP, and your request will cost $0.3032.","published_at":"2026-06-01T22:49:33.255000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c9a63/lXjppuL8GdWW8jNbNSg8M_Pxc8jj0s.png","title":"Ltx 2.3 Quality"},{"category":"image-to-video","description":"Generate high-quality video with audio from images using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/image-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the starting image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video. 'auto' derives the size from the input image aspect ratio.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":0.7,"description":"Conditioning strength on the start image. 1.0 = exact first-frame match, lower = more freedom for the model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-01T22:48:27.341000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c9802/Lr5CPJbKI-NAWD3pktc1N_pI2mH3QO.png","title":"Ltx 2.3 Quality"},{"category":"image-to-video","description":"Generate high-quality video with audio from images using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-quality/image-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the starting image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video. 'auto' derives the size from the input image aspect ratio.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":0.7,"description":"Conditioning strength on the start image. 1.0 = exact first-frame match, lower = more freedom for the model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0027075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.302.","published_at":"2026-06-01T22:48:37.629000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c981b/fVP1qFZOIhu1Ax7KwLjxm_SoTIpz7e.png","title":"Ltx 2.3 Quality"},{"category":"image-to-video","description":"Generate high-quality video with audio from reference, character sheet, storyboard using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/ingredient","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the generated video. For best results, use a 'Reference sheet: ... Generated video: ...' structure.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the Ingredient reference sheet image. The sheet should contain clean panels for the characters, props, and location to preserve.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":{"height":896,"width":1536},"description":"The final generated video size. The default keeps the workflow's first stage at the Ingredient LoRA's trained 768x448 bucket before the official 2x refinement stage.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"Strength of the built-in Ingredient IC-LoRA. Higher values make the reference sheet identities and props more dominant.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"ingredient_strength","required":false,"type":"number"},{"default":1,"description":"Strength of the reference-sheet guide. 1.0 uses the sheet fully; lower values give the model more freedom.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"reference_strength","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-18T23:42:05.784000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ed9c6/wZu25U8DGi5RA-AFBsH-T_25fea6b72edc4b6ba45e1fea25be1bfc.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Inpaint high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/inpaint","family":"","inputs":[{"default":null,"description":"The prompt describing what to generate inside the masked area.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The source video to inpaint.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The mask video. White regions are regenerated; black regions are preserved from the source video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":true,"type":"string"},{"default":1,"description":"Strength of the IC-LoRA video guide for the preserved content. Higher values keep the source video structure more strongly.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"","published_at":"2026-06-18T01:40:20.736000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ecd3d/7azLYGxLaKMGc-hFuaNi-_16b4824b15554f9ab8604903510749a4.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Inpaint high-quality video using LTX-2.3  with lora","endpoint_id":"fal-ai/ltx-2.3-quality/inpaint/lora","family":"","inputs":[{"default":null,"description":"The prompt describing what to generate inside the masked area.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The source video to inpaint.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The mask video. White regions are regenerated; black regions are preserved from the source video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":true,"type":"string"},{"default":1,"description":"Strength of the IC-LoRA video guide for the preserved content. Higher values keep the source video structure more strongly.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"fal-ai/ltx23-trainer-v2/inpaint\nfal-ai/ltx23-v2v-trainer","published_at":"2026-06-18T01:41:53.088000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ecd4a/_9B6UHpnrRWs0ijqa8Cp1_b8054c8f97ce4b84891977ed5c394967.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Instant shave high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/instant-shave","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-25T18:02:36.474000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa6bb/H2DK0pEnSoWtsuLcm_sKP.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Outpaint high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/outpaint","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the outpainted video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The source video to spatially outpaint.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"16:9","description":"Target aspect ratio for the outpainted video. Choose a different ratio than the input video to extend the frame cleanly, e.g. use 16:9 for a 4:3 source.","enum":["21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Output resolution tier. 480p is faster, 720p is the default balance, and 1080p gives a larger canvas when it fits LTX limits.","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_resolution","required":false,"type":"enum"},{"default":"landscape_16_9","description":"Legacy exact target canvas size. For new requests, prefer aspect_ratio with output_resolution; this field remains supported for backwards compatibility.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Scale of the source video inside the target canvas before outpainting. 1.0 uses the largest source size that fits the target canvas, which is recommended for true aspect-ratio outpainting such as 4:3 to 16:9. Lower values create a zoom-out border around the source and are less stable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.25,"multiline":false,"name":"source_scale","required":false,"type":"number"},{"default":1,"description":"Strength of the IC-LoRA video guide for the original content. Higher values preserve the source video more strongly inside the outpainted canvas.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2696.","published_at":"2026-06-17T17:40:41.761000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaf59/OmtjAfmMWhouM6JNovMO7_cea2ece127db4b23a66417deafa19538.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Outpaint high-quality video using LTX-2.3 with Lora","endpoint_id":"fal-ai/ltx-2.3-quality/outpaint/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide the outpainted video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The source video to spatially outpaint.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"16:9","description":"Target aspect ratio for the outpainted video. Choose a different ratio than the input video to extend the frame cleanly, e.g. use 16:9 for a 4:3 source.","enum":["21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Output resolution tier. 480p is faster, 720p is the default balance, and 1080p gives a larger canvas when it fits LTX limits.","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_resolution","required":false,"type":"enum"},{"default":"landscape_16_9","description":"Legacy exact target canvas size. For new requests, prefer aspect_ratio with output_resolution; this field remains supported for backwards compatibility.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"Scale of the source video inside the target canvas before outpainting. 1.0 uses the largest source size that fits the target canvas, which is recommended for true aspect-ratio outpainting such as 4:3 to 16:9. Lower values create a zoom-out border around the source and are less stable.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.25,"multiline":false,"name":"source_scale","required":false,"type":"number"},{"default":1,"description":"Strength of the IC-LoRA video guide for the original content. Higher values preserve the source video more strongly inside the outpainted canvas.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2696.","published_at":"2026-06-17T17:41:18.309000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaf5e/dWBkwKW8Uew4hwC5hQxqs_9c473ec1bfc042849129234bdda95d5c.jpg","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Generate high-quality video with audio from reference video, text and images using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/reference-video-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the reference video that supplies motion/structure.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional pre-computed control video (e.g. an already-rendered depth / edge / pose composite). When provided together with skip_control_preprocess, the built-in control estimation is skipped and this video is used directly as the control signal, resampled to the output resolution and frame count.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"control_video_url","required":false,"type":"string"},{"default":false,"description":"Skip the built-in control estimation (depth / edge / pose) and use control_video_url directly as the control signal. Requires control_video_url; ignored if it is not set. With resolution='auto', the output follows the source video size/aspect up to the LTX limits. Explicit resolutions are honored and 64-aligned so the RGB video and control video stay matched.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"skip_control_preprocess","required":false,"type":"boolean"},{"default":false,"description":"True video-to-video: the base video_url is used as the generation's starting point, while control_video_url still drives the structure. The amount of the original preserved is controlled by `strength` (denoise): lower `strength` keeps more of the original video's pixels. Requires skip_control_preprocess, video_url and control_video_url. Default off leaves the standard control path unchanged.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_original_video","required":false,"type":"boolean"},{"default":null,"description":"Optional reference image for style/character anchoring. This is the FIRST-frame keyframe.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Optional middle-frame keyframe image. When set, the look/appearance is anchored to this image around the middle of the clip (in addition to image_url at the start), so the appearance follows a moving camera instead of drifting. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mid_image_url","required":false,"type":"string"},{"default":null,"description":"Optional last-frame keyframe image. When set, the look/appearance is anchored to this image at the end of the clip. Useful for shots where the camera travels to a different place than the start image. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":0.6,"description":"Video conditioning strength. Lower values give the model more freedom to change the reference video motion/structure.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Sampler denoise strength for reference-video-to-video. With preserve_original_video on, this is the video-to-video amount: lower values keep more of the original video's pixels (e.g. 0.5 = keep ~50%), 1.0 fully regenerates. Without preserve_original_video it only trims the denoise schedule.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":121,"description":"The number of output frames to generate. This IC-LoRA endpoint caps the resolution x frames volume for stability (~150 frames at 720p-class; more at smaller sizes). A request above the budget returns a 422 — reduce num_frames or use a smaller resolution.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video. In direct-control mode (skip_control_preprocess with control_video_url), 'auto' follows the source video size/aspect up to the LTX limits and explicit sizes are honored with 64px alignment. In the built-in control estimation mode, the output stays near the official control workflow size. Higher resolutions reduce the maximum stable frame count; lower resolutions can run longer.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-01T22:49:07.670000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c9964/lp3BAfWrXQndCiRNCd6n__2Pt87jXS.png","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Generate high-quality video with audio from reference video, text and images using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-quality/reference-video-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to guide generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the reference video that supplies motion/structure.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional pre-computed control video (e.g. an already-rendered depth / edge / pose composite). When provided together with skip_control_preprocess, the built-in control estimation is skipped and this video is used directly as the control signal, resampled to the output resolution and frame count.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"control_video_url","required":false,"type":"string"},{"default":false,"description":"Skip the built-in control estimation (depth / edge / pose) and use control_video_url directly as the control signal. Requires control_video_url; ignored if it is not set. With resolution='auto', the output follows the source video size/aspect up to the LTX limits. Explicit resolutions are honored and 64-aligned so the RGB video and control video stay matched.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"skip_control_preprocess","required":false,"type":"boolean"},{"default":false,"description":"True video-to-video: the base video_url is used as the generation's starting point, while control_video_url still drives the structure. The amount of the original preserved is controlled by `strength` (denoise): lower `strength` keeps more of the original video's pixels. Requires skip_control_preprocess, video_url and control_video_url. Default off leaves the standard control path unchanged.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_original_video","required":false,"type":"boolean"},{"default":null,"description":"Optional reference image for style/character anchoring. This is the FIRST-frame keyframe.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Optional middle-frame keyframe image. When set, the look/appearance is anchored to this image around the middle of the clip (in addition to image_url at the start), so the appearance follows a moving camera instead of drifting. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mid_image_url","required":false,"type":"string"},{"default":null,"description":"Optional last-frame keyframe image. When set, the look/appearance is anchored to this image at the end of the clip. Useful for shots where the camera travels to a different place than the start image. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":0.6,"description":"Video conditioning strength. Lower values give the model more freedom to change the reference video motion/structure.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"video_strength","required":false,"type":"number"},{"default":1,"description":"Sampler denoise strength for reference-video-to-video. With preserve_original_video on, this is the video-to-video amount: lower values keep more of the original video's pixels (e.g. 0.5 = keep ~50%), 1.0 fully regenerates. Without preserve_original_video it only trims the denoise schedule.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":121,"description":"The number of output frames to generate. This IC-LoRA endpoint caps the resolution x frames volume for stability (~150 frames at 720p-class; more at smaller sizes). A request above the budget returns a 422 — reduce num_frames or use a smaller resolution.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"auto","description":"The size of the generated video. In direct-control mode (skip_control_preprocess with control_video_url), 'auto' follows the source video size/aspect up to the LTX limits and explicit sizes are honored with 64px alignment. In the built-in control estimation mode, the output stays near the official control workflow size. Higher resolutions reduce the maximum stable frame count; lower resolutions can run longer.","enum":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0027075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.3032.","published_at":"2026-06-01T22:49:17.670000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c9984/CzONodvUuO0rg1PBNvfSd_H2yl3Ij7.png","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Transform your 3D video render into realistic using first frame with Ltx 2.3","endpoint_id":"fal-ai/ltx-2.3-quality/render-to-real","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the 3D / CG / game render to make photorealistic.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional reference image used as the FIRST frame (image-to-video anchor), matching how the adapter was trained. It defines the photoreal look of frame 0; leave empty to let the render alone drive the result.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":"light","description":"How hard to push the render toward photorealism. 'light' keeps more of the source render's look and motion; 'strong' transforms more aggressively for a more photoreal result.","enum":["light","strong"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"intensity","required":false,"type":"enum"},{"default":"3DREAL. ","description":"The text prompt, pre-filled with the `3DREAL` trigger the adapter activates on. Describe the photorealistic result after it. The `3DREAL` trigger is always kept, even if you clear it or enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"When enabled, an AI model expands your prompt into a richer description before generation (off by default sends it as written). The `3DREAL` trigger is always kept, and the final prompt used is returned in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-26T14:53:41.410000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fdb29/iPbd8mqyEuUWSezRYmUgX.jpg","title":"Ltx 2.3 Quality"},{"category":"text-to-audio","description":"Text to Audio high-quality using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/text-to-audio","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the audio from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The audio duration expressed in LTX video-frame units. Duration is approximately num_frames / frames_per_second seconds.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frame rate used to derive the generated audio duration.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"pc game, console game, video game, cartoon, childish, ugly","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"audio","output_props":["prompt","seed","audio"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2696.","published_at":"2026-06-17T17:41:32.919000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaf7b/b3AHWqZkYMNyLjgshA2Mb_ed45e01aaf39498d9ad67b6a0eb2b33a.jpg","title":"Ltx 2.3 Quality"},{"category":"text-to-audio","description":"Text to Audio high-quality using LTX-2.3 with Lora","endpoint_id":"fal-ai/ltx-2.3-quality/text-to-audio/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the audio from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The audio duration expressed in LTX video-frame units. Duration is approximately num_frames / frames_per_second seconds.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frame rate used to derive the generated audio duration.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"pc game, console game, video game, cartoon, childish, ugly","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"audio","output_props":["prompt","seed","audio"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.2696.","published_at":"2026-06-17T17:41:47.573000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaf88/s513a8YQnd33PkvneTe47_679391ac8fea4892ba2207c49e14b2e1.jpg","title":"Ltx 2.3 Quality"},{"category":"text-to-video","description":"Generate high-quality video with audio from text using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/text-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-01T22:47:56.331000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c9702/fmggLmMmNhdfHCd7l0GpE_QYCC91lB.png","title":"Ltx 2.3 Quality"},{"category":"text-to-video","description":"Generate high-quality video with audio from text using LTX-2.3 and custom LoRA","endpoint_id":"fal-ai/ltx-2.3-quality/text-to-video/lora","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":121,"description":"The number of frames to generate.","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":"landscape_16_9","description":"The size of the generated video.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0027075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.302.","published_at":"2026-06-01T22:48:15.302000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c97d0/Ugq7VhuIclyL9jD0leufj_7lKpu3AH.png","title":"Ltx 2.3 Quality"},{"category":"video-to-video","description":"Water Simulation transformation for high-quality video using LTX-2.3","endpoint_id":"fal-ai/ltx-2.3-quality/water-simulation","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the source video to transform.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Optional short description of the video's content/scene. It is woven into the effect's trained caption to sharpen the result; leave empty to apply the effect with a generic description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"720p","description":"Output resolution (short side), preserving the source aspect ratio. The IC-LoRA control path caps the resolution x frames volume, so resolution trades against duration: 720p allows up to ~6s (sharper), 480p up to ~15s (softer but longer). A request above the budget is rejected with a clear error — pick 480p for longer clips. Output duration is num_frames / frames_per_second.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":121,"description":"The number of output frames. Output duration is num_frames / frames_per_second. The IC-LoRA control budget caps the resolution x frames volume: roughly 6s at 720p or 15s at 480p; a request above it returns a 422 (lower num_frames, or use 480p).","enum":null,"is_list":false,"max":481,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"},{"default":15,"description":"Number of inference steps. Defaults to 15 and can be increased up to 30.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":8,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. The default is tuned for fast, high-quality generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":"color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards","description":"The negative prompt to steer generation away from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"high","description":"The quality preset of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.0024075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.270.","published_at":"2026-06-25T18:02:00.405000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9fa6fd/IUPB4cLMJIDFnL4Gw7Ch_.jpg","title":"Ltx 2.3 Quality"},{"category":"audio-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/audio-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"URL of the audio file to generate a video from. Duration must be between 2 and 20 seconds. Must be publicly accessible or base64 data URI.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"URL of an image to use as the first frame of the video. If not provided, prompt is required.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Text description of how the video should be generated. Required if image_url is not provided. When image_url is provided, this describes how the image should be animated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Guidance scale for video generation. Higher values make the output more closely follow the prompt. Defaults to 5 for text-to-video, or 9 when providing an image.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"auto","description":"The aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image, or defaults to 16:9 if no image is provided.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per second.","published_at":"2026-03-05T15:26:32.464000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90debe/26j0CwrEx9xIO_CP98Tu__7ba855e94024463d96bde24c0e09f48e.jpg","title":"LTX 2.3 Video Pro"},{"category":"video-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/extend-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the video to extend","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Description of what should happen in the extended portion of the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":5,"description":"Duration in seconds to extend the video. Minimum 2 seconds, maximum 20 seconds.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":2,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":"end","description":"Where to extend the video: 'end' extends at the end, 'start' extends at the beginning.","enum":["start","end"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Number of seconds from the input video to use as context for the extension (minimum 1 second, maximum 20 seconds). If not provided, defaults to maximize available context within the 505 frame limit.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"context","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per second.","published_at":"2026-03-05T15:25:00.377000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90df98/94vlBeSzUCH4iQ2ZLYjPn_f1cc45dc9b69411e8c7271b4df43798f.jpg","title":"LTX Video 2.3 Pro"},{"category":"image-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/image-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the start image to use for the generated video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the end image to use for the generated video. When provided, generates a transition video between start and end frames.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"The prompt to use for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds","enum":[6,8,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[24,25,48,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.08 per second for 1080p, $0.16 per second for 1440p or $0.32 per second for 2160p.","published_at":"2026-03-05T15:31:20.809000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90ded1/KHsHxOVl1jWRMKZRuGWOz_391501da7abf4cbda1dd04894882d967.jpg","title":"LTX 2.3 Video Pro"},{"category":"image-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/image-to-video/fast","family":"LTX 2.3","inputs":[{"default":null,"description":"URL of the image to generate the video from. Must be publicly accessible or base64 data URI. Supports PNG, JPEG, WebP, AVIF, and HEIF formats.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the end image to use for the generated video. When provided, generates a transition video between start and end frames.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"The prompt to generate the video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds. The fast model supports 6-20 seconds. Note: Durations longer than 10 seconds (12, 14, 16, 18, 20) are only supported with 25 FPS and 1080p resolution.","enum":[6,8,10,12,14,16,18,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[24,25,48,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.06 per second for 1080p, $0.12 per second for 1440p or $0.24 per second for 2160p.","published_at":"2026-03-05T15:34:01.598000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90deec/VLgiT5pFEJA28BXrrulvj_7d7b24f447f945ffab1acb33ae27d9b9.jpg","title":"LTX 2.3 Video Fast"},{"category":"video-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/retake-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The URL of the video to retake","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The prompt to retake the video with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0,"description":"The start time of the video to retake in seconds","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"start_time","required":false,"type":"number"},{"default":5,"description":"The duration of the video to retake in seconds","enum":null,"is_list":false,"max":20,"media_kind":null,"min":2,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":"replace_audio_and_video","description":"The retake mode to use for the retake","enum":["replace_audio","replace_video","replace_audio_and_video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"retake_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per second.","published_at":"2026-03-05T15:28:12.564000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90dfa3/n0x-itbsnTjyU1PO9Nvih_9d720bc367dd4121bea3d31100f1aecf.jpg","title":"LTX Video 2.3 Pro"},{"category":"text-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/text-to-video","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to use for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds","enum":[6,8,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[24,25,48,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.08 per second for 1080p, $0.16 per second for 1440p or $0.32 per second for 2160p.","published_at":"2026-03-05T15:30:04.535000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90def0/4BRBakcGh2ZvP4Nw02RJl_aec88be7e2714348b2195104cff18dfd.jpg","title":"LTX Video 2.3 Pro"},{"category":"text-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","endpoint_id":"fal-ai/ltx-2.3/text-to-video/fast","family":"LTX 2.3","inputs":[{"default":null,"description":"The prompt to use for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds. The fast model supports 6-20 seconds. Note: Durations longer than 10 seconds (12, 14, 16, 18, 20) are only supported with 25 FPS and 1080p resolution.","enum":[6,8,10,12,14,16,18,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[24,25,48,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.06 per second for 1080p, $0.12 per second for 1440p or $0.24 per second for 2160p.","published_at":"2026-03-05T15:32:51.533000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90df05/Q8IcsF5FX1zYHwG048tqT_320cb845b0c74f44920f1c6520981b9e.jpg","title":"LTX 2.3 Video Fast"},{"category":"audio-to-video","description":"Generate video from audio using LTX-2","endpoint_id":"fal-ai/ltx-2/audio-to-video","family":"LTX 2","inputs":[{"default":null,"description":"URL of the audio file to generate a video from. Duration must be between 2 and 20 seconds. Must be publicly accessible or base64 data URI.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"URL of an image to use as the first frame of the video. If not provided, prompt is required.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Text description of how the video should be generated. Required if image_url is not provided. When image_url is provided, this describes how the image should be animated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Guidance scale for video generation. Higher values make the output more closely follow the prompt. Defaults to 5 for text-to-video, or 9 when providing an image.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per second.","published_at":"2026-03-04T23:02:23.893000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90dea8/bjIvfa3q5tupcSgdri-GR_3c638e8689f04fe58646aeec7db0aa80.jpg","title":"LTX 2.0 Video Pro"},{"category":"video-to-video","description":"Extends videos with audio using LTX-2","endpoint_id":"fal-ai/ltx-2/extend-video","family":"LTX 2","inputs":[{"default":null,"description":"The URL of the video to extend","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Description of what should happen in the extended portion of the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":5,"description":"Duration in seconds to extend the video. Minimum 2 seconds, maximum 20 seconds.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":2,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":"end","description":"Where to extend the video: 'end' extends at the end, 'start' extends at the beginning.","enum":["start","end"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Number of seconds from the input video to use as context for the extension (minimum 1 second, maximum 20 seconds). If not provided, defaults to maximize available context within the 505 frame limit.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"context","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per second.","published_at":"2026-03-04T23:10:17.828000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90df92/myer8zBUqSOtJSsywID1B_8c289b5d19bd483ea158dd708b1c6f32.jpg","title":"LTX Video 2.0 Pro"},{"category":"image-to-video","description":"Create high-fidelity video with audio from images with LTX-2 Pro","endpoint_id":"fal-ai/ltx-2/image-to-video","family":"LTX 2","inputs":[{"default":null,"description":"URL of the image to generate the video from. Must be publicly accessible or base64 data URI. Supports PNG, JPEG, WebP, AVIF, and HEIF formats.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to generate the video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds","enum":[6,8,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[25,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.06 per second for 1080p, $0.12 per second for 1440p or $0.24 per second for 2160p.","published_at":"2025-11-26T17:25:50.149000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/wwf0gbfywaeym-Zh4SMcg_5d51eb236a484230afff239319c70234.jpg","title":"LTX Video 2.0 Pro"},{"category":"image-to-video","description":"Create high-fidelity video with audio from images with LTX-2 Fast","endpoint_id":"fal-ai/ltx-2/image-to-video/fast","family":"LTX 2","inputs":[{"default":null,"description":"URL of the image to generate the video from. Must be publicly accessible or base64 data URI. Supports PNG, JPEG, WebP, AVIF, and HEIF formats.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to generate the video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds. The fast model supports 6-20 seconds. Note: Durations longer than 10 seconds (12, 14, 16, 18, 20) are only supported with 25 FPS and 1080p resolution.","enum":[6,8,10,12,14,16,18,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[25,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.04 per second for 1080p, $0.08 per second for 1440p or $0.16 per second for 2160p.","published_at":"2025-11-26T17:28:12.015000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/WmwWdXjeVdd34i5AevK5B_cf7f489dec6f4b378e057bc4d34ac0b9.jpg","title":"LTX Video 2.0 Fast"},{"category":"video-to-video","description":"Change sections of a video using LTX-2","endpoint_id":"fal-ai/ltx-2/retake-video","family":"LTX 2","inputs":[{"default":null,"description":"The URL of the video to retake","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The prompt to retake the video with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0,"description":"The start time of the video to retake in seconds","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"start_time","required":false,"type":"number"},{"default":5,"description":"The duration of the video to retake in seconds","enum":null,"is_list":false,"max":20,"media_kind":null,"min":2,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":"replace_audio_and_video","description":"The retake mode to use for the retake","enum":["replace_audio","replace_video","replace_audio_and_video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"retake_mode","required":false,"type":"enum"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per second.","published_at":"2025-11-26T17:22:47.621000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/xvJ-7NU2kAKJBpgXtwGfL_746be952110b4b5db200f410da23e7f8.jpg","title":"LTX Video 2.0 Retake"},{"category":"text-to-video","description":"Create high-fidelity video with audio from text with LTX-2 Pro.","endpoint_id":"fal-ai/ltx-2/text-to-video","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds","enum":[6,8,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[25,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.06 per second for 1080p, $0.12 per second for 1440p or $0.24 per second for 2160p.","published_at":"2025-11-26T17:29:02.911000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/8KQLQn8JfajzxzHs5KTAp_96322584ff4b4779b10368b8f0ce00bb.jpg","title":"LTX Video 2.0 Pro"},{"category":"text-to-video","description":"Create high-fidelity video with audio from text with LTX-2 Fast","endpoint_id":"fal-ai/ltx-2/text-to-video/fast","family":"LTX 2","inputs":[{"default":null,"description":"The prompt to generate the video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"The duration of the generated video in seconds. The fast model supports 6-20 seconds. Note: Durations longer than 10 seconds (12, 14, 16, 18, 20) are only supported with 25 FPS and 1080p resolution.","enum":[6,8,10,12,14,16,18,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":25,"description":"The frames per second of the generated video","enum":[25,50],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fps","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.04 per second for 1080p, $0.08 per second for 1440p or $0.16 per second for 2160p.","published_at":"2025-11-26T17:29:41.777000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/WESFAXKxTUdd23u9ruHHS_b6a3b01d00ef48aba773b29b918a8aea.jpg","title":"LTX Video 2.0 Fast"},{"category":"text-to-video","description":"Generate videos from prompts using LTX Video","endpoint_id":"fal-ai/ltx-video","family":"LTX","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed to use for random number generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"The number of inference steps to take.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-10-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","title":"LTX Video (preview)"},{"category":"text-to-video","description":"Generate videos from prompts using LTX Video-0.9.7 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-video-13b-distilled","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["9:16","1:1","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.04 per video. For $1 you can run this model approximately 25 times.","published_at":"2025-05-17T01:49:06.775000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"LTX Video-0.9.7 13B Distilled"},{"category":"video-to-video","description":"Extend videos using LTX Video-0.9.7 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-video-13b-distilled/extend","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the video.","enum":["9:16","1:1","16:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"},{"default":29,"description":"The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"constant_rate_factor","required":false,"type":"integer"},{"default":null,"description":"Video to be extended.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.04 per video. For $1 you can run this model approximately 25 times.","published_at":"2025-05-17T02:04:17.474000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-2.jpg","title":"LTX Video-0.9.7 13B Distilled"},{"category":"image-to-video","description":"Generate videos from prompts and images using LTX Video-0.9.7 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-video-13b-distilled/image-to-video","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the video.","enum":["9:16","1:1","16:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"},{"default":29,"description":"The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"constant_rate_factor","required":false,"type":"integer"},{"default":null,"description":"Image URL for Image-to-Video task","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.04 per second of generated video (at 24 fps), and $0.08 per second if the detail pass is enabled.","published_at":"2025-05-17T01:59:46.017000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922a/E8s8t2FBPrzze7IbGqvtY_h2ZGIzJR.png","title":"LTX Video-0.9.7 13B Distilled"},{"category":"video-to-video","description":"Generate videos from prompts, images, and videos using LTX Video-0.9.7 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltx-video-13b-distilled/multiconditioning","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the video.","enum":["9:16","1:1","16:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"},{"default":29,"description":"The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"constant_rate_factor","required":false,"type":"integer"},{"default":"[]","description":"URL of images to use as conditioning","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"images","required":false,"type":"json"},{"default":"[]","description":"Videos to use as conditioning","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"videos","required":false,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","prompt","seed"],"pricing":"Your request will cost $0.04 per video. For $1 you can run this model approximately 25 times.","published_at":"2025-05-17T02:02:53.741000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training.jpg","title":"LTX Video-0.9.7 13B Distilled"},{"category":"text-to-video","description":"Generate videos from prompts using LTX Video-0.9.5","endpoint_id":"fal-ai/ltx-video-v095","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"Resolution of the generated video (480p or 720p).","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":40,"description":"Number of inference steps","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to expand the prompt using the model's own capabilities.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ltx-0.9.5.webp","title":"LTX Video-0.9.5"},{"category":"video-to-video","description":"Generate videos from prompts and videos using LTX Video-0.9.5","endpoint_id":"fal-ai/ltx-video-v095/extend","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"Resolution of the generated video (480p or 720p).","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":40,"description":"Number of inference steps","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to expand the prompt using the model's own capabilities.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":null,"description":"Video to be extended.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ltx-0.9.5.webp","title":"LTX Video-0.9.5"},{"category":"video-to-video","description":"Generate videos from prompts,images, and videos using LTX Video-0.9.5","endpoint_id":"fal-ai/ltx-video-v095/multiconditioning","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"Resolution of the generated video (480p or 720p).","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":40,"description":"Number of inference steps","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to expand the prompt using the model's own capabilities.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"[]","description":"URL of images to use as conditioning","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"images","required":false,"type":"json"},{"default":"[]","description":"Videos to use as conditioning","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"videos","required":false,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/ltx-0.9.5.webp","title":"LTX Video-0.9.5"},{"category":"image-to-video","description":"Generate videos from images using LTX Video","endpoint_id":"fal-ai/ltx-video/image-to-video","family":"LTX","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"low quality, worst quality, deformed, distorted, disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, weird hand, ugly","description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed to use for random number generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":30,"description":"The number of inference steps to take.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"The guidance scale to use.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The URL of the image to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2024-11-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","title":"LTX Video (preview)"},{"category":"training","description":"Train a LoRA that transforms one audio clip into another, learning a reference→target mapping from paired audio examples.","endpoint_id":"fal-ai/ltx23-trainer-v2/a2a","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for a2a: the paired target/reference audio prep ignores scene splitting (it would desync the pair). Provide pre-split clips instead.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":5,"description":"Target audio clip length in seconds (the audio duration bucket). Clips shorter than this are skipped; longer clips are trimmed. Audio-only modes need this because there is no video frame-count to derive a length from.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.5,"multiline":false,"name":"audio_duration_seconds","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts, each with a reference audio clip.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0023 * steps. With 1000 steps, your request will cost $2.30.","published_at":"2026-06-17T18:59:58.741000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa49/_pYVyVWb5jfHC84W_fscW_e7634dcb57164e5bb57e58236088332a.jpg","title":"LTX 2.3 Trainer (V2) - Audio-to-Audio"},{"category":"training","description":"Train a LoRA that generates video from a start image plus a conditioning audio track, producing motion that matches the sound.","endpoint_id":"fal-ai/ltx23-trainer-v2/a2v","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"If true, synthesized training videos above the duration threshold are split into scenes after start-image/audio assembly.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize conditioning audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation prompts, each with a conditioning audio track.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.006 * steps. With 1000 steps, your request will cost $6.00.","published_at":"2026-06-17T19:00:02.723000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa4f/NOLY50srs-tVzfXT_a4vt_51076f03d3b04074b05fa4283a61734c.jpg","title":"LTX 2.3 Trainer (V2) - Audio-to-Video"},{"category":"training","description":"Train a LoRA that continues an audio clip forward in time, generating the audio that follows a short clean prefix.","endpoint_id":"fal-ai/ltx23-trainer-v2/audio-extend-prefix","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":1,"description":"Seconds of leading audio kept as the clean prefix condition. Must be < audio_duration_seconds so there is a continuation to generate.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0.1,"multiline":false,"name":"conditioning_seconds","required":false,"type":"number"},{"default":5,"description":"Target audio clip length in seconds (the audio duration bucket). Clips shorter than this are skipped; longer clips are trimmed.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.5,"multiline":false,"name":"audio_duration_seconds","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts, each with an audio clip to extend forward.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0022 * steps. With 1000 steps, your request will cost $2.20.","published_at":"2026-06-17T19:00:04.601000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa53/dW0lO8VwUfLX6bSiNi_Vi_c0eab055e35d4e7c92343c53e3e53a02.jpg","title":"LTX 2.3 Trainer (V2) - Forward Audio Extension"},{"category":"training","description":"Train a LoRA that generates the lead-in to an audio clip, extending audio backward in time from its ending.","endpoint_id":"fal-ai/ltx23-trainer-v2/audio-extend-suffix","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":1,"description":"Seconds of trailing audio kept as the clean suffix condition. Must be < audio_duration_seconds so there is a lead-in to generate.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0.1,"multiline":false,"name":"conditioning_seconds","required":false,"type":"number"},{"default":5,"description":"Target audio clip length in seconds (the audio duration bucket). Clips shorter than this are skipped; longer clips are trimmed.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.5,"multiline":false,"name":"audio_duration_seconds","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts, each with an audio clip to extend backward.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0023 * steps. With 1000 steps, your request will cost $2.30.","published_at":"2026-06-17T19:00:07.879000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e9a38/KBnDcIjSgYLtnqXnAhxy7_733326987e624669af43010c786d2f12.jpg","title":"LTX 2.3 Trainer (V2) - Backward Audio Extension"},{"category":"training","description":"Train a LoRA that regenerates masked time spans of an audio clip while keeping the rest unchanged.","endpoint_id":"fal-ai/ltx23-trainer-v2/audio-inpaint","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":5,"description":"Target audio clip length in seconds (the audio duration bucket). Clips shorter than this are skipped; longer clips are trimmed.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.5,"multiline":false,"name":"audio_duration_seconds","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts, each with an audio clip + time ranges.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0023 * steps. With 1000 steps, your request will cost $2.30.","published_at":"2026-06-17T19:00:10.504000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa6a/96PTq7NFEaykyDmZjDVAT_fe8130aee3e94af89490a3f5d6455aad.jpg","title":"LTX 2.3 Trainer (V2) - Audio Inpainting"},{"category":"training","description":"Train a LoRA for a joint audio+video transformation, conditioned on a reference clip (its video and audio) to produce a matching target clip.","endpoint_id":"fal-ai/ltx23-trainer-v2/av2av","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for av2av: the paired target/reference prep ignores scene splitting (it would desync the _start/_end pair). Provide pre-split clips instead.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation prompts, each with a reference video (+audio).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"},{"default":1,"description":"Spatially downscale the reference VIDEO by this factor before encoding (coarse/low-res control proxy -> full-res output). 1 = same resolution (default). Reference width/height and width/height divided by the factor must be divisible by 32.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_downscale_factor","required":false,"type":"integer"},{"default":1,"description":"Temporally downsample the reference VIDEO by this factor (lower fps) before encoding. 1 = same fps (default).","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_temporal_scale_factor","required":false,"type":"integer"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0068 * steps. With 1000 steps, your request will cost $6.80.","published_at":"2026-06-17T19:00:13.628000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa8e/MtfirL2FrL71p49CwuYkW_71aab3fc88844285a3664877e9b9835f.jpg","title":"LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation"},{"category":"training","description":"Train a LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.","endpoint_id":"fal-ai/ltx23-trainer-v2/av2av-masked","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for masked av2av: the paired target/reference/mask prep ignores scene splitting (it would desync the _start/_end/_mask triplet). Provide pre-split clips.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation inputs with a prompt, source video, mask, and reference video (+audio).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0068 * steps. With 1000 steps, your request will cost $6.80.","published_at":"2026-06-17T19:00:18.471000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa75/NxzZbvVQc922YdexuzAsK_4499a9952ad34a9295f69c024f53ea6b.jpg","title":"LTX 2.3 Trainer (V2) - Masked Audio+Video Transformation"},{"category":"training","description":"Train a LoRA that continues a video forward in time — supply an opening clip at inference and the model generates what comes next.","endpoint_id":"fal-ai/ltx23-trainer-v2/extend-prefix","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":false,"description":"Set true to jointly extend audio AND video — the model continues both from the same prefix window. Requires every training clip AND each validation clip to contain an audio track. Default (false): video-only extension (silent output).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"with_audio","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":9,"description":"Number of leading PIXEL frames used as the clean prefix condition (for audio too, when with_audio). Must be ≡ 1 (mod 8) (e.g. 9, 17, 25). Converted to the latent temporal_boundary (conditioning_frames-1)//8+1, which must be smaller than the clip's latent length so there is a continuation to generate.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"conditioning_frames","required":false,"type":"integer"},{"default":"[]","description":"A list of validation prompts, each with a video to extend forward.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0062 * steps. With 1000 steps, your request will cost $6.20.","published_at":"2026-06-17T19:00:22.741000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa77/SNJC2ki1XnwacERqWP3zI_0cde1b76fe0a492089268ce97ff7e403.jpg","title":"LTX 2.3 Trainer (V2) - Forward Video Extension"},{"category":"training","description":"Train a LoRA that generates the lead-in to a video, extending a clip backward in time from its ending.","endpoint_id":"fal-ai/ltx23-trainer-v2/extend-suffix","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":false,"description":"Set true to jointly extend audio AND video — the model continues both from the same suffix window. Requires every training clip AND each validation clip to contain an audio track. Default (false): video-only extension (silent output).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"with_audio","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":8,"description":"Number of trailing PIXEL frames used as the clean suffix condition (for audio too, when with_audio). Must be ≡ 0 (mod 8) (e.g. 8, 16, 24). Converted to the latent temporal_boundary conditioning_frames//8, which must be smaller than the clip's latent length so there is a lead-in to generate.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":8,"multiline":false,"name":"conditioning_frames","required":false,"type":"integer"},{"default":"[]","description":"A list of validation prompts, each with a video to extend backward.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0061 * steps. With 1000 steps, your request will cost $6.10.","published_at":"2026-06-17T19:00:26.603000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaa94/S01dDrZDoFxzuIWqSeCDa_a55a8d7a13bc48fbbdc503ea66731d42.jpg","title":"LTX 2.3 Trainer (V2) - Backward Video Extension"},{"category":"training","description":"Fine-tune LTX 2.3 to animate a starting image — supply a still plus a prompt at inference and the model generates a video that begins from that frame.","endpoint_id":"fal-ai/ltx23-trainer-v2/i2v","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":null,"description":"Enable joint audio-video training. If None (default), auto-detects whether input videos have audio. Set True to force audio training, or False to disable.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"with_audio","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":0.5,"description":"Probability of conditioning on the first frame during training. 0.5 trains a versatile LoRA usable for both image-to-video and text-to-video inference.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"first_frame_conditioning_p","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts, each with a first-frame image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0024 * steps. With 1000 steps, your request will cost $2.40.","published_at":"2026-06-17T19:00:30.681000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaaa3/Tcetg36NpYE2E3fqoW1Qx_fbca58f0520a450a89344d0ea71e18bc.jpg","title":"LTX 2.3 Trainer (V2) - Image-to-Video"},{"category":"training","description":"Train an IC-LoRA that transforms one audio clip into another, conditioned at inference on a reference audio clip.","endpoint_id":"fal-ai/ltx23-trainer-v2/ic-lora/a2a","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for a2a: the paired target/reference audio prep ignores scene splitting (it would desync the pair). Provide pre-split clips instead.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":5,"description":"Target audio clip length in seconds (the audio duration bucket). Clips shorter than this are skipped; longer clips are trimmed. Audio-only modes need this because there is no video frame-count to derive a length from.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.5,"multiline":false,"name":"audio_duration_seconds","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts, each with a reference audio clip.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0023 * steps. With 1000 steps, your request will cost $2.30.","published_at":"2026-06-17T19:00:34.318000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaaa6/MvNEEk196zBPzY5TE5EWT_8266bfda3e974eed965eb7f3108572bd.jpg","title":"LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA"},{"category":"training","description":"Train an IC-LoRA for a joint audio+video transformation, conditioned on a reference clip's video and audio to produce a matching target.","endpoint_id":"fal-ai/ltx23-trainer-v2/ic-lora/av2av","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for av2av: the paired target/reference prep ignores scene splitting (it would desync the _start/_end pair). Provide pre-split clips instead.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation prompts, each with a reference video (+audio).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"},{"default":1,"description":"Spatially downscale the reference VIDEO by this factor before encoding (coarse/low-res control proxy -> full-res output). 1 = same resolution (default). Reference width/height and width/height divided by the factor must be divisible by 32.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_downscale_factor","required":false,"type":"integer"},{"default":1,"description":"Temporally downsample the reference VIDEO by this factor (lower fps) before encoding. 1 = same fps (default).","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_temporal_scale_factor","required":false,"type":"integer"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0068 * steps. With 1000 steps, your request will cost $6.80.","published_at":"2026-06-17T19:00:36.687000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaaac/orKex-RhQYHKjj0sjvW4w_b9a6648967d241559086a072e7013d1b.jpg","title":"LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA"},{"category":"training","description":"Train an IC-LoRA that regenerates a masked video region (guided by kept pixels and a video reference) while jointly generating audio from an audio reference.","endpoint_id":"fal-ai/ltx23-trainer-v2/ic-lora/av2av-masked","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for masked av2av: the paired target/reference/mask prep ignores scene splitting (it would desync the _start/_end/_mask triplet). Provide pre-split clips.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation inputs with a prompt, source video, mask, and reference video (+audio).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0068 * steps. With 1000 steps, your request will cost $6.80.","published_at":"2026-06-17T19:00:39.122000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaabc/5KrVyZNpoAZvKwg93DJRG_01c4f683d3dd460db89c737a4513ed08.jpg","title":"LTX 2.3 Trainer (V2) - Masked Audio+Video IC-LoRA"},{"category":"training","description":"Train an IC-LoRA that learns a video-to-video transformation from paired before/after clips, conditioned at inference on a reference (control) video.","endpoint_id":"fal-ai/ltx23-trainer-v2/ic-lora/v2v","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":3000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":0.1,"description":"Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"first_frame_conditioning_p","required":false,"type":"number"},{"default":"[]","description":"A list of validation inputs with prompts and reference videos.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"},{"default":1,"description":"Spatially downscale the reference (IC-LoRA control) video by this factor before encoding, so the LoRA learns to drive a full-resolution output from a coarse / low-res reference (e.g. a small pose/depth/sketch proxy). 1 = same resolution (default; unchanged behavior). Both the reference width/height and width/height divided by the factor must be divisible by 32.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_downscale_factor","required":false,"type":"integer"},{"default":1,"description":"Temporally downsample the reference (IC-LoRA control) video by this factor (lower fps) before encoding, so the LoRA can be driven by a low-fps reference. 1 = same fps (default; unchanged behavior).","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_temporal_scale_factor","required":false,"type":"integer"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0059 * steps. With 1000 steps, your request will cost $5.90.","published_at":"2026-06-17T19:00:42.179000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaabd/YJab7yRoRqTau0Aq4W486_376b102304fc4d12a7831a0e0e147d14.jpg","title":"LTX 2.3 Trainer (V2) - Video-to-Video IC-LoRA"},{"category":"training","description":"Train an IC-LoRA that regenerates only the masked region of a video, guided by the kept pixels and a separate reference/control video.","endpoint_id":"fal-ai/ltx23-trainer-v2/ic-lora/v2v-masked","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":3000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for masked v2v: the paired target/reference/mask prep ignores scene splitting (it would desync the _start/_end/_mask triplet). Provide pre-split clips.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation inputs with a prompt, source video, mask, and reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0055 * steps. With 1000 steps, your request will cost $5.50.","published_at":"2026-06-17T19:00:44.452000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaabf/OseOeP3-e80ffRt-1exoB_7fff9e5e585b4e30a20ce11fba7f1722.jpg","title":"LTX 2.3 Trainer (V2) - Masked Video-to-Video IC-LoRA"},{"category":"training","description":"Train a LoRA that regenerates a masked region of a video while keeping the rest unchanged, blending the new content with its surroundings.","endpoint_id":"fal-ai/ltx23-trainer-v2/inpaint","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for inpainting: scene splitting would desync a clip from its mask. Provide pre-split clips instead.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation prompts, each with a source video + a mask.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0024 * steps. With 1000 steps, your request will cost $2.40.","published_at":"2026-06-17T19:00:47.582000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaadc/ndWbPMNanN-CS1vPAAcfj_0f1fcce5512d4d008b9509c74219b080.jpg","title":"LTX 2.3 Trainer (V2) - Video Inpainting"},{"category":"training","description":"Train a LoRA that generates the video between keyframes — supply first/last (and optional middle) frames at inference and the model fills the in-between motion.","endpoint_id":"fal-ai/ltx23-trainer-v2/interpolate","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation inputs, each with a prompt and keyframe images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"},{"default":false,"description":"Also keep a middle keyframe (first+middle+last -> video) instead of just first+last. When true, every validation sample must provide middle_image_url.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_middle_keyframe","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0024 * steps. With 1000 steps, your request will cost $2.40.","published_at":"2026-06-17T19:00:50.255000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaad6/RZzDx1qFqvsHuoQInTbNc_657662a9e66b46e48f7379bdb0a51518.jpg","title":"LTX 2.3 Trainer (V2) - Keyframe Interpolation"},{"category":"training","description":"Train a LoRA that expands the video frame outward, keeping an inner rectangle fixed and generating the surrounding region.","endpoint_id":"fal-ai/ltx23-trainer-v2/outpaint","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":null,"description":"(x1, y1) top-left corner of the KEPT inner rectangle, in TRAINING-resolution pixels — i.e. the bucket chosen by resolution x aspect_ratio, NOT the uploaded video's native size (clips are resized to that bucket before the crop is applied). Coordinates snap to a 32px latent grid.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_top_left","required":true,"type":"json"},{"default":null,"description":"(x2, y2) bottom-right corner of the KEPT inner rectangle, in TRAINING-resolution pixels. Must satisfy x2 > x1 and y2 > y1 and lie within the training frame; everything outside this rectangle is what the model generates.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_bottom_right","required":true,"type":"json"},{"default":"[]","description":"A list of validation prompts, each with a full-canvas video to outpaint.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.006 * steps. With 1000 steps, your request will cost $6.00.","published_at":"2026-06-17T19:00:53.233000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaae4/JLLuPXdZVZt7jnN7AKGis_5e64e64abefd49a9a4f6a3db903e8ba8.jpg","title":"LTX 2.3 Trainer (V2) - Spatial Outpainting"},{"category":"training","description":"Train a LoRA that generates audio from a text prompt — the audio counterpart of text-to-video — learning a sound or style from your clips.","endpoint_id":"fal-ai/ltx23-trainer-v2/t2a","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":5,"description":"Target audio clip length in seconds (the audio duration bucket). Clips shorter than this are skipped; longer clips are trimmed.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.5,"multiline":false,"name":"audio_duration_seconds","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts (audio is generated from each).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0022 * steps. With 1000 steps, your request will cost $2.20.","published_at":"2026-06-17T19:00:55.691000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaae9/avjlHhjz5ppUffXfLJS0D_fbedb4d0ef134d62b51f2a2a183d0e38.jpg","title":"LTX 2.3 Trainer (V2) - Text-to-Audio"},{"category":"training","description":"Fine-tune LTX 2.3 on your own clips to teach it a new subject, character, object, or visual style, then generate full videos from a text prompt.","endpoint_id":"fal-ai/ltx23-trainer-v2/t2v","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":null,"description":"Enable joint audio-video training. If None (default), auto-detects whether input videos have audio. Set True to force audio training, or False to disable.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"with_audio","required":false,"type":"boolean"},{"default":true,"description":"Peak-normalize audio for consistent levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"Preserve pitch when fitting audio to video duration (vs trimming/padding).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation prompts to use during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.006 * steps. With 1000 steps, your request will cost $6.00.","published_at":"2026-06-17T19:00:58.359000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaaee/7eICSEWO50QBXQurIcJjn_f16feceb5c6746a69e08ea9a8841857a.jpg","title":"LTX 2.3 Trainer (V2) - Text-to-Video"},{"category":"training","description":"Train a LoRA that generates audio (foley / sound design) for a silent video, learning a soundtrack that matches the on-screen action.","endpoint_id":"fal-ai/ltx23-trainer-v2/v2a","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"If true, long videos are split into scenes. Off by default for v2a: every clip must keep an audio track (the model generates audio), and scene splitting can produce silent trailing segments that would fail the per-clip audio check with a confusing error. Mirrors the a2v default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation prompts, each with a silent video to generate audio for.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0049 * steps. With 1000 steps, your request will cost $4.90.","published_at":"2026-06-17T19:01:01.127000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaafc/ezs5zY0lbJQwWG_wWg63j_368a233643f84755810ec510a7e6c42d.jpg","title":"LTX 2.3 Trainer (V2) - Video-to-Audio"},{"category":"training","description":"Train a LoRA that learns a video-to-video transformation from paired before/after clips, steered at inference by a reference (control) video.","endpoint_id":"fal-ai/ltx23-trainer-v2/v2v","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":3000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":0.1,"description":"Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"first_frame_conditioning_p","required":false,"type":"number"},{"default":"[]","description":"A list of validation inputs with prompts and reference videos.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"},{"default":1,"description":"Spatially downscale the reference (IC-LoRA control) video by this factor before encoding, so the LoRA learns to drive a full-resolution output from a coarse / low-res reference (e.g. a small pose/depth/sketch proxy). 1 = same resolution (default; unchanged behavior). Both the reference width/height and width/height divided by the factor must be divisible by 32.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_downscale_factor","required":false,"type":"integer"},{"default":1,"description":"Temporally downsample the reference (IC-LoRA control) video by this factor (lower fps) before encoding, so the LoRA can be driven by a low-fps reference. 1 = same fps (default; unchanged behavior).","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"reference_temporal_scale_factor","required":false,"type":"integer"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0059 * steps. With 1000 steps, your request will cost $5.90.","published_at":"2026-06-17T19:01:03.845000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eab04/zM4iWyyJu5H2HRbZO-FYb_7c535830199348e596f5066ee3d0ebc7.jpg","title":"LTX 2.3 Trainer (V2) - Video-to-Video"},{"category":"training","description":"Train a LoRA that regenerates only the masked region of a video, guided by both the kept pixels and a separate reference/control video.","endpoint_id":"fal-ai/ltx23-trainer-v2/v2v-masked","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to a `.zip` archive of your training data. The exact file layout depends on the training mode — see this endpoint's documentation for the required structure. You can include a `.txt` caption alongside each media file (same base name).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":3000,"description":"The number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for the training video (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":false,"description":"Off for masked v2v: the paired target/reference/mask prep ignores scene splitting (it would desync the _start/_end/_mask triplet). Provide pre-split clips.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":"[]","description":"A list of validation inputs with a prompt, source video, mask, and reference video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.","description":"A negative prompt to use for validation. Note: validation previews are single-stage approximations of the production two-stage (distilled) inference, so preview quality and guidance differ from final inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":24,"description":"Target frames per second for validation videos (LTX-2.3 native is 24).","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["audio","config_file","debug_dataset","video","lora_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.0055 * steps. With 1000 steps, your request will cost $5.50.","published_at":"2026-06-17T19:01:06.336000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eaaff/PiJ_vPT6tLej62mcBPmne_f0ac0cde98e74fc9a952007a60914bd6.jpg","title":"LTX 2.3 Trainer (V2) - Masked Video-to-Video"},{"category":"training","description":"Train LTX-2.3 22B for video transformation or video-conditioned generation.","endpoint_id":"fal-ai/ltx23-v2v-trainer","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to zip archive with videos or images. Try to use at least 10 files, although more is better.\n\n        **Supported video formats:** .mp4, .mov, .avi, .mkv\n        **Supported image formats:** .png, .jpg, .jpeg\n\n        Note: The dataset must contain ONLY videos OR ONLY images - mixed datasets are not supported.\n\n        The archive can also contain text files with captions. Each text file should have the same name as the media file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization. Higher values can lead to faster training but may cause overfitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":25,"description":"Target frames per second for the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":0.1,"description":"Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"first_frame_conditioning_p","required":false,"type":"number"},{"default":"[]","description":"A list of validation inputs with prompts and reference videos.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"A negative prompt to use for validation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":25,"description":"Target frames per second for validation videos.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["config_file","lora_file","video","debug_dataset"],"pricing":"Your request will cost $0.0135 per step. For example, the default 2000-step training will cost $27.00.","published_at":"2026-04-14T21:43:44.115000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a929636/dvX7J7XYUc2Llc9xo1-zB_1cbc222714e649ef9440a9000d96ae92.jpg","title":"LTX-2.3 22B Video to Video Trainer"},{"category":"training","description":"Train LTX-2.3 22B for custom styles and effects.","endpoint_id":"fal-ai/ltx23-video-trainer","family":"LTX 2.3","inputs":[{"default":null,"description":"URL to zip archive with videos or images. Try to use at least 10 files, although more is better.\n\n        **Supported video formats:** .mp4, .mov, .avi, .mkv\n        **Supported image formats:** .png, .jpg, .jpeg\n\n        Note: The dataset must contain ONLY videos OR ONLY images - mixed datasets are not supported.\n\n        The archive can also contain text files with captions. Each text file should have the same name as the media file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":32,"description":"The rank of the LoRA adaptation. Higher values increase capacity but use more memory.","enum":[8,16,32,64,128],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":2000,"description":"The number of training steps.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"Learning rate for optimization. Higher values can lead to faster training but may cause overfitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":89,"description":"Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"number_of_frames","required":false,"type":"integer"},{"default":25,"description":"Target frames per second for the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":"medium","description":"Resolution to use for training. Higher resolutions require more memory.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"1:1","description":"Aspect ratio to use for training.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"","description":"A phrase that will trigger the LoRA style. Will be prepended to captions during training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"},{"default":true,"description":"If true, videos above a certain duration threshold will be split into scenes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"split_input_into_scenes","required":false,"type":"boolean"},{"default":30,"description":"The duration threshold in seconds. If a video is longer than this, it will be split into scenes.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"split_input_duration_threshold","required":false,"type":"number"},{"default":false,"description":"When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"debug_dataset","required":false,"type":"boolean"},{"default":null,"description":"Enable joint audio-video training. If None (default), automatically detects whether input videos have audio. Set to True to force audio training, or False to disable.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"with_audio","required":false,"type":"boolean"},{"default":true,"description":"Normalize audio peak amplitude to a consistent level. Recommended for consistent audio levels across the dataset.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_normalize","required":false,"type":"boolean"},{"default":true,"description":"When audio duration doesn't match video duration, stretch/compress audio without changing pitch. If disabled, audio is trimmed or padded with silence.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_preserve_pitch","required":false,"type":"boolean"},{"default":0.5,"description":"Probability of conditioning on the first frame during training. Higher values improve image-to-video performance.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"first_frame_conditioning_p","required":false,"type":"number"},{"default":"[]","description":"A list of validation prompts to use during training. When providing an image, _all_ validation inputs must have an image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation","required":false,"type":"json"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"A negative prompt to use for validation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_negative_prompt","required":false,"type":"string"},{"default":89,"description":"The number of frames in validation videos.","enum":null,"is_list":false,"max":121,"media_kind":null,"min":9,"multiline":false,"name":"validation_number_of_frames","required":false,"type":"integer"},{"default":25,"description":"Target frames per second for validation videos.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":8,"multiline":false,"name":"validation_frame_rate","required":false,"type":"integer"},{"default":"high","description":"The resolution to use for validation.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_resolution","required":false,"type":"enum"},{"default":"1:1","description":"The aspect ratio to use for validation.","enum":["16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"validation_aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"stg_scale","required":false,"type":"number"},{"default":true,"description":"Whether to generate audio in validation samples.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_in_validation","required":false,"type":"boolean"}],"lab":"Lightricks","output_kind":"video","output_props":["lora_file","video","debug_dataset","config_file"],"pricing":"Your request will cost $0.0048 per step. For example, the default 2000-step training will cost $9.60.","published_at":"2026-04-14T21:42:29.552000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9295f6/aEhnAqMznOIIpRGD6U8e4_c0ca22678f6242349793ae9e7db55746.jpg","title":"LTX-2.3 22B Video Trainer"},{"category":"text-to-video","description":"Generate long videos from prompts using LTX Video-0.9.8 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltxv-13b-098-distilled","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["9:16","1:1","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed","prompt"],"pricing":"Your request will cost $0.02 per second, billed at 24 frames per second. For $1 you can generate 50 seconds of video. Enabling `detail_pass` will double the billed seconds.","published_at":"2025-07-17T03:01:15.578000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"LTX-Video 13B 0.9.8 Distilled"},{"category":"video-to-video","description":"Extend videos using LTX Video-0.9.8 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltxv-13b-098-distilled/extend","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the video.","enum":["9:16","1:1","16:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"},{"default":29,"description":"The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"constant_rate_factor","required":false,"type":"integer"},{"default":null,"description":"Video to be extended.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video","required":true,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed","prompt"],"pricing":"Your request will cost $0.02 per second, billed at 24 frames per second. For $1 you can generate 50 seconds of video. Enabling `detail_pass` will double the billed seconds.","published_at":"2025-07-23T16:11:07.081000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","title":"LTX-Video 13B 0.9.8 Distilled"},{"category":"image-to-video","description":"Generate long videos from prompts and images using LTX Video-0.9.8 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltxv-13b-098-distilled/image-to-video","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the video.","enum":["9:16","1:1","16:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"},{"default":29,"description":"The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"constant_rate_factor","required":false,"type":"integer"},{"default":null,"description":"Image URL for Image-to-Video task","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed","prompt"],"pricing":"Your request will cost $0.02 per second, billed at 24 frames per second. For $1 you can generate 50 seconds of video. Enabling `detail_pass` will double the billed seconds.","published_at":"2025-07-17T03:02:23.813000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-5.jpg","title":"LTX-Video 13B 0.9.8 Distilled"},{"category":"video-to-video","description":"Generate long videos from prompts, images, and videos using LTX Video-0.9.8 13B Distilled and custom LoRA","endpoint_id":"fal-ai/ltxv-13b-098-distilled/multiconditioning","family":"LTX","inputs":[{"default":null,"description":"Text prompt to guide generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"worst quality, inconsistent motion, blurry, jittery, distorted","description":"Negative prompt for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"LoRA weights to use for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":"720p","description":"Resolution of the generated video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the video.","enum":["9:16","1:1","16:9","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":121,"description":"The number of frames in the video.","enum":null,"is_list":false,"max":1441,"media_kind":null,"min":9,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the first pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"first_pass_num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"Number of inference steps during the second pass.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":2,"multiline":false,"name":"second_pass_num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.","enum":null,"is_list":false,"max":11,"media_kind":null,"min":1,"multiline":false,"name":"second_pass_skip_initial_steps","required":false,"type":"integer"},{"default":24,"description":"The frame rate of the video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"frame_rate","required":false,"type":"integer"},{"default":false,"description":"Whether to expand the prompt using a language model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":false,"description":"Whether to reverse the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_detail_pass","required":false,"type":"boolean"},{"default":0.5,"description":"The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temporal_adain_factor","required":false,"type":"number"},{"default":0,"description":"The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tone_map_compression_ratio","required":false,"type":"number"},{"default":29,"description":"The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"constant_rate_factor","required":false,"type":"integer"},{"default":"[]","description":"URL of images to use as conditioning","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"images","required":false,"type":"json"},{"default":"[]","description":"Videos to use as conditioning","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"videos","required":false,"type":"json"}],"lab":"Lightricks","output_kind":"video","output_props":["video","seed","prompt"],"pricing":"Your request will cost $0.02 per second, billed at 24 frames per second. For $1 you can generate 50 seconds of video. Enabling `detail_pass` will double the billed seconds.","published_at":"2025-07-17T02:59:51.470000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training.jpg","title":"LTX-Video 13B 0.9.8 Distilled"},{"category":"text-to-video","description":"Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.","endpoint_id":"fal-ai/luma-dream-machine/ray-2","family":"Ray 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether the video should loop (end of video is blended with the beginning)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":"540p","description":"The resolution of the generated video (720p costs 2x more, 1080p costs 4x more)","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video (9s costs 2x more)","enum":["5s","9s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-01-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2"},{"category":"text-to-video","description":"Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.","endpoint_id":"fal-ai/luma-dream-machine/ray-2-flash","family":"Ray 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether the video should loop (end of video is blended with the beginning)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":"540p","description":"The resolution of the generated video (720p costs 2x more, 1080p costs 4x more)","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video (9s costs 2x more)","enum":["5s","9s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2 Flash"},{"category":"image-to-video","description":"Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.","endpoint_id":"fal-ai/luma-dream-machine/ray-2-flash/image-to-video","family":"Ray 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Initial image to start the video from. Can be used together with end_image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Final image to end the video with. Can be used together with image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether the video should loop (end of video is blended with the beginning)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":"540p","description":"The resolution of the generated video (720p costs 2x more, 1080p costs 4x more)","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video","enum":["5s","9s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2 Flash (Image to Video)"},{"category":"video-to-video","description":"Ray2 Flash Modify is a video generative model capable of restyling or retexturing the entire shot, from turning live-action into CG or stylized animation, to changing wardrobe, props, or the overall aesthetic and swap environments or time periods, giving you control over background, location, or even weather.","endpoint_id":"fal-ai/luma-dream-machine/ray-2-flash/modify","family":"Ray 2","inputs":[{"default":null,"description":"URL of the input video to modify","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of the first frame image for modification","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Instruction for modifying the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"flex_1","description":"Amount of modification to apply to the video, adhere_1 is the least amount of modification, reimagine_3 is the most","enum":["adhere_1","adhere_2","adhere_3","flex_1","flex_2","flex_3","reimagine_1","reimagine_2","reimagine_3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-07-17T14:03:02.298000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d4/OE4NIX_CnQw39U9HWlI6A_QIbhyMoI.png","title":"Luma Ray 2 Flash Modify"},{"category":"video-to-video","description":"Adjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.","endpoint_id":"fal-ai/luma-dream-machine/ray-2-flash/reframe","family":"Ray 2","inputs":[{"default":null,"description":"URL of the input video to reframe","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The aspect ratio of the reframed video","enum":["1:1","16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the first frame image for reframing","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"X position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_x","required":false,"type":"integer"},{"default":null,"description":"Y position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_y","required":false,"type":"integer"},{"default":null,"description":"Optional prompt for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"End X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_end","required":false,"type":"integer"},{"default":null,"description":"Start X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_start","required":false,"type":"integer"},{"default":null,"description":"End Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_end","required":false,"type":"integer"},{"default":null,"description":"Start Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_start","required":false,"type":"integer"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-06-03T15:52:49.571000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2 Flash Reframe"},{"category":"image-to-video","description":"Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.","endpoint_id":"fal-ai/luma-dream-machine/ray-2/image-to-video","family":"Ray 2","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Initial image to start the video from. Can be used together with end_image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Final image to end the video with. Can be used together with image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"Whether the video should loop (end of video is blended with the beginning)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":"540p","description":"The resolution of the generated video (720p costs 2x more, 1080p costs 4x more)","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video","enum":["5s","9s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2 (Image to Video)"},{"category":"video-to-video","description":"Ray2 Modify is a video generative model capable of restyling or retexturing the entire shot, from turning live-action into CG or stylized animation, to changing wardrobe, props, or the overall aesthetic and swap environments or time periods, giving you control over background, location, or even weather.","endpoint_id":"fal-ai/luma-dream-machine/ray-2/modify","family":"Ray 2","inputs":[{"default":null,"description":"URL of the input video to modify","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of the first frame image for modification","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Instruction for modifying the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"flex_1","description":"Amount of modification to apply to the video, adhere_1 is the least amount of modification, reimagine_3 is the most","enum":["adhere_1","adhere_2","adhere_3","flex_1","flex_2","flex_3","reimagine_1","reimagine_2","reimagine_3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-06-28T19:42:05.110000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2 Modify"},{"category":"video-to-video","description":"Adjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.","endpoint_id":"fal-ai/luma-dream-machine/ray-2/reframe","family":"Ray 2","inputs":[{"default":null,"description":"URL of the input video to reframe","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The aspect ratio of the reframed video","enum":["1:1","16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the first frame image for reframing","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"X position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_x","required":false,"type":"integer"},{"default":null,"description":"Y position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_y","required":false,"type":"integer"},{"default":null,"description":"Optional prompt for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"End X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_end","required":false,"type":"integer"},{"default":null,"description":"Start X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_start","required":false,"type":"integer"},{"default":null,"description":"End Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_end","required":false,"type":"integer"},{"default":null,"description":"Start Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_start","required":false,"type":"integer"}],"lab":"Luma AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-06-03T15:50:57.754000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-dream-machine-ray-2.webp","title":"Luma Ray 2 Reframe"},{"category":"text-to-image","description":"Generate images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.","endpoint_id":"fal-ai/luma-photon","family":"Photon","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2024-06-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-photon.webp","title":"Luma Photon"},{"category":"text-to-image","description":"Generate images from your prompts using Luma Photon Flash. Photon Flash is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.","endpoint_id":"fal-ai/luma-photon/flash","family":"Photon","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2024-12-03T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-photon.webp","title":"Luma Photon Flash"},{"category":"image-to-image","description":"Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.","endpoint_id":"fal-ai/luma-photon/flash/modify","family":"Photon","inputs":[{"default":null,"description":"Instruction for modifying the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the input image to reframe","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The strength of the initial image. Higher strength values are corresponding to more influence of the initial image on the output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":true,"type":"number"},{"default":null,"description":"The aspect ratio of the reframed image","enum":["1:1","16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-06-08T12:51:44.150000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-photon.webp","title":"Luma Photon"},{"category":"image-to-image","description":"This advanced tool intelligently expands your visuals, seamlessly blending new content to enhance creativity and adaptability, offering unmatched speed and quality for creators at a fraction of the cost.","endpoint_id":"fal-ai/luma-photon/flash/reframe","family":"Photon","inputs":[{"default":null,"description":"URL of the input image to reframe","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The aspect ratio of the reframed image","enum":["1:1","16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"},{"default":null,"description":"Optional prompt for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"X position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_x","required":false,"type":"integer"},{"default":null,"description":"Y position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_y","required":false,"type":"integer"},{"default":null,"description":"End X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_end","required":false,"type":"integer"},{"default":null,"description":"Start X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_start","required":false,"type":"integer"},{"default":null,"description":"End Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_end","required":false,"type":"integer"},{"default":null,"description":"Start Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_start","required":false,"type":"integer"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-06-03T15:28:07.803000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-photon.webp","title":"Luma Photon Flash Reframe"},{"category":"image-to-image","description":"Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.","endpoint_id":"fal-ai/luma-photon/modify","family":"Photon","inputs":[{"default":null,"description":"Instruction for modifying the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the input image to reframe","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The strength of the initial image. Higher strength values are corresponding to more influence of the initial image on the output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":true,"type":"number"},{"default":null,"description":"The aspect ratio of the reframed image","enum":["1:1","16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-06-08T12:46:34.379000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-photon.webp","title":"Luma Photon"},{"category":"image-to-image","description":"Extend and reframe images with Luma Photon Reframe. This advanced tool intelligently expands your visuals, seamlessly blending new content to enhance creativity and adaptability, offering unmatched personalization and quality for creators at a fraction of the cost.","endpoint_id":"fal-ai/luma-photon/reframe","family":"Photon","inputs":[{"default":null,"description":"URL of the input image to reframe","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The aspect ratio of the reframed image","enum":["1:1","16:9","9:16","4:3","3:4","21:9","9:21"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"},{"default":null,"description":"Optional prompt for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"X position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_x","required":false,"type":"integer"},{"default":null,"description":"Y position of the grid for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grid_position_y","required":false,"type":"integer"},{"default":null,"description":"End X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_end","required":false,"type":"integer"},{"default":null,"description":"Start X coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"x_start","required":false,"type":"integer"},{"default":null,"description":"End Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_end","required":false,"type":"integer"},{"default":null,"description":"Start Y coordinate for reframing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"y_start","required":false,"type":"integer"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-06-03T15:13:14.628000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/luma-photon.webp","title":"Luma Photon Reframe"},{"category":"text-to-image","description":"Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transforer which features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.","endpoint_id":"fal-ai/lumina-image/v2","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"You are an assistant designed to generate superior images with the superior degree of image-text alignment based on textual prompts or user prompts.","description":"The system prompt to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Whether to apply normalization-based guidance scale.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"cfg_normalization","required":false,"type":"boolean"},{"default":1,"description":"The ratio of the timestep interval to apply normalization-based guidance scale.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_trunc_ratio","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","seed","prompt","timings"],"pricing":"","published_at":"2025-01-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/lumina-image-v2.webp","title":"Lumina Image 2"},{"category":"text-to-audio","description":"Lyria 2 is Google's latest music generation model, you can generate any type of music with this model.","endpoint_id":"fal-ai/lyria2","family":"Lyria 2","inputs":[{"default":null,"description":"The text prompt describing the music you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"low quality","description":"A description of what to exclude from the generated audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"A seed for deterministic generation. If provided, the model will attempt to produce the same audio given the same prompt and other parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Google","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-05-20T20:05:49.336000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-4.jpg","title":"Lyria2"},{"category":"text-to-audio","description":"Lyria 3 is most recent music model from Google","endpoint_id":"fal-ai/lyria3","family":"","inputs":[{"default":null,"description":"The text prompt describing the music you want to generate. Include genre, mood, instrumentation, tempo, and vocal style for best results. Lyria 3 supports vocals, lyrics, and multi-language generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"A description of what to exclude from the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Optional image URL to use as inspiration for music generation. The model will create music that matches the mood and theme of the image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"}],"lab":"Google","output_kind":"audio","output_props":["lyrics","audio"],"pricing":"","published_at":"2026-04-15T17:41:43.950000+00:00","thumbnail":"https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a94048f%2FbSx2MSBmQSPqHu3eKueYS_25a4c220ab8c4f67851f04f8e62b8445.jpg/tr:w-1920,q-80/bSx2MSBmQSPqHu3eKueYS_25a4c220ab8c4f67851f04f8e62b8445.webp","title":"Lyria3"},{"category":"text-to-audio","description":"Lyria 3 Pro is the latest music model from Google","endpoint_id":"fal-ai/lyria3/pro","family":"","inputs":[{"default":null,"description":"The text prompt describing the music you want to generate. Include genre, mood, instrumentation, tempo, and vocal style for best results. Lyria 3 supports vocals, lyrics, and multi-language generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"A description of what to exclude from the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Optional image URL to use as inspiration for music generation. The model will create music that matches the mood and theme of the image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"}],"lab":"Google","output_kind":"audio","output_props":["lyrics","audio"],"pricing":"","published_at":"2026-05-22T06:48:42.666000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9af59e/gZo8cVQPq90KMeAU-tQ7H_5144bb99c04b47038d174c4068bfcada.jpg","title":"Lyria 3 Pro"},{"category":"text-to-video","description":"MAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts","endpoint_id":"fal-ai/magi-distilled","family":"","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":96,"description":"Number of frames to generate. Must be between 96 and 192 (inclusive). Each additional 24 frames beyond 96 incurs an additional billing unit.","enum":null,"is_list":false,"max":192,"media_kind":null,"min":96,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":16,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":[4,8,16,32],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_inference_steps","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"Your request will cost $0.32 to generate one four-second video. For $1 you can run this model approximately 3 times. \n\nAdditional seconds will cost $0.08 each, calculated at 24 frames per second.\n\nAdditional inference steps above 16 incur a 1/16 multiplier each, such that your total cost will be multiplied x2 at 32 steps.","published_at":"2025-04-22T03:34:30.792000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","title":"MAGI-1 (Distilled)"},{"category":"video-to-video","description":"MAGI-1 distilled extends videos faster with an exceptional understanding of physical interactions and prompts","endpoint_id":"fal-ai/magi-distilled/extend-video","family":"","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input video to represent the beginning of the video. If the input video does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":96,"description":"Number of frames to generate. Must be between 96 and 192 (inclusive). Each additional 24 frames beyond 96 incurs an additional billing unit.","enum":null,"is_list":false,"max":192,"media_kind":null,"min":96,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":null,"description":"The frame to begin the generation from, with the remaining frames will be treated as the prefix video. The final video will contain the frames up until this number unchanged, followed by the generated frames. The default start frame is 32 frames before the end of the video, which gives optimal results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_frame","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":16,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":[4,8,16,32],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_inference_steps","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"Your request will cost $0.32 to generate one four-second video. For $1 you can run this model approximately 3 times. \n\nAdditional seconds will cost $0.08 each, calculated at 24 frames per second.\n\nAdditional inference steps above 16 incur a 1/16 multiplier each, such that your total cost will be multiplied x2 at 32 steps.","published_at":"2025-04-23T02:31:47.410000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","title":"MAGI-1 (Distilled)"},{"category":"image-to-video","description":"MAGI-1 distilled generates videos faster from images with exceptional understanding of physical interactions and prompting","endpoint_id":"fal-ai/magi-distilled/image-to-video","family":"","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input image to represent the first frame of the video. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":96,"description":"Number of frames to generate. Must be between 96 and 192 (inclusive). Each additional 24 frames beyond 96 incurs an additional billing unit.","enum":null,"is_list":false,"max":192,"media_kind":null,"min":96,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":16,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":[4,8,16,32],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"num_inference_steps","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"Your request will cost $0.32 to generate one four-second video. For $1 you can run this model approximately 3 times. \n\nAdditional seconds will cost $0.08 each, calculated at 24 frames per second.\n\nAdditional inference steps above 16 incur a 1/16 multiplier each, such that your total cost will be multiplied x2 at 32 steps.","published_at":"2025-04-23T02:26:54.535000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-2.jpg","title":"MAGI-1 (Distilled)"},{"category":"vision","description":"Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?","endpoint_id":"fal-ai/marlin","family":"","inputs":[{"default":null,"description":"URL of the video to caption. Up to ~2 minutes is supported.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Caption prompt sent to the model. The example value is Marlin's canonical training prompt — overriding usually degrades output quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2048,"description":"Maximum number of tokens to generate for the caption.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":64,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":false,"description":"If true, sample with temperature/top_p; if false, use greedy decoding.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"do_sample","required":false,"type":"boolean"},{"default":1,"description":"Sampling temperature. Only used when do_sample is true.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1,"description":"Nucleus sampling threshold. Only used when do_sample is true.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"","output_kind":"json","output_props":["scene","events","text"],"pricing":"","published_at":"2026-05-21T15:22:11.880000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afefa/fAcqvrcTMMrzjksn9pCE8_d52c68d7c1694395b67cbb22280a919e.jpg","title":"Marlin"},{"category":"vision","description":"Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?","endpoint_id":"fal-ai/marlin/find","family":"","inputs":[{"default":null,"description":"URL of the video to search through.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Natural-language description of the event or scene to find in the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"If true, sample with temperature/top_p; if false, use greedy decoding.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"do_sample","required":false,"type":"boolean"},{"default":1,"description":"Sampling temperature. Only used when do_sample is true.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1,"description":"Nucleus sampling threshold. Only used when do_sample is true.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"","output_kind":"json","output_props":["format_ok","text","span"],"pricing":"","published_at":"2026-05-21T15:22:03.611000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afef8/CQRc6WiRUic7BV2kfxpQk_e3e2bff829fa4a0abc66123b986922a2.jpg","title":"Marlin Find"},{"category":"text-to-speech","description":"Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.","endpoint_id":"fal-ai/maya","family":"","inputs":[{"default":null,"description":"The text to synthesize into speech. You can embed emotion tags anywhere in the text using the format <emotion_name>. Available emotions: laugh, laugh_harder, sigh, chuckle, gasp, angry, excited, whisper, cry, scream, sing, snort, exhale, gulp, giggle, sarcastic, curious. Example: 'Hello world! <excited> This is amazing!' or 'I can't believe this <sigh> happened again.'","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Description of the voice/character. Includes attributes like age, accent, pitch, timbre, pacing, tone, and intensity. See examples for format.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.4,"description":"Sampling temperature. Lower values (0.2-0.5) produce more stable/consistent audio. Higher values add variation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.9,"description":"Nucleus sampling parameter. Controls diversity of token selection.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":2000,"description":"Maximum number of SNAC tokens to generate (7 tokens per frame). Controls maximum audio length.","enum":null,"is_list":false,"max":4000,"media_kind":null,"min":28,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":1.1,"description":"Penalty for repeating tokens. Higher values reduce repetition artifacts.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":"48 kHz","description":"Output audio sample rate. 48 kHz provides higher quality audio, 24 kHz is faster.","enum":["48 kHz","24 kHz"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sample_rate","required":false,"type":"enum"},{"default":"wav","description":"Output audio format for the generated speech","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"audio","output_props":["audio","rtf","sample_rate","generation_time","duration"],"pricing":"Your request will cost 0.002 per generated audio seconds.","published_at":"2025-11-15T01:00:12+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/w_fnH4AqLcG0s0HRVYhQK_755e9d6c2502409fa7cf87f768925dd4.jpg","title":"Maya1"},{"category":"text-to-speech","description":"Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.","endpoint_id":"fal-ai/maya/batch","family":"","inputs":[{"default":null,"description":"List of texts to synthesize into speech. You can embed emotion tags in each text using the format <emotion_name>.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texts","required":true,"type":"string"},{"default":null,"description":"List of voice descriptions for each text. Must match the length of texts list. Each describes the voice/character attributes.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompts","required":true,"type":"string"},{"default":0.4,"description":"Sampling temperature for all generations.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.9,"description":"Nucleus sampling parameter for all generations.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":2000,"description":"Maximum SNAC tokens per generation.","enum":null,"is_list":false,"max":4000,"media_kind":null,"min":28,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":1.1,"description":"Repetition penalty for all generations.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":"48 kHz","description":"Output audio sample rate for all generations. 48 kHz provides higher quality, 24 kHz is faster.","enum":["48 kHz","24 kHz"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sample_rate","required":false,"type":"enum"},{"default":"wav","description":"Output audio format for all generated speech files","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"audio","output_props":["total_generation_time","sample_rate","durations","average_rtf","audios"],"pricing":"Your request will cost 0.002 per generated audio seconds.","published_at":"2025-12-12T22:26:37.028000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a860f0a/FtJNWhDtad-vpXpr9mWeX_77608b3886eb43eb9a89425ea6253d94.jpg","title":"Maya"},{"category":"text-to-speech","description":"Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.","endpoint_id":"fal-ai/maya/stream","family":"","inputs":[{"default":null,"description":"The text to synthesize into speech. You can embed emotion tags anywhere in the text using the format <emotion_name>. Available emotions: laugh, laugh_harder, sigh, chuckle, gasp, angry, excited, whisper, cry, scream, sing, snort, exhale, gulp, giggle, sarcastic, curious. Example: 'Hello world! <excited> This is amazing!' or 'I can't believe this <sigh> happened again.'","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Description of the voice/character. Includes attributes like age, accent, pitch, timbre, pacing, tone, and intensity. See examples for format.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.4,"description":"Sampling temperature. Lower values (0.2-0.5) produce more stable/consistent audio. Higher values add variation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.9,"description":"Nucleus sampling parameter. Controls diversity of token selection.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":2000,"description":"Maximum number of SNAC tokens to generate (7 tokens per frame). Controls maximum audio length.","enum":null,"is_list":false,"max":4000,"media_kind":null,"min":28,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":1.1,"description":"Penalty for repeating tokens. Higher values reduce repetition artifacts.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":"24 kHz","description":"Output audio sample rate. 48 kHz uses upsampling for higher quality audio, 24 kHz is native SNAC output (faster, lower latency).","enum":["48 kHz","24 kHz"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sample_rate","required":false,"type":"enum"},{"default":"mp3","description":"Output audio format. 'mp3' for browser-playable audio, 'wav' for uncompressed audio, 'pcm' for raw PCM (lowest latency, requires client-side decoding).","enum":["mp3","wav","pcm"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"json","output_props":[],"pricing":"Your request will cost 0.002 per generated audio seconds.","published_at":"2025-12-12T22:06:21.721000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a860e8c/yukdPKr05eoZ3Fx9zp6b0_fcbf051a9f4e4ab9a510e8cc9084098f.jpg","title":"Maya"},{"category":"3d-to-3d","description":"Rig humanoid 3D models from GLB URLs with Meshy, returning rigged GLB/FBX files plus basic   animations.","endpoint_id":"fal-ai/meshy/rigging","family":"","inputs":[{"default":null,"description":"URL of a 3D model in GLB format to rig. Can be any publicly accessible URL — works with models generated by Hunyuan, Trellis, Meshy, or any other 3D generation tool. The model must be a humanoid character with clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"model_url","required":true,"type":"string"},{"default":1.7,"description":"Approximate height of the character in meters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"json","output_props":["animation_glb","rigged_character_fbx","animation_fbx","rigged_character_glb","rig_task_id","basic_animations"],"pricing":"$0.20 per request. +$0.12 when enable_animation=true ($0.32 total).","published_at":"2026-05-19T22:13:29.355000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ae24d/XIUgczEpCoC7-xcZRvqbu_c31adb5b44304f35a23d70458c77aa31.jpg","title":"Meshy Rigging"},{"category":"3d-to-3d","description":"Meshy auto-rigs a humanoid 3D model fitting a skeleton and binding the mesh, then applies several motion presets from its animation library","endpoint_id":"fal-ai/meshy/rigging/multi-animation","family":"","inputs":[{"default":null,"description":"URL of a 3D model in GLB format to rig and animate. Can be any publicly accessible URL — works with models generated by Hunyuan, Trellis, Meshy, or any other 3D generation tool. The model must be a humanoid character with clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"model_url","required":true,"type":"string"},{"default":1.7,"description":"Approximate height of the character in meters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"height_meters","required":false,"type":"number"},{"default":null,"description":"Animation preset IDs from Meshy's library. One animation clip is generated per ID against the same rig and returned in the 'animations' output array, in request order. Must contain at least one ID. Each ID must be in [0, 696], at most 10 distinct clips may be requested, and duplicate IDs are de-duplicated. See https://docs.meshy.ai/en/api/animation-library for available IDs.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_ids","required":true,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"json","output_props":["rigged_character_fbx","animations","rigged_character_glb","rig_task_id","basic_animations"],"pricing":"$0.20 per request. +$0.12 per animation clip in `animation_action_ids` (e.g. 3 clips = $0.56 total).","published_at":"2026-06-12T21:40:43.990000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e0bf5/ZWAyCMj3wyAm8pM8Fr3Rz_9a891ce4df144559a8d9b169cca63531.jpg","title":"Meshy Rigging Multi Animation"},{"category":"image-to-3d","description":"Meshy-5 multi image generates realistic and production ready 3D models from multiple images.","endpoint_id":"fal-ai/meshy/v5/multi-image-to-3d","family":"","inputs":[{"default":null,"description":"1 to 4 images for 3D model creation. All images should depict the same object from different angles. Supports .jpg, .jpeg, .png formats, and AVIF/HEIF which will be automatically converted. If more than 4 images are provided, only the first 4 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":"auto","description":"Controls symmetry behavior during model generation.","enum":["off","auto","on"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"symmetry_mode","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the remesh phase. When false, returns triangular mesh ignoring topology and target_polycount.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_remesh","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate textures. False provides mesh without textures for 5 credits, True adds texture generation for additional 10 credits.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_texture","required":false,"type":"boolean"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color. Requires should_texture to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Deprecated: use pose_mode instead. When true, generates a T-pose model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_a_t_pose","required":false,"type":"boolean"},{"default":"","description":"Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose.","enum":["a-pose","t-pose",""],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pose_mode","required":false,"type":"enum"},{"default":null,"description":"Text prompt to guide the texturing process. Requires should_texture to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process. Requires should_texture to be true.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"texture_image_url","required":false,"type":"string"},{"default":false,"description":"Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_rigging","required":false,"type":"boolean"},{"default":1.7,"description":"Approximate height of the character in meters. Only used when enable_rigging is true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"rigging_height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model. Requires enable_rigging to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["animation_glb","seed","animation_fbx","rigged_character_glb","basic_animations","rigged_character_fbx","thumbnail","rig_task_id","model_urls","model_glb","texture_urls"],"pricing":"","published_at":"2025-10-06T23:15:19.272000+00:00","thumbnail":"https://v3.fal.media/files/penguin/wLQpmudI-iiOD545isnQ0_b7878036846e4f72b23e29f55c97016e.jpg","title":"Meshy 5 Multi"},{"category":"3d-to-3d","description":"Meshy-5 remesh allows you to remesh and export existing 3D models into various formats","endpoint_id":"fal-ai/meshy/v5/remesh","family":"","inputs":[{"default":null,"description":"URL or base64 data URI of a 3D model to remesh. Supports .glb, .gltf, .obj, .fbx, .stl formats. Can be a publicly accessible URL or data URI with MIME type application/octet-stream.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"model_url","required":true,"type":"string"},{"default":["glb"],"description":"List of target formats for the remeshed model.","enum":["glb","fbx","obj","usdz","blend","stl"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_formats","required":false,"type":"enum"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model. Actual count may vary based on geometry complexity.","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":0,"description":"Resize the model to a certain height measured in meters. Set to 0 for no resizing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"resize_height","required":false,"type":"number"},{"default":null,"description":"Position of the origin. None means no effect.","enum":["bottom","center"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"origin_at","required":false,"type":"enum"}],"lab":"Meshy","output_kind":"file","output_props":["model_urls","model_glb"],"pricing":"","published_at":"2025-10-18T01:56:03.334000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/VuvDG9KC4adICrWIBIzIu_a731968003db42be8f2c91d1f00c811f.jpg","title":"Meshy 5 Remesh"},{"category":"3d-to-3d","description":"Meshy-5 retexture applies new, high-quality textures to existing 3D models using either text prompts or reference images. It supports PBR material generation for realistic, production-ready results.","endpoint_id":"fal-ai/meshy/v5/retexture","family":"","inputs":[{"default":null,"description":"URL or base64 data URI of a 3D model to texture. Supports .glb, .gltf, .obj, .fbx, .stl formats. Can be a publicly accessible URL or data URI with MIME type application/octet-stream.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"model_url","required":true,"type":"string"},{"default":null,"description":"Describe your desired texture style using text. Maximum 600 characters. Required if image_style_url is not provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_style_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process. Supports .jpg, .jpeg, and .png formats. Required if text_style_prompt is not provided. If both are provided, image_style_url takes precedence.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_style_url","required":false,"type":"string"},{"default":true,"description":"Use the original UV mapping of the model instead of generating new UVs. If the model has no original UV, output quality may be reduced.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_original_uv","required":false,"type":"boolean"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["text_style_prompt","model_urls","thumbnail","texture_urls","model_glb","image_style_url"],"pricing":"","published_at":"2025-10-18T02:04:55.284000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/mF5SI-u0DJ_bNr5J8nhsS_0d2ff4c4ea6a4733a169f8b530b576ec.jpg","title":"Meshy 5 Retexture"},{"category":"image-to-3d","description":"Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.","endpoint_id":"fal-ai/meshy/v6-preview/image-to-3d","family":"","inputs":[{"default":null,"description":"Image URL or base64 data URI for 3D model creation. Supports .jpg, .jpeg, and .png formats. Also supports AVIF and HEIF formats which will be automatically converted.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":"standard","description":"Type of 3D mesh generation. 'standard' produces a regular high-detail mesh; 'lowpoly' produces a low-poly mesh optimized for cleaner polygons. When set to 'lowpoly', the remesh controls (topology, target_polycount, should_remesh) are ignored by Meshy.","enum":["standard","lowpoly"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":false,"type":"enum"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":"auto","description":"Controls symmetry behavior during model generation. Off disables symmetry, Auto determines it automatically, On enforces symmetry.","enum":["off","auto","on"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"symmetry_mode","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the remesh phase","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_remesh","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate textures","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_texture","required":false,"type":"boolean"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Deprecated: use pose_mode instead. When true, generates a T-pose model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_a_t_pose","required":false,"type":"boolean"},{"default":"","description":"Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose.","enum":["a-pose","t-pose",""],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pose_mode","required":false,"type":"enum"},{"default":null,"description":"Text prompt to guide the texturing process","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"texture_image_url","required":false,"type":"string"},{"default":false,"description":"Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_rigging","required":false,"type":"boolean"},{"default":1.7,"description":"Approximate height of the character in meters. Only used when enable_rigging is true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"rigging_height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model. Requires enable_rigging to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["animation_glb","seed","animation_fbx","rigged_character_glb","basic_animations","rigged_character_fbx","thumbnail","rig_task_id","model_urls","model_glb","texture_urls"],"pricing":"","published_at":"2025-10-06T23:11:32.101000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/DSTicAg_awPQiKUDYINO1_f2f15f177bfe4e94b4f91340ff0393f6.jpg","title":"Meshy 6 Preview"},{"category":"text-to-3d","description":"Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.","endpoint_id":"fal-ai/meshy/v6-preview/text-to-3d","family":"","inputs":[{"default":null,"description":"Describe what kind of object the 3D model is. Maximum 600 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"full","description":"Generation mode. 'preview' returns untextured geometry only, 'full' returns textured model (preview + refine).","enum":["preview","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Seed for reproducible results. Same prompt and seed usually generate the same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"standard","description":"Type of 3D mesh generation. 'standard' produces a regular high-detail mesh; 'lowpoly' produces a low-poly mesh optimized for cleaner polygons. When set to 'lowpoly', the remesh controls (topology, target_polycount, should_remesh) are ignored by Meshy.","enum":["standard","lowpoly"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":false,"type":"enum"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the remesh phase. When false, returns unprocessed triangular mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_remesh","required":false,"type":"boolean"},{"default":"auto","description":"Controls symmetry behavior during model generation.","enum":["off","auto","on"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"symmetry_mode","required":false,"type":"enum"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Deprecated: use pose_mode instead. When true, generates a T-pose model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_a_t_pose","required":false,"type":"boolean"},{"default":"","description":"Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose.","enum":["a-pose","t-pose",""],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pose_mode","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Additional text prompt to guide the texturing process (only used in 'full' mode)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process (only used in 'full' mode)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"texture_image_url","required":false,"type":"string"},{"default":false,"description":"Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_rigging","required":false,"type":"boolean"},{"default":1.7,"description":"Approximate height of the character in meters. Only used when enable_rigging is true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"rigging_height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model. Requires enable_rigging to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["animation_glb","seed","animation_fbx","rigged_character_glb","basic_animations","prompt","actual_prompt","rigged_character_fbx","thumbnail","rig_task_id","texture_urls","model_glb","model_urls"],"pricing":"","published_at":"2025-10-06T23:26:16.872000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/R9WXOPkhbiHFjL8iXBLDG_79f59228974346e59950364b95325d80.jpg","title":"Meshy 6 Preview"},{"category":"image-to-3d","description":"Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.","endpoint_id":"fal-ai/meshy/v6/image-to-3d","family":"","inputs":[{"default":null,"description":"Image URL or base64 data URI for 3D model creation. Supports .jpg, .jpeg, and .png formats. Also supports AVIF and HEIF formats which will be automatically converted.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":"standard","description":"Type of 3D mesh generation. 'standard' produces a regular high-detail mesh; 'lowpoly' produces a low-poly mesh optimized for cleaner polygons. When set to 'lowpoly', the remesh controls (topology, target_polycount, should_remesh) are ignored by Meshy.","enum":["standard","lowpoly"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":false,"type":"enum"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":"auto","description":"Controls symmetry behavior during model generation. Off disables symmetry, Auto determines it automatically, On enforces symmetry.","enum":["off","auto","on"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"symmetry_mode","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the remesh phase","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_remesh","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate textures","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_texture","required":false,"type":"boolean"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Deprecated: use pose_mode instead. When true, generates a T-pose model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_a_t_pose","required":false,"type":"boolean"},{"default":"","description":"Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose.","enum":["a-pose","t-pose",""],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pose_mode","required":false,"type":"enum"},{"default":null,"description":"Text prompt to guide the texturing process","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"texture_image_url","required":false,"type":"string"},{"default":false,"description":"Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_rigging","required":false,"type":"boolean"},{"default":1.7,"description":"Approximate height of the character in meters. Only used when enable_rigging is true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"rigging_height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model. Requires enable_rigging to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["animation_glb","seed","animation_fbx","rigged_character_glb","basic_animations","rigged_character_fbx","thumbnail","rig_task_id","model_urls","model_glb","texture_urls"],"pricing":"","published_at":"2026-02-09T19:31:09.486000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e124f/OYdUQ-yuyJzJNcN0AIdph_5bb69644c92241afaeb4bcf0db85dbcf.jpg","title":"Meshy 6"},{"category":"image-to-3d","description":"Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.","endpoint_id":"fal-ai/meshy/v6/multi-image-to-3d","family":"","inputs":[{"default":null,"description":"1 to 4 images for 3D model creation. All images should depict the same object from different angles. Supports .jpg, .jpeg, .png formats, and AVIF/HEIF which will be automatically converted. If more than 4 images are provided, only the first 4 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":"auto","description":"Controls symmetry behavior during model generation.","enum":["off","auto","on"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"symmetry_mode","required":false,"type":"enum"},{"default":true,"description":"Whether to enable the remesh phase. When false, returns triangular mesh ignoring topology and target_polycount.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_remesh","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate textures. False provides mesh without textures for 5 credits, True adds texture generation for additional 10 credits.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_texture","required":false,"type":"boolean"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color. Requires should_texture to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Deprecated: use pose_mode instead. When true, generates a T-pose model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_a_t_pose","required":false,"type":"boolean"},{"default":"","description":"Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose.","enum":["a-pose","t-pose",""],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pose_mode","required":false,"type":"enum"},{"default":null,"description":"Text prompt to guide the texturing process. Requires should_texture to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process. Requires should_texture to be true.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"texture_image_url","required":false,"type":"string"},{"default":false,"description":"Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_rigging","required":false,"type":"boolean"},{"default":1.7,"description":"Approximate height of the character in meters. Only used when enable_rigging is true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"rigging_height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model. Requires enable_rigging to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["animation_glb","seed","animation_fbx","rigged_character_glb","basic_animations","rigged_character_fbx","thumbnail","rig_task_id","model_urls","model_glb","texture_urls"],"pricing":"$0.8 per untextured model / $1.2 per textured model. Add +$0.2 for auto-rigging and +$0.12 for animation.","published_at":"2026-04-23T16:08:02.069000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9754f9/65pGyzqHpV1-jzdapsyud_dd4d045f28e347dfa5afda4566b0e71d.jpg","title":"Meshy 6 - Multi Image To 3D"},{"category":"text-to-3d","description":"Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.","endpoint_id":"fal-ai/meshy/v6/text-to-3d","family":"","inputs":[{"default":null,"description":"Describe what kind of object the 3D model is. Maximum 600 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"full","description":"Generation mode. 'preview' returns untextured geometry only, 'full' returns textured model (preview + refine).","enum":["preview","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":null,"description":"Seed for reproducible results. Same prompt and seed usually generate the same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"standard","description":"Type of 3D mesh generation. 'standard' produces a regular high-detail mesh; 'lowpoly' produces a low-poly mesh optimized for cleaner polygons. When set to 'lowpoly', the remesh controls (topology, target_polycount, should_remesh) are ignored by Meshy.","enum":["standard","lowpoly"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_type","required":false,"type":"enum"},{"default":"triangle","description":"Specify the topology of the generated model. Quad for smooth surfaces, Triangle for detailed geometry.","enum":["quad","triangle"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"topology","required":false,"type":"enum"},{"default":30000,"description":"Target number of polygons in the generated model","enum":null,"is_list":false,"max":300000,"media_kind":null,"min":100,"multiline":false,"name":"target_polycount","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the remesh phase. When false, returns unprocessed triangular mesh.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"should_remesh","required":false,"type":"boolean"},{"default":"auto","description":"Controls symmetry behavior during model generation.","enum":["off","auto","on"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"symmetry_mode","required":false,"type":"enum"},{"default":false,"description":"Generate PBR Maps (metallic, roughness, normal) in addition to base color.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pbr","required":false,"type":"boolean"},{"default":false,"description":"Deprecated: use pose_mode instead. When true, generates a T-pose model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_a_t_pose","required":false,"type":"boolean"},{"default":"","description":"Pose mode for the generated model. 'a-pose' generates an A-pose, 't-pose' generates a T-pose, empty string for no specific pose.","enum":["a-pose","t-pose",""],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pose_mode","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Additional text prompt to guide the texturing process (only used in 'full' mode)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_prompt","required":false,"type":"string"},{"default":null,"description":"2D image to guide the texturing process (only used in 'full' mode)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"texture_image_url","required":false,"type":"string"},{"default":false,"description":"Automatically rig the generated model as a humanoid character. Includes basic walking and running animations. Best results with humanoid characters that have clearly defined limbs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_rigging","required":false,"type":"boolean"},{"default":1.7,"description":"Approximate height of the character in meters. Only used when enable_rigging is true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"rigging_height_meters","required":false,"type":"number"},{"default":false,"description":"Apply an animation preset to the rigged model. Requires enable_rigging to be true.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"},{"default":92,"description":"Animation preset ID from Meshy's library. Only used when enable_animation is true; in that case it must be in [0, 696] (``0`` is the \"Idle\" preset) and is otherwise rejected with a 422. See https://docs.meshy.ai/en/api/animation-library for available action IDs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"animation_action_id","required":false,"type":"integer"},{"default":true,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Meshy","output_kind":"file","output_props":["animation_glb","seed","animation_fbx","rigged_character_glb","basic_animations","prompt","actual_prompt","rigged_character_fbx","thumbnail","rig_task_id","texture_urls","model_glb","model_urls"],"pricing":"","published_at":"2026-02-09T19:27:07.101000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e1285/ItPdnJIwgzjDt76F_HWXf_6ac5e192c97e46cda9c929a829b786e4.jpg","title":"Meshy 6"},{"category":"text-to-audio","description":"Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","endpoint_id":"fal-ai/minimax-music","family":"","inputs":[{"default":null,"description":"Lyrics with optional formatting. You can use a newline to separate each line of lyrics. You can use two newlines to add a pause between lines. You can use double hash marks (##) at the beginning and end of the lyrics to add accompaniment. Maximum 600 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference song, should contain music and vocals. Must be a .wav or .mp3 file longer than 15 seconds.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"reference_audio_url","required":true,"type":"string"}],"lab":"Minimax","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2024-12-17T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9226/ErX7ZBppvx3nKC_mTIZOs_5HfTRVWx.png","title":"MiniMax (Hailuo AI) Music"},{"category":"text-to-audio","description":"Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","endpoint_id":"fal-ai/minimax-music/v1.5","family":"","inputs":[{"default":null,"description":"Lyrics, supports [intro][verse][chorus][bridge][outro] sections. 10-600 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Control music generation. 10-3000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"lyrics_prompt","required":true,"type":"string"}],"lab":"Minimax","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-09-11T22:14:58.124000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cc/aUmpKwGz4nPeB6JqmAyxr_pKYFLz4u.png","title":"MiniMax (Hailuo AI) Music v1.5"},{"category":"text-to-audio","description":"Generate music from text prompts using the MiniMax Music 2.0 model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","endpoint_id":"fal-ai/minimax-music/v2","family":"","inputs":[{"default":null,"description":"A description of the music, specifying style, mood, and scenario. 10-300 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Lyrics of the song. Use n to separate lines. You may add structure tags like [Intro], [Verse], [Chorus], [Bridge], [Outro] to enhance the arrangement. 10-3000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics_prompt","required":true,"type":"string"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-10-30T22:33:42.886000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/jnrLOiQsmRXqYCI_haHe5_63de465a7ccb447bb3bf9ed6c0c1c88e.jpg","title":"Minimax Music"},{"category":"text-to-audio","description":"MiniMax Music 2.5 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.","endpoint_id":"fal-ai/minimax-music/v2.5","family":"Music","inputs":[{"default":null,"description":"A description of the music style, mood, genre, and scenario. Max 2000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Lyrics of the song. Use \\n to separate lines. Supports structure tags: [Intro], [Verse], [Pre Chorus], [Chorus], [Bridge], [Outro], [Interlude], [Hook], [Break], [Solo], [Inst]. Max 3500 characters. Required when is_instrumental is false and lyrics_optimizer is false.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics","required":false,"type":"string"},{"default":false,"description":"When true, generates vocal-free instrumental music.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_instrumental","required":false,"type":"boolean"},{"default":false,"description":"When true and lyrics is empty, auto-generates lyrics from the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"lyrics_optimizer","required":false,"type":"boolean"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-04-11T06:22:56.644000+00:00","thumbnail":"https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a959abf%2F6tnoknThTQqVLnqwuX7Xv_97eaac1b47904e9cb8f02fedba07132e.jpg/tr:w-1920,q-80/6tnoknThTQqVLnqwuX7Xv_97eaac1b47904e9cb8f02fedba07132e.webp","title":"Minimax Music 2.5"},{"category":"text-to-audio","description":"MiniMax Music 2.6 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.","endpoint_id":"fal-ai/minimax-music/v2.6","family":"Music","inputs":[{"default":null,"description":"A description of the music style, mood, genre, and scenario. 10-2000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Lyrics of the song. Use \\n to separate lines. Supports structure tags: [Intro], [Verse], [Pre Chorus], [Chorus], [Post Chorus], [Hook], [Bridge], [Interlude], [Transition], [Build Up], [Break], [Inst], [Solo], [Outro]. Max 3500 characters. Required when is_instrumental is false.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"lyrics","required":false,"type":"string"},{"default":false,"description":"When true and lyrics is empty, auto-generates lyrics from the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"lyrics_optimizer","required":false,"type":"boolean"},{"default":false,"description":"When true, generates vocal-free instrumental music.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_instrumental","required":false,"type":"boolean"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-04-11T06:21:38.902000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a959abf/bBuGvGbMCy6eYzC8n05Ql_7f5c08f2be3f495cb9847f89217309a8.jpg","title":"Minimax Music 2.6"},{"category":"image-to-video","description":"Create blazing fast and economical videos with MiniMax Hailuo-02 Image To Video API at 512p resolution","endpoint_id":"fal-ai/minimax/hailuo-02-fast/image-to-video","family":"Hailuo 2 Standard","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"6","description":"The duration of the video in seconds. 10 seconds videos are not supported for 1080p resolution.","enum":["6","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"For each second of video generated at 512P, it will cost roughly $0.017/sec","published_at":"2025-08-06T17:29:12.950000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f921d/RHcsJffErSrCYhfAxUF1Y_Y4MdqvFW.png","title":"Minimax"},{"category":"image-to-video","description":"MiniMax Hailuo-02 Image To Video API (Pro, 1080p): Advanced image-to-video generation model with 1080p resolution","endpoint_id":"fal-ai/minimax/hailuo-02/pro/image-to-video","family":"Hailuo 2 Pro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":null,"description":"Optional URL of the image to use as the last frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"For each second of video generated, it will cost $0.08/sec. A single 6 second video will cost $0.48/video.","published_at":"2025-06-18T00:46:50.998000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"MiniMax Hailuo 02 [Pro] (Image to Video)"},{"category":"text-to-video","description":"MiniMax Hailuo-02 Text To Video API (Pro, 1080p): Advanced video generation model with 1080p resolution","endpoint_id":"fal-ai/minimax/hailuo-02/pro/text-to-video","family":"Hailuo 2 Pro","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"For each second of video generated, it will cost $0.08/sec. A single 6 second video will cost $0.48/video.","published_at":"2025-06-18T00:41:11.159000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"MiniMax Hailuo 02 [Pro] (Text to Video)"},{"category":"image-to-video","description":"MiniMax Hailuo-02 Image To Video API (Standard, 768p, 512p): Advanced image-to-video generation model with 768p and 512p resolutions","endpoint_id":"fal-ai/minimax/hailuo-02/standard/image-to-video","family":"Hailuo 2 Standard","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"6","description":"The duration of the video in seconds. 10 seconds videos are not supported for 1080p resolution.","enum":["6","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":"768P","description":"The resolution of the generated video.","enum":["512P","768P"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Optional URL of the image to use as the last frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"For each second of video generated at 768P, it will cost $0.045/sec. For each second of video generated at 512P, it will cost roughly $0.017/sec. A single 6 second 768p video will cost $0.27/video.","published_at":"2025-06-18T00:47:27.952000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale.jpg","title":"MiniMax Hailuo 02 [Standard] (Image to Video)"},{"category":"text-to-video","description":"MiniMax Hailuo-02 Text To Video API (Standard, 768p): Advanced video generation model with 768p resolution","endpoint_id":"fal-ai/minimax/hailuo-02/standard/text-to-video","family":"Hailuo 2 Standard","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"6","description":"The duration of the video in seconds. 10 seconds videos are not supported for 1080p resolution.","enum":["6","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"For each second of video generated, it will cost $0.045/sec. A single 6 second video will cost $0.27/video.","published_at":"2025-06-18T00:40:08.840000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","title":"MiniMax Hailuo 02 [Standard] (Text to Video)"},{"category":"image-to-video","description":"MiniMax Hailuo-2.3-Fast Image To Video API (Pro, 1080p): Advanced fast image-to-video generation model with 1080p resolution","endpoint_id":"fal-ai/minimax/hailuo-2.3-fast/pro/image-to-video","family":"Hailuo 2.3 Pro","inputs":[{"default":null,"description":"Text prompt for video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-10-27T13:08:20.657000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/37ZHJodysdkE5NcfUc3fu_5731672b9b3c4e47b4b851a5145e5d3c.jpg","title":"MiniMax Hailuo 2.3 Fast [Pro] (Image to Video)"},{"category":"image-to-video","description":"MiniMax Hailuo-2.3-Fast Image To Video API (Standard, 768p): Advanced fast image-to-video generation model with 768p resolution","endpoint_id":"fal-ai/minimax/hailuo-2.3-fast/standard/image-to-video","family":"Hailuo 2.3 Standard","inputs":[{"default":null,"description":"Text prompt for video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"6","description":"The duration of the video in seconds.","enum":["6","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.19 per 6 second video generation, and a $0.32 per 10 second video generation.","published_at":"2025-10-27T13:12:54.242000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/wEXBG5qZxdJ1Ed5P-EWYT_c69665fc168a437bb53d99ae8534eabe.jpg","title":"MiniMax Hailuo 2.3 Fast [Standard] (Image to Video)"},{"category":"image-to-video","description":"MiniMax Hailuo-2.3 Image To Video API (Pro, 1080p): Advanced image-to-video generation model with 1080p resolution","endpoint_id":"fal-ai/minimax/hailuo-2.3/pro/image-to-video","family":"Hailuo 2.3 Pro","inputs":[{"default":null,"description":"Text prompt for video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.49 per video generation.","published_at":"2025-10-27T13:16:08.044000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/tFrccsrBCt7X_80Je77Ie_a073f11dc9354f5eab801768841430a9.jpg","title":"MiniMax Hailuo 2.3 [Pro] (Image to Video)"},{"category":"text-to-video","description":"MiniMax Hailuo-2.3 Text To Video API (Pro, 1080p): Advanced text-to-video generation model with 1080p resolution","endpoint_id":"fal-ai/minimax/hailuo-2.3/pro/text-to-video","family":"Hailuo 2.3 Pro","inputs":[{"default":null,"description":"Text prompt for video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.49 per video generation.","published_at":"2025-10-27T13:05:46.983000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/x_n_LT1ApmpYZnZw8sdNq_0147471d0d7e4bbba8780820dee6a3da.jpg","title":"MiniMax Hailuo 2.3 [Pro] (Text to Video)"},{"category":"image-to-video","description":"MiniMax Hailuo-2.3 Image To Video API (Standard, 768p): Advanced image-to-video generation model with 768p resolution","endpoint_id":"fal-ai/minimax/hailuo-2.3/standard/image-to-video","family":"Hailuo 2.3 Standard","inputs":[{"default":null,"description":"Text prompt for video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":"6","description":"The duration of the video in seconds.","enum":["6","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.28 per 6 second video generation, and a $0.56 per 10 second video generation.","published_at":"2025-10-27T13:11:19.864000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/7kDvX2hsHnnUu9mSt-I_C_3a18467c2b234f6590e01edd53840f2d.jpg","title":"MiniMax Hailuo 2.3 [Standard] (Image to Video)"},{"category":"text-to-video","description":"MiniMax Hailuo-2.3 Text To Video API (Standard, 768p): Advanced text-to-video generation model with 768p resolution","endpoint_id":"fal-ai/minimax/hailuo-2.3/standard/text-to-video","family":"Hailuo 2.3 Standard","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"},{"default":"6","description":"The duration of the video in seconds.","enum":["6","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.28 per 6 second video generation, and a $0.56 per 10 second video generation.","published_at":"2025-10-27T13:06:48.176000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/j3hSIKLqmWT7NXmIwTUQ0_1ec8fc1d7a53473fac7c2892ff459693.jpg","title":"MiniMax Hailuo 2.3 [Standard] (Text to Video)"},{"category":"text-to-image","description":"Generate high quality images from text prompts using MiniMax Image-01. Longer text prompts will result in better quality images.","endpoint_id":"fal-ai/minimax/image-01","family":"","inputs":[{"default":null,"description":"Text prompt for image generation (max 1500 characters)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Aspect ratio of the generated image","enum":["1:1","16:9","4:3","3:2","2:3","3:4","9:16","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9)","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"Whether to enable automatic prompt optimization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"images","output_props":["images"],"pricing":"For 1 image your request will cost 0.01$. For $1 you can run this model approximately 100 times.","published_at":"2025-05-06T16:11:12.334000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/minimax-image/minimax.webp","title":"MiniMax (Hailuo AI) Text to Image"},{"category":"image-to-image","description":"Generate images from text and a reference image using MiniMax Image-01 for consistent character appearance.","endpoint_id":"fal-ai/minimax/image-01/subject-reference","family":"","inputs":[{"default":null,"description":"Text prompt for image generation (max 1500 characters)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the subject reference image to use for consistent character appearance","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"1:1","description":"Aspect ratio of the generated image","enum":["1:1","16:9","4:3","3:2","2:3","3:4","9:16","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-9)","enum":null,"is_list":false,"max":9,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"Whether to enable automatic prompt optimization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-05-06T16:14:51.517000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-3.jpeg","title":"Minimax Image Subject Reference"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/preview/speech-2.5-hd","family":"","inputs":[{"default":null,"description":"Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Persian","Filipino","Tamil","Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"","published_at":"2025-08-11T09:41:03.032000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d1/HmXRZPRtPK9mGJUDtlnu0_59gznpUE.png","title":"Minimax"},{"category":"text-to-speech","description":"Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/preview/speech-2.5-turbo","family":"","inputs":[{"default":null,"description":"Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Persian","Filipino","Tamil","Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"","published_at":"2025-08-11T09:33:12.088000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/CVkTH0KATZIyuBLbfuVz4_ca6fAKxo.png","title":"Minimax"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/speech-02-hd","family":"","inputs":[{"default":null,"description":"Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"Your request will cost $0.1 per 1000 characters.","published_at":"2025-05-06T16:17:49.560000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b5/Li_VoZtaOd5__F9GMv1O4_yPTcO4eQ.png","title":"MiniMax Speech-02 HD"},{"category":"text-to-speech","description":"Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/speech-02-turbo","family":"","inputs":[{"default":null,"description":"Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"Your request will cost $0.06 per 1000 character.","published_at":"2025-05-06T16:20:17.682000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b6/054Hl3dIeF1BDfoCszbuS_1WPpjHNS.png","title":"MiniMax Speech-02 Turbo"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/speech-2.6-hd","family":"","inputs":[{"default":null,"description":"Text to convert to speech. Paragraph breaks should be marked with newline characters. **NOTE**: You can customize speech pauses by adding markers in the form `<#x#>`, where `x` is the pause duration in seconds. Valid range: `[0.01, 99.99]`, up to two decimal places. Pause markers must be placed between speakable text segments and cannot be used consecutively.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"},{"default":null,"description":"Loudness normalization settings for the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normalization_setting","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"","published_at":"2025-10-29T14:33:02.910000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/SjejS2pB-SmgrWVM-2UQ9_0b44c0c9f723499297b9f93624fa899b.jpg","title":"MiniMax Speech 2.6 [HD]"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/speech-2.6-turbo","family":"","inputs":[{"default":null,"description":"Text to convert to speech. Paragraph breaks should be marked with newline characters. **NOTE**: You can customize speech pauses by adding markers in the form `<#x#>`, where `x` is the pause duration in seconds. Valid range: `[0.01, 99.99]`, up to two decimal places. Pause markers must be placed between speakable text segments and cannot be used consecutively.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"},{"default":null,"description":"Loudness normalization settings for the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normalization_setting","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"","published_at":"2025-10-29T14:37:37.968000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/i6OK72M3MRgCjSurJLlYT_018f5a573af24e69aadfc9a9b559a110.jpg","title":"MiniMax Speech 2.6 [Turbo]"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/speech-2.8-hd","family":"","inputs":[{"default":null,"description":"Text to convert to speech. Use `<#x#>` for pauses (x = 0.01-99.99 seconds). Supports interjection tags: `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, `(yawns)`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"},{"default":null,"description":"Loudness normalization settings for the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normalization_setting","required":false,"type":"json"},{"default":null,"description":"Voice modification settings to adjust pitch, intensity, and timbre.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_modify","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"","published_at":"2026-02-04T00:13:29.621000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d0e4a/5FhhsQ0BicVC_DZ_BDLGL_895a8e6af34848f8844c20244c3e4672.jpg","title":"MiniMax Speech 2.8 [HD]"},{"category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-2.8 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/speech-2.8-turbo","family":"","inputs":[{"default":null,"description":"Text to convert to speech. Use `<#x#>` for pauses (x = 0.01-99.99 seconds). Supports interjection tags: `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, `(yawns)`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"{\"english_normalization\": false, \"pitch\": 0, \"speed\": 1, \"voice_id\": \"Wise_Woman\", \"vol\": 1}","description":"Voice configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_setting","required":false,"type":"json"},{"default":null,"description":"Audio configuration settings","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"json"},{"default":null,"description":"Enhance recognition of specified languages and dialects","enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language_boost","required":false,"type":"enum"},{"default":"hex","description":"Format of the output content (non-streaming only)","enum":["url","hex"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Custom pronunciation dictionary for text replacement","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pronunciation_dict","required":false,"type":"json"},{"default":null,"description":"Loudness normalization settings for the audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normalization_setting","required":false,"type":"json"},{"default":null,"description":"Voice modification settings to adjust pitch, intensity, and timbre.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_modify","required":false,"type":"json"}],"lab":"Minimax","output_kind":"audio","output_props":["audio","duration_ms"],"pricing":"","published_at":"2026-02-04T00:09:54.525000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d0e23/l9QaO81QWM5lp_w3ZnahE_efa53369ffad488ba50146e6f9567df1.jpg","title":"MiniMax Speech 2.8 [Turbo]"},{"category":"text-to-video","description":"Generate video clips from your prompts using MiniMax model","endpoint_id":"fal-ai/minimax/video-01","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/red_clouds.jpg","title":"MiniMax (Hailuo AI) Video 01"},{"category":"text-to-video","description":"Generate video clips more accurately with respect to natural language descriptions and using camera movement instructions for shot control.","endpoint_id":"fal-ai/minimax/video-01-director","family":"","inputs":[{"default":null,"description":"Text prompt for video generation. Camera movement instructions can be added using square brackets (e.g. [Pan left] or [Zoom in]). You can use up to 3 combined movements per prompt. Supported movements: Truck left/right, Pan left/right, Push in/Pull out, Pedestal up/down, Tilt up/down, Zoom in/out, Shake, Tracking shot, Static shot. For example: [Truck left, Pan right, Zoom in]. For a more detailed guide, refer https://sixth-switch-2ac.notion.site/T2V-01-Director-Model-Tutorial-with-camera-moveme","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-02-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/red_clouds.jpg","title":"MiniMax (Hailuo AI) Video 01 Director"},{"category":"image-to-video","description":"Generate video clips more accurately with respect to initial image, natural language descriptions, and using camera movement instructions for shot control.","endpoint_id":"fal-ai/minimax/video-01-director/image-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation. Camera movement instructions can be added using square brackets (e.g. [Pan left] or [Zoom in]). You can use up to 3 combined movements per prompt. Supported movements: Truck left/right, Pan left/right, Push in/Pull out, Pedestal up/down, Tilt up/down, Zoom in/out, Shake, Tracking shot, Static shot. For example: [Truck left, Pan right, Zoom in]. For a more detailed guide, refer https://sixth-switch-2ac.notion.site/T2V-01-Director-Model-Tutorial-with-camera-moveme","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-02-24T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/red_clouds.jpg","title":"MiniMax (Hailuo AI) Video 01 Director - Image to Video"},{"category":"text-to-video","description":"Generate video clips from your prompts using MiniMax model","endpoint_id":"fal-ai/minimax/video-01-live","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-12-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_016.jpg","title":"MiniMax (Hailuo AI) Video 01 Live"},{"category":"image-to-video","description":"Generate video clips from your images using MiniMax Video model","endpoint_id":"fal-ai/minimax/video-01-live/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-12-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_016.jpg","title":"MiniMax (Hailuo AI) Video 01"},{"category":"image-to-video","description":"Generate video clips maintaining consistent, realistic facial features and identity across dynamic video content","endpoint_id":"fal-ai/minimax/video-01-subject-reference","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the subject reference image to use for consistent subject appearance","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"subject_reference_image_url","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-01-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/minimax-video-01-subject-reference.webp","title":"MiniMax (Hailuo AI) Video 01 Subject Reference"},{"category":"image-to-video","description":"Generate video clips from your images using MiniMax Video model","endpoint_id":"fal-ai/minimax/video-01/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":true,"description":"Whether to use the model's prompt optimizer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_optimizer","required":false,"type":"boolean"}],"lab":"Minimax","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-10-30T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/minimax-video-01-image-to-video.webp","title":"MiniMax (Hailuo AI) Video 01"},{"category":"text-to-speech","description":"Clone a voice from a sample audio and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/voice-clone","family":"","inputs":[{"default":null,"description":"URL of the input audio file for voice cloning. Should be at least 10 seconds\n            long. To retain the voice permanently, use it with a TTS (text-to-speech)\n            endpoint at least once within 7 days. Otherwise, it will be\n            automatically deleted.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"},{"default":false,"description":"Enable noise reduction for the cloned voice","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"noise_reduction","required":false,"type":"boolean"},{"default":false,"description":"Enable volume normalization for the cloned voice","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"need_volume_normalization","required":false,"type":"boolean"},{"default":null,"description":"Text validation accuracy threshold (0-1)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"accuracy","required":false,"type":"number"},{"default":"Hello, this is a preview of your cloned voice! I hope you like it!","description":"Text to generate a TTS preview with the cloned voice (optional)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":false,"type":"string"},{"default":"speech-02-hd","description":"TTS model to use for preview. Options: speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo","enum":["speech-02-hd","speech-02-turbo","speech-01-hd","speech-01-turbo"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"}],"lab":"Minimax","output_kind":"audio","output_props":["custom_voice_id","audio"],"pricing":"Each voice clone request will cost $1.5, with preview inputs costing $0.3 per 1000 characters.","published_at":"2025-05-06T16:22:37.683000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/minimax-tts/minimax-tts.webp","title":"MiniMax Voice Cloning"},{"category":"text-to-speech","description":"Design a personalized voice from a text description, and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.","endpoint_id":"fal-ai/minimax/voice-design","family":"","inputs":[{"default":null,"description":"Voice description prompt for generating a personalized voice","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Text for audio preview. Limited to 500 characters. A fee of $30 per 1M characters will be charged for the generation of the preview audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"preview_text","required":true,"type":"string"}],"lab":"Minimax","output_kind":"audio","output_props":["custom_voice_id","audio"],"pricing":"Designing a voice will cost $3 per created voice, with 0.03 per 1000 preview characters","published_at":"2025-07-18T21:21:52.686000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922c/aV3yMfiK-rdJiNGqmfVru_lPguf8oY.png","title":"MiniMax Voice Design"},{"category":"video-to-video","description":"MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.","endpoint_id":"fal-ai/mmaudio-v2","family":"mmaudio","inputs":[{"default":null,"description":"The URL of the video to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The prompt to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":25,"description":"The number of steps to generate the audio for.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_steps","required":false,"type":"integer"},{"default":8,"description":"The duration of the audio to generate.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":4.5,"description":"The strength of Classifier Free Guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"cfg_strength","required":false,"type":"number"},{"default":false,"description":"Whether to mask away the clip.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mask_away_clip","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-12-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/mmaudio-v2.webp","title":"MMAudio V2"},{"category":"text-to-audio","description":"MMAudio generates synchronized audio given text inputs. It can generate sounds described by a prompt.","endpoint_id":"fal-ai/mmaudio-v2/text-to-audio","family":"mmaudio","inputs":[{"default":null,"description":"The prompt to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":65535,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":25,"description":"The number of steps to generate the audio for.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"num_steps","required":false,"type":"integer"},{"default":8,"description":"The duration of the audio to generate.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":4.5,"description":"The strength of Classifier Free Guidance.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"cfg_strength","required":false,"type":"number"},{"default":false,"description":"Whether to mask away the clip.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mask_away_clip","required":false,"type":"boolean"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2024-12-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/mmaudio-v2.webp","title":"MMAudio V2 Text to Audio"},{"category":"vision","description":"MoonDreamNext is a multimodal vision-language model for captioning, gaze detection, bbox detection, point detection, and more.","endpoint_id":"fal-ai/moondream-next","family":"","inputs":[{"default":null,"description":"Image URL to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"caption","description":"Type of task to perform","enum":["caption","query"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"task_type","required":false,"type":"enum"},{"default":null,"description":"Prompt for query task","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":64,"description":"Maximum number of tokens to generate","enum":null,"is_list":false,"max":512,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Moondream","output_kind":"text","output_props":["output"],"pricing":"","published_at":"2025-01-09T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/moondreamnext/moondream-next.webp","title":"MoonDreamNext"},{"category":"vision","description":"MoonDreamNext Batch is a multimodal vision-language model for batch captioning.","endpoint_id":"fal-ai/moondream-next/batch","family":"","inputs":[{"default":null,"description":"List of image URLs to be processed (maximum 32 images)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"images_data_url","required":true,"type":"string"},{"default":null,"description":"Single prompt to apply to all images","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":64,"description":"Maximum number of tokens to generate","enum":null,"is_list":false,"max":512,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Moondream","output_kind":"json","output_props":["outputs","captions_file"],"pricing":"","published_at":"2025-01-17T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/moondreamnext/moondream-next.webp","title":"MoonDreamNext Batch"},{"category":"image-to-image","description":"MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.","endpoint_id":"fal-ai/moondream-next/detection","family":"","inputs":[{"default":null,"description":"Image URL to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Type of detection to perform","enum":["bbox_detection","point_detection","gaze_detection"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"task_type","required":true,"type":"enum"},{"default":null,"description":"Text description of what to detect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detection_prompt","required":true,"type":"string"},{"default":false,"description":"Whether to use ensemble for gaze detection","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_ensemble","required":false,"type":"boolean"},{"default":false,"description":"Whether to combine points into a single point for point detection. This has no effect for bbox detection or gaze detection.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"combine_points","required":false,"type":"boolean"},{"default":true,"description":"Whether to show visualization for detection","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"show_visualization","required":false,"type":"boolean"}],"lab":"Moondream","output_kind":"image","output_props":["image","text_output"],"pricing":"","published_at":"2025-01-09T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/moondreamnext/moondream-next.webp","title":"MoonDreamNext Detection"},{"category":"vision","description":"Answer questions from the images.","endpoint_id":"fal-ai/moondream/batched","family":"","inputs":[{"default":"vikhyatk/moondream2","description":"Model ID to use for inference","enum":["vikhyatk/moondream2","fal-ai/moondream2-docci"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_id","required":false,"type":"enum"},{"default":null,"description":"List of input prompts and image URLs","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"inputs","required":true,"type":"json"},{"default":64,"description":"Maximum number of new tokens to generate","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":32,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.2,"description":"Temperature for sampling","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1,"description":"Top P for sampling","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":1,"description":"Repetition penalty for sampling","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"}],"lab":"","output_kind":"json","output_props":["timings","outputs","filenames","partial"],"pricing":"","published_at":"2024-03-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/moondream.jpeg","title":"Moondream"},{"category":"vision","description":"Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.","endpoint_id":"fal-ai/moondream2","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Moondream","output_kind":"text","output_props":["output"],"pricing":"","published_at":"2025-04-26T07:09:30.111000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Moondream2"},{"category":"vision","description":"Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.","endpoint_id":"fal-ai/moondream2/object-detection","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Object to be detected in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"object","required":true,"type":"string"}],"lab":"Moondream","output_kind":"image","output_props":["objects","image"],"pricing":"","published_at":"2025-04-26T07:09:05.554000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Moondream2"},{"category":"vision","description":"Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.","endpoint_id":"fal-ai/moondream2/point-object-detection","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Object to be detected in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"object","required":true,"type":"string"}],"lab":"Moondream","output_kind":"image","output_props":["objects","image"],"pricing":"","published_at":"2025-04-26T07:09:10.417000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Moondream2"},{"category":"vision","description":"Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.","endpoint_id":"fal-ai/moondream2/visual-query","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Query to be asked in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Moondream","output_kind":"text","output_props":["output"],"pricing":"","published_at":"2025-04-26T07:12:07.007000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Moondream2"},{"category":"vision","description":"Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.","endpoint_id":"fal-ai/moondream3-preview/caption","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"normal","description":"Length of the caption to generate","enum":["short","normal","long"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"length","required":false,"type":"enum"},{"default":null,"description":"Sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If not set, defaults to 0.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"Nucleus sampling probability mass to use, between 0 and 1.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"Moondream","output_kind":"json","output_props":["usage_info","output","finish_reason"],"pricing":"Your request will cost $0.4 per million input tokens, and $3.5 per million output tokens.","published_at":"2025-10-09T20:50:44.363000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/MThU-RSBqLWpvP60bOvk__d2902b4bea314d49bb01fe92584a0922.jpg","title":"Moondream3 Preview [Caption]"},{"category":"vision","description":"Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.","endpoint_id":"fal-ai/moondream3-preview/detect","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Object to be detected in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to preview the output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preview","required":false,"type":"boolean"}],"lab":"Moondream","output_kind":"image","output_props":["usage_info","objects","image","finish_reason"],"pricing":"Your request will cost $0.4 per million input tokens, and $3.5 per million output tokens.","published_at":"2025-10-09T20:57:37.622000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/Ma6NXbAm7Gi18CcciKraL_c5133f964896437ca8fdb88652c1a3b9.jpg","title":"Moondream3 Preview [Detect]"},{"category":"vision","description":"Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.","endpoint_id":"fal-ai/moondream3-preview/point","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Object to be located in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to preview the output","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preview","required":false,"type":"boolean"}],"lab":"Moondream","output_kind":"image","output_props":["usage_info","image","points","finish_reason"],"pricing":"Your request will cost $0.4 per million input tokens, and $3.5 per million output tokens.","published_at":"2025-10-09T20:55:39.296000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/r903D3raEamwM13Bmn1Lp_fa12f25ab96c41008fc48492bbdbbea2.jpg","title":"Moondream3 Preview [Point]"},{"category":"vision","description":"Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.","endpoint_id":"fal-ai/moondream3-preview/query","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Query to be asked in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to include detailed reasoning behind the answer","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":null,"description":"Sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If not set, defaults to 0.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"Nucleus sampling probability mass to use, between 0 and 1.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"Moondream","output_kind":"json","output_props":["usage_info","output","finish_reason","reasoning"],"pricing":"Your request will cost $0.4 per million input tokens, and $3.5 per million output tokens.","published_at":"2025-10-09T20:54:23.184000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/nWpJhvShCa7NcOUhC0JJ-_7dec4ab5fb2c49869d74af99dfa66bf4.jpg","title":"Moondream 3 Preview [Query]"},{"category":"image-to-image","description":"Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.","endpoint_id":"fal-ai/moondream3-preview/segment","family":"","inputs":[{"default":null,"description":"URL of the image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Object to be segmented in the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"object","required":true,"type":"string"},{"default":null,"description":"Spatial references to guide the segmentation. By feeding in references you can help the segmentation process. Must be either list of Point object with x and y members, or list of arrays containing either 2 floats (x,y) or 4 floats (x1,y1,x2,y2). \n**NOTE**: You can also use the [**point endpoint**](https://fal.ai/models/fal-ai/moondream3-preview/point) to get points for the objects, and pass them in here.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"spatial_references","required":false,"type":"json"},{"default":null,"description":"Sampling settings for the segmentation model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"settings","required":false,"type":"json"},{"default":false,"description":"Whether to preview the output and return a binary mask of the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preview","required":false,"type":"boolean"}],"lab":"Moondream","output_kind":"image","output_props":["usage_info","image","finish_reason","bbox","path"],"pricing":"Your request will cost $0.4 per million input tokens, and $3.5 per million output tokens.","published_at":"2025-12-12T18:23:06.363000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86094c/GEhsfrfki4ZTLUFdUC9qa_7e2a85f8b4b74946abf7c31e813fefb9.jpg","title":"Moondream3 Preview [Segment]"},{"category":"image-to-video","description":"MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.","endpoint_id":"fal-ai/musetalk","family":"","inputs":[{"default":null,"description":"URL of the source video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"source_video_url","required":true,"type":"string"},{"default":null,"description":"URL of the audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-04-11T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9227/8XcYHHeV-25IQer_NtAT9_VJRe8zYm.png","title":"MuseTalk"},{"category":"image-to-image","description":"Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.","endpoint_id":"fal-ai/nafnet/deblur","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"seed to be used for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/HyeESWwRpMtc-Q0fVsDdt_2de9ad23b7894d18abc770358c32eee7.webp","title":"NAFNet-deblur"},{"category":"image-to-image","description":"Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.","endpoint_id":"fal-ai/nafnet/denoise","family":"","inputs":[{"default":null,"description":"URL of image to be used for relighting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"seed to be used for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/HyeESWwRpMtc-Q0fVsDdt_2de9ad23b7894d18abc770358c32eee7.webp","title":"NAFNet-denoise"},{"category":"text-to-image","description":"Google's famous original image generation and editing model","endpoint_id":"fal-ai/nano-banana","family":"Nano Banana","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["description","images"],"pricing":"Your request will cost $0.039 per image. For $1.00, you can run this model 25 times.","published_at":"2025-08-19T22:11:04.357000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91a7/UOFMBU7hW6hqvFYvXHH-o_MZBJlwLt.png","title":"Nano Banana"},{"category":"text-to-image","description":"Nano Banana 2 is Google's new state-of-the-art fast image generation and editing model","endpoint_id":"fal-ai/nano-banana-2","family":"Nano Banana 2","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use \"auto\" to let the model decide based on the prompt.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["0.5K","1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.08 per image. For $1.00, you can run this model 12 times. 2K and 4K outputs will be charged at 1.5 times and 2 times the standard rate, respectively. 0.5K (512px) resolution outputs will be charged at 0.75 times the standard rate. If web search is used, an additional $0.015 will be charged. If high thinking is used, an additional $0.002 will be charged. Note: Pricing is subject to change.","published_at":"2026-02-26T16:08:01.361000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a900b9e/ptbZcVWIQ_fXGGHfv8Zez_0ea5ca41bdf143a29e21e30a53120672.jpg","title":"Nano Banana 2"},{"category":"image-to-image","description":"Nano Banana 2 is Google's new state-of-the-art image generation and editing model","endpoint_id":"fal-ai/nano-banana-2/edit","family":"Nano Banana 2","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing. Optional when at least one of `video_url`, `audio_url`, or `pdf_url` is provided.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["0.5K","1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Optional video to use as input context. Accepts an http(s)/data URL to a video file (downloaded and sent inline, max 15MB) or a YouTube URL (passed through to the model without downloading).","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":false,"type":"string"},{"default":null,"description":"Optional audio file to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":null,"description":"Optional PDF document to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"pdf_url","required":false,"type":"string"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.08 per image. For $1.00, you can run this model 12 times. 2K and 4K outputs will be charged at 1.5 times and 2 times the standard rate, respectively. 0.5K (512px) resolution outputs will be charged at 0.75 times the standard rate. If web search is used, an additional $0.015 will be charged. If high thinking is used, an additional $0.002 will be charged. Note: Pricing is subject to change.","published_at":"2026-02-26T16:20:09.685000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a900b75/DHb_RgXoXsYLdvzQz6mdn_95e87a44239c43448939b4c382dd957c.jpg","title":"Nano Banana 2"},{"category":"text-to-image","description":"Nano Banana Pro is Google's new state-of-the-art image generation and editing model","endpoint_id":"fal-ai/nano-banana-pro","family":"Nano Banana Pro","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"1:1","description":"The aspect ratio of the generated image.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.15 per image. For $1.00, you can run this model 7 times. 4K outputs will be charged at double the standard rate. If web search is used, an additional $0.015 will be charged. Note: Pricing may change in the future.","published_at":"2025-11-20T14:24:45.001000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8691ce/SR0_u1zPJbx8jCIO6bJR0_8c83f0d66bbd48f3b55f825117941f84.jpg","title":"Nano Banana Pro"},{"category":"image-to-image","description":"Nano Banana Pro is Google's new state-of-the-art image generation and editing model","endpoint_id":"fal-ai/nano-banana-pro/edit","family":"Nano Banana Pro","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":"1K","description":"The resolution of the image to generate.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":false,"description":"Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Your request will cost $0.15 per image. For $1.00, you can run this model 7 times. 4K outputs will be charged at double the standard rate. If web search is used, an additional $0.015 will be charged. Note: Pricing may change in the future.","published_at":"2025-11-20T14:27:03.344000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f0f/p3rXI18zMYTBz1M0qP2h4_b9a2087ce0b64cd788cb5ec067edc26e.jpg","title":"Nano Banana Pro"},{"category":"image-to-image","description":"Google's famous original image generation and editing model","endpoint_id":"fal-ai/nano-banana/edit","family":"Nano Banana","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":false,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"}],"lab":"Google","output_kind":"images","output_props":["description","images"],"pricing":"Your request will cost $0.039 per image. For $1.00, you can run this model 25 times.","published_at":"2025-08-19T22:16:18.949000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a4a/mjFnPPGaaBaf5OHrDSoSO_ns4MA9ac.png","title":"Nano Banana"},{"category":"vision","description":"Nemotron-Labs-Diffusion-VLM-8B is the vision-language extension of the Nemotron-Labs-Diffusion family.","endpoint_id":"fal-ai/nemotron-diffusion-vlm","family":"","inputs":[{"default":null,"description":"URL of the image to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt to answer about the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":512,"description":"Maximum number of tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":256,"description":"Number of diffusion decoding steps. Defaults to 256, rounded up only when omitted and required by the upstream block schedule. Explicit values must be at least max_tokens / block_length and divisible by max_tokens / block_length.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":32,"description":"Block length used by diffusion decoding.","enum":null,"is_list":false,"max":128,"media_kind":null,"min":8,"multiline":false,"name":"block_length","required":false,"type":"integer"},{"default":0.9,"description":"Confidence threshold used by diffusion decoding.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"threshold","required":false,"type":"number"}],"lab":"NVIDIA","output_kind":"json","output_props":["timings","output","usage"],"pricing":"","published_at":"2026-05-21T15:14:10.095000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afefa/Q7HRLq1tyeWeIJGDtTJwK_2a24d91060104ab08fc7f9e167c2f9a4.jpg","title":"Nemotron Diffusion Vlm"},{"category":"text-to-image","description":"Nucleus-Image is a text-to-image generation model built on a sparse mixture-of-experts (MoE) diffusion transformer architecture.","endpoint_id":"fal-ai/nucleus-image","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use for generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"1:1","description":"The output aspect ratio. Nucleus-Image supports a fixed set of aspect-ratio presets.","enum":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":8,"description":"The classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2026-04-16T10:33:09.199000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9678fe/fJRHXzdVxDGigCg5IhEjo_3023ffcd7fb2429b8efc7948e1563bdb.jpg","title":"Nucleus Image"},{"category":"image-to-image","description":"Removes objects and their visual effects using natural language, replacing them with contextually appropriate content","endpoint_id":"fal-ai/object-removal","family":"","inputs":[{"default":null,"description":"The URL of the image to remove objects from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text description of the object to remove.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"best_quality","description":"Model","enum":["low_quality","medium_quality","high_quality","best_quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":15,"description":"Amount of pixels to expand the mask by. Range: 0-50","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"mask_expansion","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.006 with Low Quality, $0.012 with Medium Quality, $0.018 with High Quality, and $0.024 with Best Quality","published_at":"2025-06-16T20:10:46.926000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"Object Removal"},{"category":"image-to-image","description":"Removes box-selected objects and their visual effects, seamlessly reconstructing the scene with contextually appropriate content.","endpoint_id":"fal-ai/object-removal/bbox","family":"","inputs":[{"default":null,"description":"The URL of the image to remove objects from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"[]","description":"List of bounding box coordinates to erase (only one box prompt is supported)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":"best_quality","description":"Model","enum":["low_quality","medium_quality","high_quality","best_quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":15,"description":"Amount of pixels to expand the mask by. Range: 0-50","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"mask_expansion","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.006 with Low Quality, $0.012 with Medium Quality, $0.018 with High Quality, and $0.024 with Best Quality","published_at":"2025-06-16T20:15:04.257000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"Object Removal"},{"category":"image-to-image","description":"Removes mask-selected objects and their visual effects, seamlessly reconstructing the scene with contextually appropriate content.","endpoint_id":"fal-ai/object-removal/mask","family":"","inputs":[{"default":null,"description":"The URL of the image to remove objects from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask image. White pixels (255) indicate areas to remove.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":"best_quality","description":"Model","enum":["low_quality","medium_quality","high_quality","best_quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":15,"description":"Amount of pixels to expand the mask by. Range: 0-50","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"mask_expansion","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.006 with Low Quality, $0.012 with Medium Quality, $0.018 with High Quality, and $0.024 with Best Quality","published_at":"2025-06-16T20:13:18.407000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"Object Removal"},{"category":"image-to-image","description":"Any pose, any style, any identity","endpoint_id":"fal-ai/omni-zero","family":"","inputs":[{"default":null,"description":"Prompt to guide the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to guide the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Input image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Composition image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"composition_image_url","required":true,"type":"string"},{"default":null,"description":"Style image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"style_image_url","required":true,"type":"string"},{"default":null,"description":"Identity image url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"identity_image_url","required":true,"type":"string"},{"default":0.75,"description":"Image strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_strength","required":false,"type":"number"},{"default":1,"description":"Composition strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"composition_strength","required":false,"type":"number"},{"default":0.5,"description":"Depth strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"depth_strength","required":false,"type":"number"},{"default":1,"description":"Style strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_strength","required":false,"type":"number"},{"default":1,"description":"Face strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_strength","required":false,"type":"number"},{"default":1,"description":"Identity strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"identity_strength","required":false,"type":"number"},{"default":5,"description":"Guidance scale.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":42,"description":"Seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"number_of_images","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-04-25T00:00:00+00:00","thumbnail":"https://pbs.twimg.com/media/GMBtTg8W0AEg_-I?format=jpg&name=medium","title":"Omni Zero"},{"category":"text-to-image","description":"OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!","endpoint_id":"fal-ai/omnigen-v1","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":[],"description":"URL of images to use while generating the image, Use <img><|image_1|></img> for the first image and so on.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1.6,"description":"The Image Guidance scale is a measure of how close you want\n            the model to stick to your input image when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"img_guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","images","prompt","seed","timings"],"pricing":"","published_at":"2024-11-29T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/omnigen-v1.webp","title":"OmniGen v1"},{"category":"text-to-image","description":"OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!","endpoint_id":"fal-ai/omnigen-v2","family":"","inputs":[{"default":null,"description":"The prompt to generate or edit an image. Use specific language like 'Add the bird from image 1 to the desk in image 2' for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":[],"description":"URLs of input images to use for image editing or multi-image generation. Support up to 3 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The Text Guidance scale controls how closely the model follows the text prompt.\n            Higher values make the model stick more closely to the prompt.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"text_guidance_scale","required":false,"type":"number"},{"default":2,"description":"The Image Guidance scale controls how closely the model follows the input images.\n            For image editing: 1.3-2.0, for in-context generation: 2.0-3.0","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"image_guidance_scale","required":false,"type":"number"},{"default":"(((deformed))), blurry, over saturation, bad anatomy, disfigured, poorly drawn face, mutation, mutated, (extra_limb), (ugly), (poorly drawn hands), fused fingers, messy drawing, broken legs censor, censored, censor_bar","description":"Negative prompt to guide what should not be in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":0,"description":"CFG range start value.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_range_start","required":false,"type":"number"},{"default":1,"description":"CFG range end value.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg_range_end","required":false,"type":"number"},{"default":"euler","description":"The scheduler to use for the diffusion process.","enum":["euler","dpmsolver"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-06-25T11:26:05.155000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"Omnigen V2"},{"category":"json","description":"Convert your assets into lottie using Omnilottie.","endpoint_id":"fal-ai/omnilottie","family":"","inputs":[{"default":null,"description":"Text description of the Lottie animation to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":4096,"description":"Maximum number of Lottie tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":256,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.9,"description":"Sampling temperature for generation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.25,"description":"Nucleus sampling probability threshold.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":5,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"top_k","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["lottie_file"],"pricing":"","published_at":"2026-03-11T17:52:45.424000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91c462/LC-kCGEX5QzFgdcT2-WTl_a5f2161657074c7bac2d9a1a317e7359.png","title":"Omnilottie"},{"category":"json","description":"Convert your assets into lottie using Omnilottie.","endpoint_id":"fal-ai/omnilottie/image-to-lottie","family":"","inputs":[{"default":null,"description":"Text description guiding the animation of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the reference image to animate.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":4096,"description":"Maximum number of Lottie tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":256,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.9,"description":"Sampling temperature for generation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.25,"description":"Nucleus sampling probability threshold.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":5,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"top_k","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["lottie_file"],"pricing":"","published_at":"2026-03-11T17:48:27.243000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91c43d/f3CoP_dYKSKZvn9ZPvQSr_9a27962a7a834d038168933c2cc9bce8.png","title":"Omnilottie"},{"category":"json","description":"Convert your assets into lottie using Omnilottie.","endpoint_id":"fal-ai/omnilottie/video-to-lottie","family":"","inputs":[{"default":null,"description":"Optional text description guiding the conversion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the video to convert into a Lottie animation.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":4096,"description":"Maximum number of Lottie tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":256,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.9,"description":"Sampling temperature for generation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.25,"description":"Nucleus sampling probability threshold.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":5,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"top_k","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["lottie_file"],"pricing":"","published_at":"2026-03-11T17:55:06.882000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91c46c/vWXGBbJOv6p_n3qd0duhC_9cf1cee1295f49bfb5470a7a67ef08bd.png","title":"Omnilottie"},{"category":"video-to-video","description":"One-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes","endpoint_id":"fal-ai/one-to-all-animation/1.3b","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the video to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"480p","description":"The resolution of the video to generate.","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to use for the video generation.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":2,"description":"The image guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"image_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"The pose guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"pose_guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.06 per video second for 720p, $0.045 per video second for 580p, $0.03 per video second for 480p.","published_at":"2025-12-11T18:59:16.434000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85e86c/_YM6CaRHSSPdK06dwfle4_5ca446af223a4a7db272e9db359fada1.jpg","title":"One To All Animation"},{"category":"video-to-video","description":"One-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes","endpoint_id":"fal-ai/one-to-all-animation/14b","family":"","inputs":[{"default":null,"description":"The prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The negative prompt to generate the video from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the video to use as a reference for the video generation.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"480p","description":"The resolution of the video to generate.","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to use for the video generation.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":2,"description":"The image guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"image_guidance_scale","required":false,"type":"number"},{"default":1.5,"description":"The pose guidance scale to use for the video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"pose_guidance_scale","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.12 per video second for 720p, $0.09 per video second for 580p, $0.06 per video second for 480p.","published_at":"2025-12-11T18:56:35.518000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85e85f/dT7NUI11TBLXU-CGY9SMO_fbfc70e4d74544f1820ec29e914c1724.jpg","title":"One To All Animation"},{"category":"text-to-speech","description":"Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time performances.","endpoint_id":"fal-ai/orpheus-tts","family":"","inputs":[{"default":null,"description":"The text to be converted to speech. You can additionally add the following emotive tags: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"tara","description":"Voice ID for the desired voice.","enum":["tara","leah","jess","leo","dan","mia","zac","zoe"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":0.7,"description":"Temperature for generation (higher = more creative).","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1.2,"description":"Repetition penalty (>= 1.1 required for stable generations).","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1.1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-03-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound.jpg","title":"Orpheus TTS"},{"category":"text-to-video","description":"A unified paradigm for audio-video generation","endpoint_id":"fal-ai/ovi","family":"","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"jitter, bad hands, blur, distortion","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"The number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"robotic, muffled, echo, distorted","description":"Negative prompt for audio generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"992x512","description":"Resolution of the generated video in W:H format. One of (512x992, 992x512, 960x512, 512x960, 720x720, or 448x1120).","enum":["512x992","992x512","960x512","512x960","720x720","448x1120","1120x448"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-10-03T12:43:15.945000+00:00","thumbnail":"https://v3.fal.media/files/lion/yU9aRgq2QMYK4eGH5mohA_2822a9b5892d46699e218791b207ae5c.jpg","title":"Ovi Text to Video"},{"category":"image-to-video","description":"Ovi can generate videos with audio from image and text inputs.","endpoint_id":"fal-ai/ovi/image-to-video","family":"","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"jitter, bad hands, blur, distortion","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"The number of inference steps.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"robotic, muffled, echo, distorted","description":"Negative prompt for audio generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"The image URL to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-10-03T14:39:19.458000+00:00","thumbnail":"https://v3.fal.media/files/elephant/0C5YI172kcCI9lcCtXDJI_61f25dd2c735440aafb1a2ec647b6bd0.jpg","title":"Ovi"},{"category":"text-to-image","description":"Ovis-Image is a 7B text-to-image model specifically optimized for quick, high quality text rendering.","endpoint_id":"fal-ai/ovis-image","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["prompt","timings","seed","images","has_nsfw_concepts"],"pricing":"","published_at":"2025-11-29T18:45:42.568000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a849101/zu6l9lNp8GIuvAQyX7miT_0b2125b05401473bac38bf8d8bd40577.jpg","title":"Ovis Image"},{"category":"image-to-image","description":"Pixel-Aware Diffusion Model for Realistic Image Super-Resolution and Personalized Stylization","endpoint_id":"fal-ai/pasd","family":"","inputs":[{"default":null,"description":"Input image to super-resolve","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":2,"description":"Upscaling factor (1-4x)","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"scale","required":false,"type":"integer"},{"default":25,"description":"Number of inference steps (10-50)","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":7,"description":"Guidance scale for diffusion (1.0-20.0)","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0.8,"description":"ControlNet conditioning scale (0.1-1.0)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"conditioning_scale","required":false,"type":"number"},{"default":"","description":"Additional prompt to guide super-resolution","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"blurry, dirty, messy, frames, deformed, dotted, noise, raster lines, unclear, lowres, over-smoothed, painting, ai generated","description":"Negative prompt to avoid unwanted artifacts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"","output_kind":"images","output_props":["timings","images"],"pricing":"","published_at":"2025-06-17T22:57:07.317000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","title":"PASD"},{"category":"image-to-image","description":"PATINA creates seamless high-resolution normal, roughness, basecolor (albedo), height (displacement) and metalness maps from images","endpoint_id":"fal-ai/patina","family":"PATINA","inputs":[{"default":null,"description":"URL of the input image (photograph or render).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":["basecolor","normal","roughness","metalness","height"],"description":"Which PBR maps to predict. Defaults to all five.","enum":["basecolor","normal","roughness","metalness","height"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"maps","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible denoising. If not set, a random seed is used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable the safety checker for images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"Output image format.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Fal","output_kind":"images","output_props":["timings","images","seed"],"pricing":"Your request will cost $0.01 plus $0.01 per megapixel, per output map. For example, a 1024x1024 input image generating all 5 map types will cost $0.06","published_at":"2026-04-10T16:42:45.053000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9596de/rM98s4o9rBuzShY5_OvHz_50bff4e15999429a8c8c68fa8d931c5d.jpg","title":"PATINA"},{"category":"text-to-image","description":"Generate complete seamlessly tiling PBR materials including normal, roughness, basecolor, height and metalness maps up to 8K","endpoint_id":"fal-ai/patina/material","family":"PATINA","inputs":[{"default":null,"description":"The text prompt describing the material/texture to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Output texture dimensions in pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"Number of denoising steps for texture generation.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of texture images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Expand prompt with an LLM for richer detail. Adds ~0.0025 credits.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable the safety checker for generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"both","description":"Tiling direction: 'both' (omnidirectional), 'horizontal', or 'vertical'.","enum":["both","horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tiling_mode","required":false,"type":"enum"},{"default":128,"description":"Tile size in latent space (64 = 512px, 128 = 1024px).","enum":null,"is_list":false,"max":256,"media_kind":null,"min":32,"multiline":false,"name":"tile_size","required":false,"type":"integer"},{"default":64,"description":"Tile stride in latent space.","enum":null,"is_list":false,"max":128,"media_kind":null,"min":16,"multiline":false,"name":"tile_stride","required":false,"type":"integer"},{"default":null,"description":"URL of an input image for image-to-image or inpainting. When provided without mask_url, performs image-to-image; with mask_url, performs inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"URL of a mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":0.6,"description":"How much to transform the input image. Only used when image_url is provided.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":["basecolor","normal","roughness","metalness","height"],"description":"Which PBR maps to predict. Deselect all to skip PBR estimation entirely. Defaults to all five.","enum":["basecolor","normal","roughness","metalness","height"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"maps","required":false,"type":"enum"},{"default":0,"description":"Upscale factor for predicted PBR maps via SeedVR seamless upscaling. 0 = no upscaling, 2 = 2× resolution, 4 = 4× resolution. The base texture image is not upscaled.","enum":[0,2,4],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_factor","required":false,"type":"enum"},{"default":"png","description":"Output image format for textures and PBR maps.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Fal","output_kind":"images","output_props":["images","timings","seed","prompt"],"pricing":"Your request will cost $0.01 plus $0.02 per megapixel plus $0.01 per megapixel per map type. When using 2x upscaling, an additional $0.004 per (pre-upscaling) megapixel per map will be charged, and when using 4x upscaling, an additional $0.016 per (pre-upscaling) megapixel per map will be charged. For example, A 1024x1024 material with all 5 maps and no upscaling (1K) will cost $0.08, and a 2048x2048 material with all 5 maps and 4x upscaling (8K) will cost $0.61.","published_at":"2026-04-10T16:42:49.705000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9596f4/U3y78FMFLx6ZDukI2cHTK_2f621082b5f940d3a0276f1cb37a3eaf.jpg","title":"PATINA"},{"category":"image-to-image","description":"Extract seamless tiling textures with PBR attribute maps from images","endpoint_id":"fal-ai/patina/material/extract","family":"PATINA","inputs":[{"default":null,"description":"Describe which texture to extract from the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Output texture dimensions in pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"Number of denoising steps for texture generation.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"Number of texture images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Expand prompt with an LLM for richer detail. Adds ~0.0025 credits.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable the safety checker for generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"both","description":"Tiling direction: 'both' (omnidirectional), 'horizontal', or 'vertical'.","enum":["both","horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tiling_mode","required":false,"type":"enum"},{"default":128,"description":"Tile size in latent space (64 = 512px, 128 = 1024px).","enum":null,"is_list":false,"max":256,"media_kind":null,"min":32,"multiline":false,"name":"tile_size","required":false,"type":"integer"},{"default":64,"description":"Tile stride in latent space.","enum":null,"is_list":false,"max":128,"media_kind":null,"min":16,"multiline":false,"name":"tile_stride","required":false,"type":"integer"},{"default":null,"description":"URL of the image to extract a texture from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.6,"description":"How much to transform the input image. Only used when image_url is provided.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":["basecolor","normal","roughness","metalness","height"],"description":"Which PBR maps to predict. Deselect all to skip PBR estimation entirely. Defaults to all five.","enum":["basecolor","normal","roughness","metalness","height"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"maps","required":false,"type":"enum"},{"default":0,"description":"Upscale factor for predicted PBR maps via SeedVR seamless upscaling. 0 = no upscaling, 2 = 2× resolution, 4 = 4× resolution. The base texture image is not upscaled.","enum":[0,2,4],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_factor","required":false,"type":"enum"},{"default":"png","description":"Output image format for textures and PBR maps.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Fal","output_kind":"images","output_props":["images","timings","seed","prompt"],"pricing":"Your request will cost $0.10 plus $0.02 per megapixel plus $0.01 per megapixel per map type. When using 2x upscaling, an additional $0.004 per (pre-upscaling) megapixel per map will be charged, and when using 4x upscaling, an additional $0.016 per (pre-upscaling) megapixel per map will be charged.  For example, A 1024x1024 material with all 5 maps and no upscaling (1K) will cost $0.17, and a 2048x2048 material with all 5 maps and 4x upscaling (8K) will cost $0.70.","published_at":"2026-04-10T16:43:03.330000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9596fb/hGlZRKSg6METXKPyJr-7D_7152ffc4674342699bff539ff28f7d77.jpg","title":"PATINA"},{"category":"audio-to-audio","description":"PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.","endpoint_id":"fal-ai/personaplex","family":"","inputs":[{"default":"You are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.","description":"Text prompt describing the AI persona and conversation context.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"NATF2","description":"Voice ID for the AI response. NAT = natural, VAR = variety. F = female, M = male. Ignored when voice_audio_url is provided.","enum":["NATF0","NATF1","NATF2","NATF3","NATM0","NATM1","NATM2","NATM3","VARF0","VARF1","VARF2","VARF3","VARF4","VARM0","VARM1","VARM2","VARM3","VARM4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"URL to a voice sample audio for on-the-fly voice cloning. When provided, the AI responds in the cloned voice instead of the preset 'voice'. 10+ seconds of clear speech recommended. Billed at 2x rate.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"voice_audio_url","required":false,"type":"string"},{"default":0.8,"description":"Audio sampling temperature. Higher values produce more diverse outputs.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature_audio","required":false,"type":"number"},{"default":0.7,"description":"Text sampling temperature. Higher values produce more diverse outputs.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature_text","required":false,"type":"number"},{"default":250,"description":"Top-K sampling for audio tokens.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":1,"multiline":false,"name":"top_k_audio","required":false,"type":"integer"},{"default":25,"description":"Top-K sampling for text tokens.","enum":null,"is_list":false,"max":1000,"media_kind":null,"min":1,"multiline":false,"name":"top_k_text","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL to the input audio file (user's speech).","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"","output_kind":"audio","output_props":["audio","seed","duration","text"],"pricing":"You will be charged $0.001 per audio second","published_at":"2026-02-12T22:40:11.433000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e3bdd/S3TTkSpfq9z3cw4vaiPAh_749c28da9b9c48f4a945d405b25d5163.jpg","title":"Personaplex"},{"category":"audio-to-audio","description":"PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.","endpoint_id":"fal-ai/personaplex/realtime","family":"","inputs":[{"default":0.8,"description":"Audio sampling temperature. Higher values produce more diverse outputs.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature_audio","required":false,"type":"number"},{"default":null,"description":"Input audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio","required":true,"type":"string"},{"default":250,"description":"Top-K sampling for audio tokens.","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":1,"multiline":false,"name":"top_k_audio","required":false,"type":"integer"},{"default":"NATF2","description":"Voice ID for the AI response. NAT = natural, VAR = variety. F = female, M = male. Ignored when voice_audio_url is provided.","enum":["NATF0","NATF1","NATF2","NATF3","NATM0","NATM1","NATM2","NATM3","VARF0","VARF1","VARF2","VARF3","VARF4","VARM0","VARM1","VARM2","VARM3","VARM4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"URL to a voice sample audio for on-the-fly voice cloning. When provided, the AI responds in the cloned voice instead of the preset 'voice'. 10+ seconds of clear speech recommended. Billed at 2x rate.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"voice_audio_url","required":false,"type":"string"},{"default":0.7,"description":"Text sampling temperature. Higher values produce more diverse outputs.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature_text","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"You are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.","description":"Text prompt describing the AI persona and conversation context.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":25,"description":"Top-K sampling for text tokens.","enum":null,"is_list":false,"max":1000,"media_kind":null,"min":1,"multiline":false,"name":"top_k_text","required":false,"type":"integer"}],"lab":"","output_kind":"audio","output_props":["audio","text"],"pricing":"Your request will cost $0.001 per compute second.","published_at":"2026-02-20T19:49:59.950000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f45c2/IPYw_gEnouvQbF5oGJVR__350b67f5b52e42169f43650f2d171d23.jpg","title":"Personaplex"},{"category":"text-to-image","description":"Phota's model empowers developers, photographers, and creators with personalized photograph generation and editing.","endpoint_id":"fal-ai/phota","family":"","inputs":[{"default":null,"description":"Text description of the desired image. In case you wish to use specific profiles, refer to them as [[profile_id_1]], [[profile_id_2]], etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"1K","description":"Resolution of the generated image.","enum":["1K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated image.","enum":["auto","1:1","16:9","4:3","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.09 per 1K image and $0.18 per 4K image. Each 1K image costs 1 unit, and each 4K generation costs 2 units, with each unit costing $0.09.","published_at":"2026-03-26T13:42:50.195000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a93b7b5/TZslEQvrUH6GW_ppgEv60_6820d0833f7e44b19fd5f50c65540821.jpg","title":"Phota Text to Image"},{"category":"training","description":"Generate profiles using 30-50 images of a subject with Phota.","endpoint_id":"fal-ai/phota/create-profile","family":"","inputs":[{"default":null,"description":"URL to a ZIP archive containing the profile images.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_data_url","required":true,"type":"string"}],"lab":"Phota","output_kind":"text","output_props":["profile_id"],"pricing":"Your request will cost $2.9 per training run. For $3 you can run this model with approximately 1 times.","published_at":"2026-03-26T13:39:47.304000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a93b7bc/sQ4Vvcr7wdouV8JaeRlsY_43f3a0e4c96a4d38a6b6634343cb0852.jpg","title":"Phota Create Profile"},{"category":"image-to-image","description":"Phota's model enables personalized photo editing, preserving identity while erasing distractions seamlessly.","endpoint_id":"fal-ai/phota/edit","family":"","inputs":[{"default":null,"description":"Text description of the desired image. To refer to specific profiles, use [[profile_id_1]], [[profile_id_2]], etc.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"List of profile IDs to use for the image generation. Profiles may be tagged in the prompt as @Profile1, @Profile2, etc.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"profile_ids","required":false,"type":"string"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"1K","description":"Resolution of the generated image.","enum":["1K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated image.","enum":["auto","1:1","16:9","4:3","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"List of URLs/ Base64 data URIs of the images to edit. At least one image is required; for pure text-to-image generation use the `/` endpoint instead. A maximum of 10 images are supported, additional images will be ignored.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Phota","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.09 per 1K image and $0.18 per 4K image. Each 1K image costs 1 unit, and each 4K image charges 2 units, with each unit costing $0.09.","published_at":"2026-03-26T13:49:17.927000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a93b8fc/3UCkN5HYIJMfui9wNis3X_162f28fa834741318aa99b9d46047e9e.jpg","title":"Phota"},{"category":"image-to-image","description":"Enhance images while preserving identities with Phota","endpoint_id":"fal-ai/phota/enhance","family":"","inputs":[{"default":null,"description":"URL/Base64 data URI of the image to enhance.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"List of profile IDs to use for the image enhancement. The profiles sent over will be used as candidates for identity preservation.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"profile_ids","required":false,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Phota","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-03-26T13:47:20.910000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a93b79c/OaBXvYtrMGZmu_KJyUCFw_07076628192447cd85c0772f083985fd.jpg","title":"Phota Enhance"},{"category":"image-to-image","description":"Customizing Realistic Human Photos via Stacked ID Embedding","endpoint_id":"fal-ai/photomaker","family":"","inputs":[{"default":null,"description":"The URL of the image archive containing the images you want to use.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_archive_url","required":true,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"photomaker","description":"The base pipeline to use for generating the image.","enum":["photomaker","photomaker-style"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"base_pipeline","required":false,"type":"enum"},{"default":null,"description":"Optional initial image for img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"initial_image_url","required":false,"type":"string"},{"default":0.5,"description":"How much noise to add to the latent image. O for no noise, 1 for maximum noise.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"initial_image_strength","required":false,"type":"number"},{"default":"Photographic","description":"Style","enum":["(No style)","Cinematic","Disney Character","Digital Art","Photographic","Fantasy art","Neonpunk","Enhance","Comic book","Lowpoly","Line art"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Increasing the amount of steps tells Stable Diffusion that it should take more steps\n            to generate your final result which can increase the amount of detail in your image.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":20,"description":"Style strength (in %)","enum":null,"is_list":false,"max":50,"media_kind":null,"min":15,"multiline":false,"name":"style_strength","required":false,"type":"integer"},{"default":1,"description":"Number of images to generate in one request. Note that the higher the batch size,\n            the longer it will take to generate the images.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0.1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2024-03-08T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/photomaker.jpeg","title":"PhotoMaker"},{"category":"image-to-video","description":"Pika Effects are AI-powered video effects designed to modify objects, characters, and environments in a fun, engaging, and visually compelling manner.","endpoint_id":"fal-ai/pika/v1.5/pikaffects","family":"Pikaffects 1.5","inputs":[{"default":null,"description":"URL of the input image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The Pikaffect to apply","enum":["Cake-ify","Crumble","Crush","Decapitate","Deflate","Dissolve","Explode","Eye-pop","Inflate","Levitate","Melt","Peel","Poke","Squish","Ta-da","Tear"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pikaffect","required":true,"type":"enum"},{"default":null,"description":"Text prompt to guide the effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/2uSfx4xu1fXv4am4PvLAm_499f61b93f924a7496982491a87fb169.jpg","title":"Pika Effects (v1.5)"},{"category":"image-to-video","description":"Turn photos into mind-blowing, dynamic videos. Your images can can come to life with sharp details, impressive character control and cinematic camera moves.","endpoint_id":"fal-ai/pika/v2.1/image-to-video","family":"","inputs":[{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/9yJyc4ezyAPejLJlzquI9_f8b95aa25041426fbc0c0861ae80a2c6.jpg","title":"Pika Image to Video (v2.1)"},{"category":"text-to-video","description":"Start with a simple text input to create dynamic generations that defy expectations. Anything you dream can come to life with sharp details, impressive character control and cinematic camera moves.","endpoint_id":"fal-ai/pika/v2.1/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1","4:5","5:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/CUxIh-EAd_N4npYGWlEqA_d08d3d9739e947e9814d7d2f2a1c998d.jpg","title":"Pika Text to Video (v2.1)"},{"category":"image-to-video","description":"Turn photos into mind-blowing, dynamic videos in up to 1080p. Experience better image clarity and crisper, sharper visuals.","endpoint_id":"fal-ai/pika/v2.2/image-to-video","family":"","inputs":[{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":[5,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"5 second video at 720p costs $0.20. 5 second video at 1080p costs $0.45.","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/mATl0lc8FwiR6WceFEDfH_692743a190bc4859a00caa338a1809c5.jpg","title":"Pika Image to Video (v2.2)"},{"category":"image-to-video","description":"Discover ultimate control with Pikaframes key frame interpolation, a stunning image-to-video feature that allows you to upload up to 5 keyframes, customize their transition length and prompt, and see their images come to life as seamless videos.","endpoint_id":"fal-ai/pika/v2.2/pikaframes","family":"Pikaframes 2.2","inputs":[{"default":null,"description":"URLs of keyframe images (2-5 images) to create transitions between","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Configuration for each transition. Length must be len(image_urls) - 1. Total duration of all transitions must not exceed 25 seconds. If not provided, uses default 5-second transitions with the global prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transitions","required":false,"type":"json"},{"default":null,"description":"Default prompt for all transitions. Individual transition prompts override this.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.04 per second for 720p or $0.06 per second for 1080p, with a minimum of 5 billable seconds -  $0.20 for 720p and $0.30 for 1080p.","published_at":"2025-11-07T23:56:01.434000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/CtOfvKi8w3X6qO495bKva_4377f203234f47d69a57efef836c93aa.jpg","title":"Pika"},{"category":"image-to-video","description":"Pika Scenes v2.2 creates videos from a images with high quality output.","endpoint_id":"fal-ai/pika/v2.2/pikascenes","family":"Pikascenes 2.2","inputs":[{"default":null,"description":"URLs of images to combine into a video","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Text prompt describing the desired video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"ugly, bad, terrible","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1","4:5","5:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":[5,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"precise","description":"Mode for integrating multiple images. Precise mode is more accurate, creative mode is more creative.","enum":["precise","creative"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ingredients_mode","required":false,"type":"enum"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"5 second video at 720p costs $0.20. 5 second video at 1080p costs $0.45.","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/3FYXmzqtjqf6xQ5YVxbKi_bf6ff3d3904a42c783662e7e1fa21ce9.jpg","title":"Pika Scenes (v2.2)"},{"category":"text-to-video","description":"Start with a simple text input to create dynamic generations that defy expectations in up to 1080p. Experience better image clarity and crisper, sharper visuals.","endpoint_id":"fal-ai/pika/v2.2/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"ugly, bad, terrible","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1","4:5","5:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["1080p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":[5,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"5 second video at 720p costs $0.20. 5 second video at 1080p costs $0.45.","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/d7bGY17P07W2dKiNoWXfQ_fb8e23d259a44c5a893f04ae7a710b95.jpg","title":"Pika Text to Video (v2.2)"},{"category":"video-to-video","description":"Pikadditions is a powerful video-to-video AI model that allows you to add anyone or anything to any video with seamless integration.","endpoint_id":"fal-ai/pika/v2/pikadditions","family":"Pikadditions 2","inputs":[{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to add","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text prompt describing what to add","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/1wavesunset.webp","title":"Pikadditions (v2)"},{"category":"image-to-video","description":"Turbo is the model to use when you feel the need for speed. Turn your image to stunning video up to 3x faster – all with high quality outputs.","endpoint_id":"fal-ai/pika/v2/turbo/image-to-video","family":"","inputs":[{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/izszWyAu5LZ56Z-ZK63x5_1c8004b9a1054d0d849848569196d293.jpg","title":"Pika Image to Video Turbo (v2)"},{"category":"text-to-video","description":"Pika v2 Turbo creates videos from a text prompt with high quality output.","endpoint_id":"fal-ai/pika/v2/turbo/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"A negative prompt to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1","4:5","5:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Pika","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/D6kbQkNiBrPL9m05gdWnE_48bca5e513bd42a6b777dfb9b08e0ca9.jpg","title":"Pika Text to Video Turbo (v2)"},{"category":"image-to-3d","description":"Pixal3D turns a single image into a high-fidelity 3D model with detailed geometry and realistic textures.","endpoint_id":"fal-ai/pixal3d","family":"","inputs":[{"default":null,"description":"URL of the input image to convert to 3D","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1024,"description":"Output resolution; higher is slower but more detailed","enum":[1024,1536],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":7.5,"description":"How closely the initial 3D structure follows the input image. Higher values produce more faithful but potentially noisier results.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_strength","required":false,"type":"number"},{"default":0.7,"description":"Dampens artifacts from high guidance in stage 1. Lower values allow stronger guidance effects, higher values stabilize the output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for the initial structure. More steps = slower but potentially higher quality.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"ss_sampling_steps","required":false,"type":"integer"},{"default":5,"description":"Controls noise schedule sharpness for structure generation. Higher values produce sharper transitions.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"ss_rescale_t","required":false,"type":"number"},{"default":7.5,"description":"How closely the detailed geometry follows the input image. Higher values add more detail but may introduce noise.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_strength","required":false,"type":"number"},{"default":0.5,"description":"Dampens artifacts from high guidance in the shape stage. Increase if you see noisy geometry.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for shape refinement. More steps = slower but potentially smoother geometry.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for shape refinement. Higher values produce sharper geometric details.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_rescale_t","required":false,"type":"number"},{"default":1,"description":"How closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_strength","required":false,"type":"number"},{"default":0,"description":"Dampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for texture generation. More steps = slower but potentially cleaner textures.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for texture generation. Higher values produce sharper texture details.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_rescale_t","required":false,"type":"number"},{"default":1,"description":"Scale factor applied to the inferred mesh. Affects the camera distance estimation used by the model.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0.1,"multiline":false,"name":"mesh_scale","required":false,"type":"number"},{"default":49152,"description":"Maximum number of HR tokens used by the cascaded shape sampler. Higher values allow finer geometry; lower values reduce memory and time.","enum":null,"is_list":false,"max":131072,"media_kind":null,"min":4096,"multiline":false,"name":"max_num_tokens","required":false,"type":"integer"},{"default":200000,"description":"Target number of vertices in the final mesh. Lower values produce smaller files but less detail.","enum":null,"is_list":false,"max":1586021,"media_kind":null,"min":5000,"multiline":false,"name":"decimation_target","required":false,"type":"integer"},{"default":2048,"description":"Resolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files.","enum":[1024,2048,4096],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"},{"default":true,"description":"Rebuild the mesh topology for cleaner triangles. Slower but usually produces better results for downstream use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remesh","required":false,"type":"boolean"}],"lab":"","output_kind":"file","output_props":["seed","model_glb"],"pricing":"Your request will cost $0.3 for 1024p resolution, $0.42 for 1536 resolution.","published_at":"2026-05-13T20:35:36.991000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a157d/Ll0Qg8SYE0Z5PFp2TEkXh_0dd653f1c39c4c7593efb1bb028dbec9.jpg","title":"Pixal3d"},{"category":"text-to-image","description":"Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","endpoint_id":"fal-ai/pixart-sigma","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"(No style)","description":"The style to apply to the image.","enum":["(No style)","Cinematic","Photographic","Anime","Manga","Digital Art","Pixel art","Fantasy art","Neonpunk","3D Model"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":5,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"DPM-SOLVER","description":"The scheduler to use for the model.","enum":["DPM-SOLVER","SA-SOLVER"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"scheduler","required":false,"type":"enum"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["timings","prompt","has_nsfw_concepts","images","seed"],"pricing":"","published_at":"2024-08-01T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixart-sigma.jpeg","title":"PixArt-Σ"},{"category":"image-to-video","description":"Animate images into cinematic videos with PixVerse C1, supporting 1080p resolution and native audio generation.","endpoint_id":"fal-ai/pixverse/c1/image-to-video","family":"PixVerse C1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds (1-15)","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.030 per second without audio and $0.040 per second with audio. For 540p, it will cost $0.040 per second without audio and $0.050 per second with audio. For 720p, it will cost $0.050 per second without audio and $0.065 per second with audio. For 1080p, it will cost $0.095 per second without audio and $0.120 per second with audio. For $1 you can run this model for approximately 33 seconds at 360p (no audio) or about 10 seconds at 1080p (no audio).","published_at":"2026-04-09T23:44:02.328000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a957a2b/vPLdm8Nrb6L_q1c2wObcX_c1d8db8dbfe1407fa539f4477f5ba550.jpg","title":"PixVerse C1 Image To Video"},{"category":"image-to-video","description":"Generate character-consistent videos from reference images using PixVerse C1, with subject and background references.","endpoint_id":"fal-ai/pixverse/c1/reference-to-video","family":"PixVerse C1","inputs":[{"default":null,"description":"The prompt for the reference-to-video generation. Use @ref_name to refer to uploaded references.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds (1-15)","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"List of reference images with type and name. Use @ref_name in the prompt to refer to each reference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_references","required":true,"type":"json"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.030 per second without audio and $0.040 per second with audio. For 540p, it will cost $0.040 per second without audio and $0.050 per second with audio. For 720p, it will cost $0.050 per second without audio and $0.065 per second with audio. For 1080p, it will cost $0.095 per second without audio and $0.120 per second with audio. For $1 you can run this model for approximately 33 seconds at 360p (no audio) or about 10 seconds at 1080p (no audio).","published_at":"2026-04-09T23:44:36.305000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a95798a/fCnVWzH0_WkQiWSdjqkwO_e7cc6f7bfb2c4bb1b4e7c915466455f8.jpg","title":"PixVerse C1 Reference To Video"},{"category":"text-to-video","description":"Generate film-grade videos from text prompts with native audio, up to 1080p and 15 seconds, using PixVerse C1.","endpoint_id":"fal-ai/pixverse/c1/text-to-video","family":"PixVerse C1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds (1-15)","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.030 per second without audio and $0.040 per second with audio. For 540p, it will cost $0.040 per second without audio and $0.050 per second with audio. For 720p, it will cost $0.050 per second without audio and $0.065 per second with audio. For 1080p, it will cost $0.095 per second without audio and $0.120 per second with audio. For $1 you can run this model for approximately 33 seconds at 360p (no audio) or about 10 seconds at 1080p (no audio).","published_at":"2026-04-09T23:44:23.016000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a957a29/F9h26mxs4zndIlypwPTV5_c4d0e69c4b514f5cb70075b8a5a6987c.jpg","title":"PixVerse C1 Text To Video"},{"category":"image-to-video","description":"Create seamless cinematic transitions between two images with PixVerse C1, with native audio and up to 1080p.","endpoint_id":"fal-ai/pixverse/c1/transition","family":"PixVerse C1","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds (1-15)","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.030 per second without audio and $0.040 per second with audio. For 540p, it will cost $0.040 per second without audio and $0.050 per second with audio. For 720p, it will cost $0.050 per second without audio and $0.065 per second with audio. For 1080p, it will cost $0.095 per second without audio and $0.120 per second with audio. For $1 you can run this model for approximately 33 seconds at 360p (no audio) or about 10 seconds at 1080p (no audio).","published_at":"2026-04-09T23:43:40.351000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a957a29/yTOKdpiOzGEDrcl3TZri4_98c2405835e64049949b4230eb082ce1.jpg","title":"PixVerse C1 Transition"},{"category":"video-to-video","description":"PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques","endpoint_id":"fal-ai/pixverse/extend","family":"","inputs":[{"default":null,"description":"URL of the input video to extend","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Prompt describing how to extend the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the extended video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"v4.5","description":"The model version to use for generation","enum":["v3.5","v4","v4.5","v5","v5.5","v5.6","v6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue). Supported in v5.6+ models.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-06-30T20:57:59.382000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse Extend"},{"category":"video-to-video","description":"PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques","endpoint_id":"fal-ai/pixverse/extend/fast","family":"","inputs":[{"default":null,"description":"URL of the input video to extend","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Prompt describing how to extend the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the extended video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video. Fast mode doesn't support 1080p","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"v4.5","description":"The model version to use for generation","enum":["v3.5","v4","v4.5","v5","v5.5","v5.6","v6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue). Supported in v5.6+ models.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-06-30T20:58:06.204000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse Extend Fast"},{"category":"video-to-video","description":"Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with PixVerse Lipsync model","endpoint_id":"fal-ai/pixverse/lipsync","family":"","inputs":[{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input audio. If not provided, TTS will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":"Auto","description":"Voice to use for TTS when audio_url is not provided","enum":["Emily","James","Isabella","Liam","Chloe","Adrian","Harper","Ava","Sophia","Julia","Mason","Jack","Oliver","Ethan","Auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice_id","required":false,"type":"enum"},{"default":null,"description":"Text content for TTS when audio_url is not provided","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":false,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For every second of output videos your request will cost $0.04. If audio is not provided for every 100 characters your request will cost $0.24.","published_at":"2025-06-30T20:57:46.375000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b4/lhteFXTaKCmfz9Noxirug_anEumAjC.png","title":"PixVerse Lipsync"},{"category":"video-to-video","description":"Add immersive sound effects and background music to your videos using PixVerse sound effects  generation","endpoint_id":"fal-ai/pixverse/sound-effects","family":"","inputs":[{"default":null,"description":"URL of the input video to add sound effects to","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"Whether to keep the original audio from the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_sound_switch","required":false,"type":"boolean"},{"default":"","description":"Description of the sound effect to generate. If empty, a random sound effect will be generated","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-07-07T20:56:55.765000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse Sound Effects"},{"category":"image-to-video","description":"Generate high quality video clips by swapping person, objects and background using Pixverse Swap.","endpoint_id":"fal-ai/pixverse/swap","family":"","inputs":[{"default":null,"description":"URL of the external video to swap","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"person","description":"The swap mode to use","enum":["person","object","background"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":1,"description":"The keyframe ID to use for face/object mapping. The input video is normalized to 24 FPS before processing, so keyframe 1 = first frame, keyframe 24 = 1 second in, etc. Valid range: 1 to (duration_seconds * 24).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"keyframe_id","required":false,"type":"integer"},{"default":null,"description":"URL of the target image for swapping","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"720p","description":"The output resolution (1080p not supported)","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to keep the original audio","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"original_sound_switch","required":false,"type":"boolean"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. If input video duration is greater than 5 s the cost will double. For $1 you can run this model with approximately 2 times.","published_at":"2025-11-10T14:14:52.148000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/NannfsqTmo5KZP4HWcpBx_ee601644250b4ed589741220176495fe.jpg","title":"PixVerse Swap"},{"category":"image-to-video","description":"Generate high quality video clips with different effects using PixVerse v3.5","endpoint_id":"fal-ai/pixverse/v3.5/effects","family":"","inputs":[{"default":null,"description":"The effect to apply to the video","enum":["Kiss Me AI","Kiss","Muscle Surge","Warmth of Jesus","Anything, Robot","The Tiger Touch","Hug","Holy Wings","Microwave","Zombie Mode","Squid Game","Baby Face","Black Myth: Wukong","Long Hair Magic","Leggy Run","Fin-tastic Mermaid","Punch Face","Creepy Devil Smile","Thunder God","Eye Zoom Challenge","Who's Arrested?","Baby Arrived","Werewolf Rage","Bald Swipe","BOOM DROP","Huge Cutie","Liquid Metal","Sharksnap!","Dust Me Away","3D Figurine Factor","Bikini Up","My Girlfriends","My Boyfriends","Subject 3 Fever","Earth Zoom","Pole Dance","Vroom Dance","GhostFace Terror","Dragon Evoker","Skeletal Bae","Summoning succubus","Halloween Voodoo Doll","3D Naked-Eye AD","Package Explosion","Dishes Served","Ocean ad","Supermarket AD","Tree doll","Come Feel My Abs","The Bicep Flex","London Elite Vibe","Flora Nymph Gown","Christmas Costume","It's Snowy","Reindeer Cruiser","Snow Globe Maker","Pet Christmas Outfit","Adopt a Polar Pal","Cat Christmas Box","Starlight Gift Box","Xmas Poster","Pet Christmas Tree","City Santa Hat","Stocking Sweetie","Christmas Night","Xmas Front Page Karma","Grinch's Xmas Hijack","Giant Product","Truck Fashion Shoot","Beach AD","Shoal Surround","Mechanical Assembly","Lighting AD","Billboard AD","Product close-up","Parachute Delivery","Dreamlike Cloud","Macaron Machine","Poster AD","Truck AD","Graffiti AD","3D Figurine Factory","The Exclusive First Class","Art Zoom Challenge","I Quit","Hitchcock Dolly Zoom","Smell the Lens","I believe I can fly","Strikout Dance","Courtside Cam","Pit Crew Moment","K-Baseball Sprint","Toddler Doodle","Idol Ending","Apex Dance","OmniHero Forge","Palm Decode","The Age Ripple","My Future Is Limitless","Knee Slide","Epic Goal Save","Sideline Ball Boy","Cup Celebration","Victory Roar","Vuvuzela Fan","World Champion Lift","Tunnel to Captain","Liquid Soccer Morph","Jump Into Crowd 2","Golden Pitch Crasher","Stadium Fan Cam","Broadcast Moto GP","The Grotesque Clay","Rookie Star Card","The Final Hug","Sharp Post-Match Comment","Street Maverick","Pitch Legend","One Step At A Time","Birthday Mirror","Superstar Lobby","Final Battle Room","Top of the World","Pixel World","Mint in Box","Hands up, Hand","Flora Nymph Go","Somber Embrace","Beam me up","Suit Swagger"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the image to use as the first frame. If not provided, generates from text","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-01T02:53:00.990000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V3.5 Effects"},{"category":"image-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v3.5","endpoint_id":"fal-ai/pixverse/v3.5/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-01-29T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V3.5 Image To Video"},{"category":"image-to-video","description":"Generate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast","endpoint_id":"fal-ai/pixverse/v3.5/image-to-video/fast","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-01-29T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V3.5 Image To Video Fast"},{"category":"text-to-video","description":"Generate high quality video clips from text prompts using PixVerse v3.5","endpoint_id":"fal-ai/pixverse/v3.5/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-01-29T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V3.5 Text To Video"},{"category":"text-to-video","description":"Generate high quality video clips quickly from text prompts using PixVerse v3.5 Fast","endpoint_id":"fal-ai/pixverse/v3.5/text-to-video/fast","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-01-29T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V3.5 Text To Video Fast"},{"category":"image-to-video","description":"Create seamless transition between images using PixVerse v3.5","endpoint_id":"fal-ai/pixverse/v3.5/transition","family":"","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-01T02:35:42.865000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V3.5 Transition"},{"category":"image-to-video","description":"Generate high quality video clips with different effects using PixVerse v4.5","endpoint_id":"fal-ai/pixverse/v4.5/effects","family":"","inputs":[{"default":null,"description":"The effect to apply to the video","enum":["Kiss Me AI","Kiss","Muscle Surge","Warmth of Jesus","Anything, Robot","The Tiger Touch","Hug","Holy Wings","Microwave","Zombie Mode","Squid Game","Baby Face","Black Myth: Wukong","Long Hair Magic","Leggy Run","Fin-tastic Mermaid","Punch Face","Creepy Devil Smile","Thunder God","Eye Zoom Challenge","Who's Arrested?","Baby Arrived","Werewolf Rage","Bald Swipe","BOOM DROP","Huge Cutie","Liquid Metal","Sharksnap!","Dust Me Away","3D Figurine Factor","Bikini Up","My Girlfriends","My Boyfriends","Subject 3 Fever","Earth Zoom","Pole Dance","Vroom Dance","GhostFace Terror","Dragon Evoker","Skeletal Bae","Summoning succubus","Halloween Voodoo Doll","3D Naked-Eye AD","Package Explosion","Dishes Served","Ocean ad","Supermarket AD","Tree doll","Come Feel My Abs","The Bicep Flex","London Elite Vibe","Flora Nymph Gown","Christmas Costume","It's Snowy","Reindeer Cruiser","Snow Globe Maker","Pet Christmas Outfit","Adopt a Polar Pal","Cat Christmas Box","Starlight Gift Box","Xmas Poster","Pet Christmas Tree","City Santa Hat","Stocking Sweetie","Christmas Night","Xmas Front Page Karma","Grinch's Xmas Hijack","Giant Product","Truck Fashion Shoot","Beach AD","Shoal Surround","Mechanical Assembly","Lighting AD","Billboard AD","Product close-up","Parachute Delivery","Dreamlike Cloud","Macaron Machine","Poster AD","Truck AD","Graffiti AD","3D Figurine Factory","The Exclusive First Class","Art Zoom Challenge","I Quit","Hitchcock Dolly Zoom","Smell the Lens","I believe I can fly","Strikout Dance","Courtside Cam","Pit Crew Moment","K-Baseball Sprint","Toddler Doodle","Idol Ending","Apex Dance","OmniHero Forge","Palm Decode","The Age Ripple","My Future Is Limitless","Knee Slide","Epic Goal Save","Sideline Ball Boy","Cup Celebration","Victory Roar","Vuvuzela Fan","World Champion Lift","Tunnel to Captain","Liquid Soccer Morph","Jump Into Crowd 2","Golden Pitch Crasher","Stadium Fan Cam","Broadcast Moto GP","The Grotesque Clay","Rookie Star Card","The Final Hug","Sharp Post-Match Comment","Street Maverick","Pitch Legend","One Step At A Time","Birthday Mirror","Superstar Lobby","Final Battle Room","Top of the World","Pixel World","Mint in Box","Hands up, Hand","Flora Nymph Go","Somber Embrace","Beam me up","Suit Swagger"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the image to use as the first frame. If not provided, generates from text","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-05-15T15:44:19.595000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4.5 Effects"},{"category":"image-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v4.5","endpoint_id":"fal-ai/pixverse/v4.5/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The type of camera movement to apply to the video","enum":["horizontal_left","horizontal_right","vertical_up","vertical_down","zoom_in","zoom_out","crane_up","quickly_zoom_in","quickly_zoom_out","smooth_zoom_in","camera_rotation","robo_arm","super_dolly_out","whip_pan","hitchcock","left_follow","right_follow","pan_left","pan_right","fix_bg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_movement","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-05-15T15:53:06.944000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","title":"PixVerse V4.5 Image To Video"},{"category":"image-to-video","description":"Generate fast high quality video clips from text and image prompts using PixVerse v4.5","endpoint_id":"fal-ai/pixverse/v4.5/image-to-video/fast","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The type of camera movement to apply to the video","enum":["horizontal_left","horizontal_right","vertical_up","vertical_down","zoom_in","zoom_out","crane_up","quickly_zoom_in","quickly_zoom_out","smooth_zoom_in","camera_rotation","robo_arm","super_dolly_out","whip_pan","hitchcock","left_follow","right_follow","pan_left","pan_right","fix_bg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_movement","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-05-15T15:55:20.848000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4.5 Image To Video Fast"},{"category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v4.5","endpoint_id":"fal-ai/pixverse/v4.5/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-05-15T15:48:45.845000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4.5 Text To Video"},{"category":"text-to-video","description":"Generate high quality and fast video clips from text and image prompts using PixVerse v4.5 fast","endpoint_id":"fal-ai/pixverse/v4.5/text-to-video/fast","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-05-15T15:51:13.967000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4.5 Text To Video Fast"},{"category":"image-to-video","description":"Create seamless transition between images using PixVerse v4.5","endpoint_id":"fal-ai/pixverse/v4.5/transition","family":"","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-05-15T15:57:02.859000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4.5 Transition"},{"category":"image-to-video","description":"Generate high quality video clips with different effects using PixVerse v4","endpoint_id":"fal-ai/pixverse/v4/effects","family":"","inputs":[{"default":null,"description":"The effect to apply to the video","enum":["Kiss Me AI","Kiss","Muscle Surge","Warmth of Jesus","Anything, Robot","The Tiger Touch","Hug","Holy Wings","Microwave","Zombie Mode","Squid Game","Baby Face","Black Myth: Wukong","Long Hair Magic","Leggy Run","Fin-tastic Mermaid","Punch Face","Creepy Devil Smile","Thunder God","Eye Zoom Challenge","Who's Arrested?","Baby Arrived","Werewolf Rage","Bald Swipe","BOOM DROP","Huge Cutie","Liquid Metal","Sharksnap!","Dust Me Away","3D Figurine Factor","Bikini Up","My Girlfriends","My Boyfriends","Subject 3 Fever","Earth Zoom","Pole Dance","Vroom Dance","GhostFace Terror","Dragon Evoker","Skeletal Bae","Summoning succubus","Halloween Voodoo Doll","3D Naked-Eye AD","Package Explosion","Dishes Served","Ocean ad","Supermarket AD","Tree doll","Come Feel My Abs","The Bicep Flex","London Elite Vibe","Flora Nymph Gown","Christmas Costume","It's Snowy","Reindeer Cruiser","Snow Globe Maker","Pet Christmas Outfit","Adopt a Polar Pal","Cat Christmas Box","Starlight Gift Box","Xmas Poster","Pet Christmas Tree","City Santa Hat","Stocking Sweetie","Christmas Night","Xmas Front Page Karma","Grinch's Xmas Hijack","Giant Product","Truck Fashion Shoot","Beach AD","Shoal Surround","Mechanical Assembly","Lighting AD","Billboard AD","Product close-up","Parachute Delivery","Dreamlike Cloud","Macaron Machine","Poster AD","Truck AD","Graffiti AD","3D Figurine Factory","The Exclusive First Class","Art Zoom Challenge","I Quit","Hitchcock Dolly Zoom","Smell the Lens","I believe I can fly","Strikout Dance","Courtside Cam","Pit Crew Moment","K-Baseball Sprint","Toddler Doodle","Idol Ending","Apex Dance","OmniHero Forge","Palm Decode","The Age Ripple","My Future Is Limitless","Knee Slide","Epic Goal Save","Sideline Ball Boy","Cup Celebration","Victory Roar","Vuvuzela Fan","World Champion Lift","Tunnel to Captain","Liquid Soccer Morph","Jump Into Crowd 2","Golden Pitch Crasher","Stadium Fan Cam","Broadcast Moto GP","The Grotesque Clay","Rookie Star Card","The Final Hug","Sharp Post-Match Comment","Street Maverick","Pitch Legend","One Step At A Time","Birthday Mirror","Superstar Lobby","Final Battle Room","Top of the World","Pixel World","Mint in Box","Hands up, Hand","Flora Nymph Go","Somber Embrace","Beam me up","Suit Swagger"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the image to use as the first frame. If not provided, generates from text","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-23T17:11:05.284000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4 Effects"},{"category":"image-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v4","endpoint_id":"fal-ai/pixverse/v4/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The type of camera movement to apply to the video","enum":["horizontal_left","horizontal_right","vertical_up","vertical_down","zoom_in","zoom_out","crane_up","quickly_zoom_in","quickly_zoom_out","smooth_zoom_in","camera_rotation","robo_arm","super_dolly_out","whip_pan","hitchcock","left_follow","right_follow","pan_left","pan_right","fix_bg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_movement","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-01T02:54:43.687000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4 Image To Video"},{"category":"image-to-video","description":"Generate fast high quality video clips from text and image prompts using PixVerse v4","endpoint_id":"fal-ai/pixverse/v4/image-to-video/fast","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The type of camera movement to apply to the video","enum":["horizontal_left","horizontal_right","vertical_up","vertical_down","zoom_in","zoom_out","crane_up","quickly_zoom_in","quickly_zoom_out","smooth_zoom_in","camera_rotation","robo_arm","super_dolly_out","whip_pan","hitchcock","left_follow","right_follow","pan_left","pan_right","fix_bg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_movement","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-01T02:56:53.842000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4 Image To Video Fast"},{"category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v4","endpoint_id":"fal-ai/pixverse/v4/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-01T02:42:23.743000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4 Text To Video"},{"category":"text-to-video","description":"Generate high quality and fast video clips from text and image prompts using PixVerse v4 fast","endpoint_id":"fal-ai/pixverse/v4/text-to-video/fast","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost 0.3$ for 360p and 540p, 0.4$ for 720p and 0.8$ for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-04-01T02:33:43.392000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V4 Text To Video Fast"},{"category":"image-to-video","description":"Pixverse Effects","endpoint_id":"fal-ai/pixverse/v5.5/effects","family":"","inputs":[{"default":null,"description":"The effect to apply to the video","enum":["Kiss Me AI","Kiss","Muscle Surge","Warmth of Jesus","Anything, Robot","The Tiger Touch","Hug","Holy Wings","Microwave","Zombie Mode","Squid Game","Baby Face","Black Myth: Wukong","Long Hair Magic","Leggy Run","Fin-tastic Mermaid","Punch Face","Creepy Devil Smile","Thunder God","Eye Zoom Challenge","Who's Arrested?","Baby Arrived","Werewolf Rage","Bald Swipe","BOOM DROP","Huge Cutie","Liquid Metal","Sharksnap!","Dust Me Away","3D Figurine Factor","Bikini Up","My Girlfriends","My Boyfriends","Subject 3 Fever","Earth Zoom","Pole Dance","Vroom Dance","GhostFace Terror","Dragon Evoker","Skeletal Bae","Summoning succubus","Halloween Voodoo Doll","3D Naked-Eye AD","Package Explosion","Dishes Served","Ocean ad","Supermarket AD","Tree doll","Come Feel My Abs","The Bicep Flex","London Elite Vibe","Flora Nymph Gown","Christmas Costume","It's Snowy","Reindeer Cruiser","Snow Globe Maker","Pet Christmas Outfit","Adopt a Polar Pal","Cat Christmas Box","Starlight Gift Box","Xmas Poster","Pet Christmas Tree","City Santa Hat","Stocking Sweetie","Christmas Night","Xmas Front Page Karma","Grinch's Xmas Hijack","Giant Product","Truck Fashion Shoot","Beach AD","Shoal Surround","Mechanical Assembly","Lighting AD","Billboard AD","Product close-up","Parachute Delivery","Dreamlike Cloud","Macaron Machine","Poster AD","Truck AD","Graffiti AD","3D Figurine Factory","The Exclusive First Class","Art Zoom Challenge","I Quit","Hitchcock Dolly Zoom","Smell the Lens","I believe I can fly","Strikout Dance","Courtside Cam","Pit Crew Moment","K-Baseball Sprint","Toddler Doodle","Idol Ending","Apex Dance","OmniHero Forge","Palm Decode","The Age Ripple","My Future Is Limitless","Knee Slide","Epic Goal Save","Sideline Ball Boy","Cup Celebration","Victory Roar","Vuvuzela Fan","World Champion Lift","Tunnel to Captain","Liquid Soccer Morph","Jump Into Crowd 2","Golden Pitch Crasher","Stadium Fan Cam","Broadcast Moto GP","The Grotesque Clay","Rookie Star Card","The Final Hug","Sharp Post-Match Comment","Street Maverick","Pitch Legend","One Step At A Time","Birthday Mirror","Superstar Lobby","Final Battle Room","Top of the World","Pixel World","Mint in Box","Hands up, Hand","Flora Nymph Go","Somber Embrace","Beam me up","Suit Swagger"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the image to use as the first frame. If not provided, generates from text","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5s video in single-clip mode without audio, your request will cost $0.15 for 360p and 540p, $0.2 for 720p, and $0.4 for 1080p. Enabling audio adds $0.05, and multi-clip mode adds $0.10 (or $0.15 with audio). For 8-second videos, costs double; for 10-second videos, costs are 2.2x the 5-second base (1080p not supported for 10s). For $1 you can run this model with approximately 2 times.","published_at":"2025-12-02T08:44:21.318000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922e/OQxt500_isDiJxo5EKggy_xJRYm9gx.png","title":"PixVerse V5.5 Effects"},{"category":"image-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v5.5","endpoint_id":"fal-ai/pixverse/v5.5/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. Longer durations cost more. 1080p videos are limited to 5 or 8 seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":false,"description":"Enable multi-clip generation with dynamic camera changes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_multi_clip_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5s video in single-clip mode without audio, your request will cost $0.15 for 360p and 540p, $0.2 for 720p, and $0.4 for 1080p. Enabling audio adds $0.05, and multi-clip mode adds $0.10 (or $0.15 with audio). For 8-second videos, costs double; for 10-second videos, costs are 2.2x the 5-second base (1080p not supported for 10s). For $1 you can run this model with approximately 2 times.","published_at":"2025-12-01T17:08:41.560000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f921b/fEI40T08g70A0lkG6ll83_Wpe6ebRg.png","title":"PixVerse V5.5 Image To Video"},{"category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v5.5","endpoint_id":"fal-ai/pixverse/v5.5/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. Longer durations cost more. 1080p videos are limited to 5 or 8 seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":false,"description":"Enable multi-clip generation with dynamic camera changes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_multi_clip_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5s video in single-clip mode without audio, your request will cost $0.15 for 360p and 540p, $0.2 for 720p, and $0.4 for 1080p. Enabling audio adds $0.05, and multi-clip mode adds $0.10 (or $0.15 with audio). For 8-second videos, costs double; for 10-second videos, costs are 2.2x the 5-second base (1080p not supported for 10s). For $1 you can run this model with approximately 2 times.","published_at":"2025-12-01T16:59:49.183000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cc/poyvEi1p-X7BvVUUq5ZdG_qMPjpi2n.png","title":"PixVerse V5.5 Text To Video"},{"category":"image-to-video","description":"Pixverse Transition","endpoint_id":"fal-ai/pixverse/v5.5/transition","family":"","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. Longer durations cost more. 1080p videos are limited to 5 or 8 seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5-second video in single-clip mode without audio, your request will cost $0.45 for 360p and 540p, $0.60 for 720p, and $1.20 for 1080p. Enabling audio adds $0.10, and multi-clip mode adds $0.30 (or $0.40 with audio). For 8-second videos, costs double; for 10-second videos, costs are 2.2x the 5-second base (1080p not supported for 10s). With $1, you can run this model approximately 2.2 times for a basic 5s video at 540p.","published_at":"2025-12-02T08:44:08.938000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92ce/v6VCDoaON8GsXnLz4NRtA_W03Bhbsr.png","title":"PixVerse V5.5 Transition"},{"category":"image-to-video","description":"Use the latest pixverse v5.6 model to turn your texts and images into amazing videos.","endpoint_id":"fal-ai/pixverse/v5.6/image-to-video","family":"PixVerse 5.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 1080p videos are limited to 5 or 8 seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5s video without audio, your request will cost $0.35 for 360p and 540p, $0.45 for 720p, and $0.75 for 1080p. Enabling audio adds $0.45 for 360p/540p/720p, and $0.75 for 1080p. For 8-second videos, costs are 2x the 5-second base; for 10-second videos, costs are 2.2x the 5-second base for 360p/540p and 720p (1080p not supported for 10s).","published_at":"2026-01-26T17:16:21.492000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf684/NHFUK0Vloyg4QuqEQDdxP_e3dc7704795542dfa183ecf6423c7883.jpg","title":"PixVerse V5.6 Image To Video"},{"category":"text-to-video","description":"Use the latest pixverse v5.6 model to turn your texts into amazing videos.","endpoint_id":"fal-ai/pixverse/v5.6/text-to-video","family":"Pixverse 5.6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 1080p videos are limited to 5 or 8 seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5s video without audio, your request will cost $0.35 for 360p and 540p, $0.45 for 720p, and $0.75 for 1080p. Enabling audio adds $0.45 for 360p/540p/720p, and $0.75 for 1080p. For 8-second videos, costs are 2x the 5-second base; for 10-second videos, costs are 2.2x the 5-second base for 360p/540p and 720p (1080p not supported for 10s).","published_at":"2026-01-26T17:02:31.936000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf630/B3GZjoCeMcK3mjcRg_gSU_cdbadbe8b3d84cd1a4bbfb2ef6f3675b.jpg","title":"PixVerse V5.6 Text To Video"},{"category":"image-to-video","description":"Use the latest pixverse v5.6 model to turn your texts and images into amazing videos.","endpoint_id":"fal-ai/pixverse/v5.6/transition","family":"","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 1080p videos are limited to 5 or 8 seconds","enum":["5","8","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For a 5s video without audio, your request will cost $0.35 for 360p and 540p, $0.45 for 720p, and $0.75 for 1080p. Enabling audio adds $0.45 for 360p/540p/720p, and $0.75 for 1080p. For 8-second videos, costs are 2x the 5-second base; for 10-second videos, costs are 2.2x the 5-second base for 360p/540p and 720p (1080p not supported for 10s).","published_at":"2026-01-26T17:28:03.386000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf6c6/5g6zE3Sjy-aR-GBc8DhWT_603ad74d67aa47b68cab750e1cf9b5a6.jpg","title":"PixVerse V5.6 Transition"},{"category":"image-to-video","description":"Generate high quality video clips with different effects using PixVerse v5","endpoint_id":"fal-ai/pixverse/v5/effects","family":"","inputs":[{"default":null,"description":"The effect to apply to the video","enum":["Kiss Me AI","Kiss","Muscle Surge","Warmth of Jesus","Anything, Robot","The Tiger Touch","Hug","Holy Wings","Microwave","Zombie Mode","Squid Game","Baby Face","Black Myth: Wukong","Long Hair Magic","Leggy Run","Fin-tastic Mermaid","Punch Face","Creepy Devil Smile","Thunder God","Eye Zoom Challenge","Who's Arrested?","Baby Arrived","Werewolf Rage","Bald Swipe","BOOM DROP","Huge Cutie","Liquid Metal","Sharksnap!","Dust Me Away","3D Figurine Factor","Bikini Up","My Girlfriends","My Boyfriends","Subject 3 Fever","Earth Zoom","Pole Dance","Vroom Dance","GhostFace Terror","Dragon Evoker","Skeletal Bae","Summoning succubus","Halloween Voodoo Doll","3D Naked-Eye AD","Package Explosion","Dishes Served","Ocean ad","Supermarket AD","Tree doll","Come Feel My Abs","The Bicep Flex","London Elite Vibe","Flora Nymph Gown","Christmas Costume","It's Snowy","Reindeer Cruiser","Snow Globe Maker","Pet Christmas Outfit","Adopt a Polar Pal","Cat Christmas Box","Starlight Gift Box","Xmas Poster","Pet Christmas Tree","City Santa Hat","Stocking Sweetie","Christmas Night","Xmas Front Page Karma","Grinch's Xmas Hijack","Giant Product","Truck Fashion Shoot","Beach AD","Shoal Surround","Mechanical Assembly","Lighting AD","Billboard AD","Product close-up","Parachute Delivery","Dreamlike Cloud","Macaron Machine","Poster AD","Truck AD","Graffiti AD","3D Figurine Factory","The Exclusive First Class","Art Zoom Challenge","I Quit","Hitchcock Dolly Zoom","Smell the Lens","I believe I can fly","Strikout Dance","Courtside Cam","Pit Crew Moment","K-Baseball Sprint","Toddler Doodle","Idol Ending","Apex Dance","OmniHero Forge","Palm Decode","The Age Ripple","My Future Is Limitless","Knee Slide","Epic Goal Save","Sideline Ball Boy","Cup Celebration","Victory Roar","Vuvuzela Fan","World Champion Lift","Tunnel to Captain","Liquid Soccer Morph","Jump Into Crowd 2","Golden Pitch Crasher","Stadium Fan Cam","Broadcast Moto GP","The Grotesque Clay","Rookie Star Card","The Final Hug","Sharp Post-Match Comment","Street Maverick","Pitch Legend","One Step At A Time","Birthday Mirror","Superstar Lobby","Final Battle Room","Top of the World","Pixel World","Mint in Box","Hands up, Hand","Flora Nymph Go","Somber Embrace","Beam me up","Suit Swagger"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect","required":true,"type":"enum"},{"default":null,"description":"Optional URL of the image to use as the first frame. If not provided, generates from text","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-08-23T10:55:07.548000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V5 Effects"},{"category":"image-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v5","endpoint_id":"fal-ai/pixverse/v5/image-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-08-23T10:53:29.956000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9221/wRlAOIJ9KuJL0CbH0qqSG_G7ADHYoi.png","title":"PixVerse V5 Image To Video"},{"category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v5","endpoint_id":"fal-ai/pixverse/v5/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-08-23T10:50:22.733000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V5 Text To Video"},{"category":"image-to-video","description":"Create seamless transition between images using PixVerse v5","endpoint_id":"fal-ai/pixverse/v5/transition","family":"","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"The duration of the generated video in seconds","enum":["5","8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.15 for 360p and 540p, $0.2 for 720p and $0.4 for 1080p. For $1 you can run this model with approximately 2 times.","published_at":"2025-08-23T10:56:18.163000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","title":"PixVerse V5 Transition"},{"category":"video-to-video","description":"Pixverse's latest v6 Model.","endpoint_id":"fal-ai/pixverse/v6/extend","family":"","inputs":[{"default":null,"description":"URL of the input video to extend","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Prompt describing how to extend the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the extended video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.025 per second without audio and $0.035 per second with audio. For 540p, it will cost $0.035 per second without audio and $0.045 per second with audio. For 720p, it will cost $0.045 per second without audio and $0.060 per second with audio. For 1080p, it will cost $0.090 per second without audio and $0.115 per second with audio. For $1 you can run this model for approximately 40 seconds at 360p (no audio) or about 11 seconds at 1080p (no audio).","published_at":"2026-03-29T11:11:49.660000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94048b/du-U-EA4tSGw2eo5YnJnW_0ceb86d70db5420f9fd294d247f5f843.jpg","title":"PixVerse V6 Extend"},{"category":"image-to-video","description":"Pixverse's latest V6 Model","endpoint_id":"fal-ai/pixverse/v6/image-to-video","family":"Pixverse 6","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":false,"description":"Enable multi-clip generation with dynamic camera changes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_multi_clip_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.025 per second without audio and $0.035 per second with audio. For 540p, it will cost $0.035 per second without audio and $0.045 per second with audio. For 720p, it will cost $0.045 per second without audio and $0.060 per second with audio. For 1080p, it will cost $0.090 per second without audio and $0.115 per second with audio. For $1 you can run this model for approximately 40 seconds at 360p (no audio) or about 11 seconds at 1080p (no audio).","published_at":"2026-03-29T09:44:52.746000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94048a/NbqGsBzItNNlvMmlYie7E_7d241b8764b64124b42edbcd5da51960.jpg","title":"PixVerse V6 Image To Video"},{"category":"text-to-video","description":"Pixverse's latest v6 Model.","endpoint_id":"fal-ai/pixverse/v6/text-to-video","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":false,"description":"Enable multi-clip generation with dynamic camera changes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_multi_clip_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.025 per second without audio and $0.035 per second with audio. For 540p, it will cost $0.035 per second without audio and $0.045 per second with audio. For 720p, it will cost $0.045 per second without audio and $0.060 per second with audio. For 1080p, it will cost $0.090 per second without audio and $0.115 per second with audio. For $1 you can run this model for approximately 40 seconds at 360p (no audio) or about 11 seconds at 1080p (no audio).","published_at":"2026-03-29T09:43:09.635000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a940489/sEtg0Kth_fWhHMR5MS664_222abe748d96461ba565ba860c3061d8.jpg","title":"PixVerse V6 Text To Video"},{"category":"image-to-video","description":"Pixverse's latest v6 Model.","endpoint_id":"fal-ai/pixverse/v6/transition","family":"","inputs":[{"default":null,"description":"The prompt for the transition","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"The resolution of the generated video","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"","description":"Negative prompt to be used for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The style of the generated video","enum":["anime","3d_animation","clay","comic","cyberpunk"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Enable audio generation (BGM, SFX, dialogue)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio_switch","required":false,"type":"boolean"},{"default":false,"description":"Enable multi-clip generation with dynamic camera changes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_multi_clip_switch","required":false,"type":"boolean"},{"default":null,"description":"Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision","enum":["enabled","disabled","auto"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_type","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"}],"lab":"Pixverse","output_kind":"video","output_props":["video"],"pricing":"Billing is calculated per second of video generated. For 360p, your request will cost $0.025 per second without audio and $0.035 per second with audio. For 540p, it will cost $0.035 per second without audio and $0.045 per second with audio. For 720p, it will cost $0.045 per second without audio and $0.060 per second with audio. For 1080p, it will cost $0.090 per second without audio and $0.115 per second with audio. For $1 you can run this model for approximately 40 seconds at 360p (no audio) or about 11 seconds at 1080p (no audio).","published_at":"2026-03-29T11:13:01.862000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94048c/mHSoHdPA4NFw5xaGR8lgF_4fb060e5ef624dc6a038a532134bee1e.jpg","title":"PixVerse V6 Transition"},{"category":"text-to-image","description":"State-of-the-art open-source model in aesthetic quality","endpoint_id":"fal-ai/playground-v25","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":3,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["timings","images","has_nsfw_concepts","prompt","seed"],"pricing":"","published_at":"2024-04-25T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cc/FJ-QJZqazTLZ8kOWIHpDF_Bo9fmwAg.png","title":"Playground v2.5"},{"category":"image-to-image","description":"State-of-the-art open-source model in aesthetic quality","endpoint_id":"fal-ai/playground-v25/image-to-image","family":"","inputs":[{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":65,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["timings","images","has_nsfw_concepts","prompt","seed"],"pricing":"","published_at":"2024-02-21T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9396/NCUSwF5bD4_A07etweHp0_9MUuG2Df.png","title":"Playground v2.5"},{"category":"image-to-image","description":"State-of-the-art open-source model in aesthetic quality","endpoint_id":"fal-ai/playground-v25/inpainting","family":"","inputs":[{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":65,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":3,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The URL of the mask to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["timings","images","has_nsfw_concepts","prompt","seed"],"pricing":"","published_at":"2024-02-21T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939a/Wi2QKndRxhpADk9k-sWhs_S0QgU3k5.png","title":"Playground v2.5"},{"category":"text-to-image","description":"Pony V7 is a finetuned text to image for superior aesthetics and prompt following.","endpoint_id":"fal-ai/pony-v7","family":"","inputs":[{"default":null,"description":"The prompt to generate images from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generating images","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"Classifier free guidance scale","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to take","enum":null,"is_list":false,"max":50,"media_kind":null,"min":20,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"gpu","description":"The source of the noise to use for generating images.\n            If set to 'gpu', the noise will be generated on the GPU.\n            If set to 'cpu', the noise will be generated on the CPU.","enum":["gpu","cpu"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"noise_source","required":false,"type":"enum"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","prompt","timings","seed","images"],"pricing":"","published_at":"2025-05-05T08:25:39.654000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-5.jpg","title":"Pony V7"},{"category":"image-to-image","description":"Post Processing is an endpoint that can enhance images using a variety of techniques including grain, blur, sharpen, and more.","endpoint_id":"fal-ai/post-processing","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"Enable film grain effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_grain","required":false,"type":"boolean"},{"default":0.4,"description":"Film grain intensity (when enabled)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"grain_intensity","required":false,"type":"number"},{"default":10,"description":"Film grain scale (when enabled)","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"grain_scale","required":false,"type":"number"},{"default":"modern","description":"Style of film grain to apply","enum":["modern","analog","kodak","fuji","cinematic","newspaper"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grain_style","required":false,"type":"enum"},{"default":false,"description":"Enable color correction","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_color_correction","required":false,"type":"boolean"},{"default":0,"description":"Color temperature adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0,"description":"Brightness adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"brightness","required":false,"type":"number"},{"default":0,"description":"Contrast adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"contrast","required":false,"type":"number"},{"default":0,"description":"Saturation adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"saturation","required":false,"type":"number"},{"default":1,"description":"Gamma adjustment","enum":null,"is_list":false,"max":2.2,"media_kind":null,"min":0.2,"multiline":false,"name":"gamma","required":false,"type":"number"},{"default":false,"description":"Enable chromatic aberration","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_chromatic","required":false,"type":"boolean"},{"default":0,"description":"Red channel shift amount","enum":null,"is_list":false,"max":20,"media_kind":null,"min":-20,"multiline":false,"name":"red_shift","required":false,"type":"integer"},{"default":"horizontal","description":"Red channel shift direction","enum":["horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"red_direction","required":false,"type":"enum"},{"default":0,"description":"Green channel shift amount","enum":null,"is_list":false,"max":20,"media_kind":null,"min":-20,"multiline":false,"name":"green_shift","required":false,"type":"integer"},{"default":"horizontal","description":"Green channel shift direction","enum":["horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"green_direction","required":false,"type":"enum"},{"default":0,"description":"Blue channel shift amount","enum":null,"is_list":false,"max":20,"media_kind":null,"min":-20,"multiline":false,"name":"blue_shift","required":false,"type":"integer"},{"default":"horizontal","description":"Blue channel shift direction","enum":["horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"blue_direction","required":false,"type":"enum"},{"default":false,"description":"Enable blur effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_blur","required":false,"type":"boolean"},{"default":"gaussian","description":"Type of blur to apply","enum":["gaussian","kuwahara"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"blur_type","required":false,"type":"enum"},{"default":3,"description":"Blur radius","enum":null,"is_list":false,"max":31,"media_kind":null,"min":0,"multiline":false,"name":"blur_radius","required":false,"type":"integer"},{"default":1,"description":"Sigma for Gaussian blur","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0.1,"multiline":false,"name":"blur_sigma","required":false,"type":"number"},{"default":false,"description":"Enable vignette effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_vignette","required":false,"type":"boolean"},{"default":0.5,"description":"Vignette strength (when enabled)","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"vignette_strength","required":false,"type":"number"},{"default":false,"description":"Enable parabolize effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_parabolize","required":false,"type":"boolean"},{"default":1,"description":"Parabolize coefficient","enum":null,"is_list":false,"max":10,"media_kind":null,"min":-10,"multiline":false,"name":"parabolize_coeff","required":false,"type":"number"},{"default":0.5,"description":"Vertex X position","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"vertex_x","required":false,"type":"number"},{"default":0.5,"description":"Vertex Y position","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"vertex_y","required":false,"type":"number"},{"default":false,"description":"Enable color tint effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_tint","required":false,"type":"boolean"},{"default":1,"description":"Tint strength","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"tint_strength","required":false,"type":"number"},{"default":"sepia","description":"Tint color mode","enum":["sepia","red","green","blue","cyan","magenta","yellow","purple","orange","warm","cool","lime","navy","vintage","rose","teal","maroon","peach","lavender","olive"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tint_mode","required":false,"type":"enum"},{"default":false,"description":"Enable dissolve effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_dissolve","required":false,"type":"boolean"},{"default":"","description":"URL of second image for dissolve","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"dissolve_image_url","required":false,"type":"string"},{"default":0.5,"description":"Dissolve blend factor","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"dissolve_factor","required":false,"type":"number"},{"default":false,"description":"Enable dodge and burn effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_dodge_burn","required":false,"type":"boolean"},{"default":0.5,"description":"Dodge and burn intensity","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"dodge_burn_intensity","required":false,"type":"number"},{"default":"dodge","description":"Dodge and burn mode","enum":["dodge","burn","dodge_and_burn","burn_and_dodge","color_dodge","color_burn","linear_dodge","linear_burn"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dodge_burn_mode","required":false,"type":"enum"},{"default":false,"description":"Enable glow effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_glow","required":false,"type":"boolean"},{"default":1,"description":"Glow intensity","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"glow_intensity","required":false,"type":"number"},{"default":5,"description":"Glow blur radius","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"glow_radius","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-02-18T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing"},{"category":"image-to-image","description":"Apply Gaussian or Kuwahara blur effects with adjustable radius and sigma parameters","endpoint_id":"fal-ai/post-processing/blur","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"gaussian","description":"Type of blur to apply","enum":["gaussian","kuwahara"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"blur_type","required":false,"type":"enum"},{"default":3,"description":"Blur radius","enum":null,"is_list":false,"max":31,"media_kind":null,"min":0,"multiline":false,"name":"blur_radius","required":false,"type":"integer"},{"default":1,"description":"Sigma for Gaussian blur","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0.1,"multiline":false,"name":"blur_sigma","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T18:49:58.071000+00:00","thumbnail":"https://fal.media/files/panda/bjwlW3KSsaWKc_0aK5zu1_1bd1f105d15a43618789039ab333c21a.jpg","title":"Post Processing Blur"},{"category":"image-to-image","description":"Create chromatic aberration by shifting red, green, and blue channels horizontally or vertically with customizable shift amounts.","endpoint_id":"fal-ai/post-processing/chromatic-aberration","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0,"description":"Red channel shift amount","enum":null,"is_list":false,"max":20,"media_kind":null,"min":-20,"multiline":false,"name":"red_shift","required":false,"type":"integer"},{"default":"horizontal","description":"Red channel shift direction","enum":["horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"red_direction","required":false,"type":"enum"},{"default":0,"description":"Green channel shift amount","enum":null,"is_list":false,"max":20,"media_kind":null,"min":-20,"multiline":false,"name":"green_shift","required":false,"type":"integer"},{"default":"horizontal","description":"Green channel shift direction","enum":["horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"green_direction","required":false,"type":"enum"},{"default":0,"description":"Blue channel shift amount","enum":null,"is_list":false,"max":20,"media_kind":null,"min":-20,"multiline":false,"name":"blue_shift","required":false,"type":"integer"},{"default":"horizontal","description":"Blue channel shift direction","enum":["horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"blue_direction","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T18:51:01+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Chromatic Aberration"},{"category":"image-to-image","description":"Adjust color temperature, brightness, contrast, saturation, and gamma values for color correction.","endpoint_id":"fal-ai/post-processing/color-correction","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0,"description":"Color temperature adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0,"description":"Brightness adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"brightness","required":false,"type":"number"},{"default":0,"description":"Contrast adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"contrast","required":false,"type":"number"},{"default":0,"description":"Saturation adjustment","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-100,"multiline":false,"name":"saturation","required":false,"type":"number"},{"default":1,"description":"Gamma adjustment","enum":null,"is_list":false,"max":2.2,"media_kind":null,"min":0.2,"multiline":false,"name":"gamma","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T18:51:53.197000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9393/Y6AttcAmrTnEPSbrjZDLR_7pNcbkzH.png","title":"Post Processing Color Correction"},{"category":"image-to-image","description":"Apply various color tints (sepia, red, green, blue, cyan, magenta, yellow, purple, orange, warm, cool, lime, navy, vintage, rose, teal, maroon, peach, lavender, olive) with adjustable strength.","endpoint_id":"fal-ai/post-processing/color-tint","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"Tint strength","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"tint_strength","required":false,"type":"number"},{"default":"sepia","description":"Tint color mode","enum":["sepia","red","green","blue","cyan","magenta","yellow","purple","orange","warm","cool","lime","navy","vintage","rose","teal","maroon","peach","lavender","olive"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tint_mode","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T18:52:48.294000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Color Tint"},{"category":"image-to-image","description":"Reduce color saturation using different methods (luminance Rec.709, luminance Rec.601, average, lightness) with adjustable factor.","endpoint_id":"fal-ai/post-processing/desaturate","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"Desaturation factor","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"desaturate_factor","required":false,"type":"number"},{"default":"luminance (Rec.709)","description":"Desaturation method","enum":["luminance (Rec.709)","luminance (Rec.601)","average","lightness"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"desaturate_method","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T18:53:36.237000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Desaturate"},{"category":"image-to-image","description":"Blend two images together using smooth linear interpolation with a configurable blend factor.","endpoint_id":"fal-ai/post-processing/dissolve","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of second image for dissolve","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"dissolve_image_url","required":true,"type":"string"},{"default":0.5,"description":"Dissolve blend factor","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"dissolve_factor","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T18:54:24.846000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Dissolve"},{"category":"image-to-image","description":"Apply dodge and burn effects with multiple modes and adjustable intensity.","endpoint_id":"fal-ai/post-processing/dodge-burn","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.5,"description":"Dodge and burn intensity","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"dodge_burn_intensity","required":false,"type":"number"},{"default":"dodge","description":"Dodge and burn mode","enum":["dodge","burn","dodge_and_burn","burn_and_dodge","color_dodge","color_burn","linear_dodge","linear_burn"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dodge_burn_mode","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T19:05:17.650000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Dodge Burn"},{"category":"image-to-image","description":"Apply film grain effect with different styles (modern, analog, kodak, fuji, cinematic, newspaper) and customizable intensity and scale","endpoint_id":"fal-ai/post-processing/grain","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.4,"description":"Film grain intensity","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"grain_intensity","required":false,"type":"number"},{"default":10,"description":"Film grain scale","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"grain_scale","required":false,"type":"number"},{"default":"modern","description":"Style of film grain to apply","enum":["modern","analog","kodak","fuji","cinematic","newspaper"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"grain_style","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T19:07:29.002000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Grain"},{"category":"image-to-image","description":"Apply a parabolic distortion effect with configurable coefficient and vertex position.","endpoint_id":"fal-ai/post-processing/parabolize","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"Parabolize coefficient","enum":null,"is_list":false,"max":10,"media_kind":null,"min":-10,"multiline":false,"name":"parabolize_coeff","required":false,"type":"number"},{"default":0.5,"description":"Vertex X position","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"vertex_x","required":false,"type":"number"},{"default":0.5,"description":"Vertex Y position","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"vertex_y","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T19:08:11.793000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/post-process/post-processing.webp","title":"Post Processing Parabolize"},{"category":"image-to-image","description":"Apply sharpening effects with three modes: basic unsharp mask, smart sharpening with edge preservation, and Contrast Adaptive Sharpening (CAS).","endpoint_id":"fal-ai/post-processing/sharpen","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"basic","description":"Type of sharpening to apply","enum":["basic","smart","cas"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sharpen_mode","required":false,"type":"enum"},{"default":1,"description":"Sharpen radius (for basic mode)","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"sharpen_radius","required":false,"type":"integer"},{"default":1,"description":"Sharpen strength (for basic mode)","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.1,"multiline":false,"name":"sharpen_alpha","required":false,"type":"number"},{"default":7,"description":"Noise radius for smart sharpen","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"noise_radius","required":false,"type":"integer"},{"default":0.75,"description":"Edge preservation factor","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"preserve_edges","required":false,"type":"number"},{"default":5,"description":"Smart sharpen strength","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"smart_sharpen_strength","required":false,"type":"number"},{"default":0.5,"description":"Smart sharpen blend ratio","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"smart_sharpen_ratio","required":false,"type":"number"},{"default":0.8,"description":"CAS sharpening amount","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cas_amount","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T19:09:38.467000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d4/R9vwIWQ5aIxovUgAyPxC-_QBHHRQEl.png","title":"Post Processing Sharpen"},{"category":"image-to-image","description":"Apply solarization effect by inverting pixel values above a threshold","endpoint_id":"fal-ai/post-processing/solarize","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.5,"description":"Solarize threshold","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"solarize_threshold","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T19:10:42.546000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939f/K2-1qgb9JEj72UmaPgVxj_sVQS0AnR.png","title":"Post Processing Solarize"},{"category":"image-to-image","description":"Add a darkening vignette effect around the edges of the image with adjustable strength","endpoint_id":"fal-ai/post-processing/vignette","family":"","inputs":[{"default":null,"description":"URL of image to process","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.5,"description":"Vignette strength","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"vignette_strength","required":false,"type":"number"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-07-01T19:20:16.130000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a4c/EKJrEFsDXkxTIgKthVJvk_JgKGslON.png","title":"Post Processing Vignette"},{"category":"image-to-image","description":"Tuning-free ID customization.","endpoint_id":"fal-ai/pulid","family":"","inputs":[{"default":null,"description":"List of reference faces, ideally 4 images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reference_images","required":true,"type":"json"},{"default":null,"description":"Prompt to generate the face from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"flaws in the eyes, flaws in the face, flaws, lowres, non-HDRi, low quality, worst quality,artifacts noise, text, watermark, glitch, deformed, mutated, ugly, disfigured, hands, low resolution, partially rendered objects,  deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed,blurry","description":"Negative prompt to generate the face from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":1.2,"description":"Guidance scale","enum":null,"is_list":false,"max":1.5,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Number of steps to take","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":{"height":1024,"width":768},"description":"Size of the generated image","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":0.8,"description":"ID scale","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"id_scale","required":false,"type":"number"},{"default":"fidelity","description":"Mode of generation","enum":["fidelity","extreme style"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":false,"description":"if you want to mix two ID image, please turn this on, otherwise, turn this off","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"id_mix","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2023-12-14T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f921f/u0ptA5BjdGXui9fYhAHx7_6x8UH1ug.png","title":"PuLID"},{"category":"audio-to-audio","description":"Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!","endpoint_id":"fal-ai/qwen-3-tts/clone-voice/0.6b","family":"Qwen 3","inputs":[{"default":null,"description":"URL to the reference audio file used for voice cloning.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"reference_text","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"json","output_props":["speaker_embedding"],"pricing":"","published_at":"2026-01-26T16:19:27.641000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf531/Rd0WefO2k5vCoxNgTSyzn_97cc41f0cf54490d8780612f0691f62f.jpg","title":"Qwen 3 TTS - Clone Voice [0.6B]"},{"category":"audio-to-audio","description":"Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!","endpoint_id":"fal-ai/qwen-3-tts/clone-voice/1.7b","family":"Qwen 3","inputs":[{"default":null,"description":"URL to the reference audio file used for voice cloning.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"reference_text","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"json","output_props":["speaker_embedding"],"pricing":"","published_at":"2026-01-26T16:20:48.076000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf538/p0L3C6l3FW2tyXCmwR0Fs_f6585c02243149fcadb77b0d4c6122b9.jpg","title":"Qwen 3 TTS - Clone Voice [1.7B]"},{"category":"text-to-speech","description":"Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model","endpoint_id":"fal-ai/qwen-3-tts/text-to-speech/0.6b","family":"Qwen 3","inputs":[{"default":null,"description":"The text to be converted to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Optional prompt to guide the style of the generated speech. This prompt will be ignored if a speaker embedding is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The voice to be used for speech synthesis, will be ignored if a speaker embedding is provided. Check out the **[documentation](https://github.com/QwenLM/Qwen3-TTS/tree/main?tab=readme-ov-file#custom-voice-generate)** for each voice's details and which language they primarily support.","enum":["Vivian","Serena","Uncle_Fu","Dylan","Eric","Ryan","Aiden","Ono_Anna","Sohee"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":"Auto","description":"The language of the voice.","enum":["Auto","English","Chinese","Spanish","French","German","Italian","Japanese","Korean","Portuguese","Russian"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":null,"description":"URL to a speaker embedding file in safetensors format, from `fal-ai/qwen-3-tts/clone-voice/0.6b` endpoint. If provided, the TTS model will use the cloned voice for synthesis instead of the predefined voices.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"speaker_voice_embedding_file_url","required":false,"type":"string"},{"default":null,"description":"Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"reference_text","required":false,"type":"string"},{"default":50,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"top_k","required":false,"type":"integer"},{"default":1,"description":"Top-p sampling parameter.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":0.9,"description":"Sampling temperature; higher => more random.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1.05,"description":"Penalty to reduce repeated tokens/codes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":true,"description":"Sampling switch for the sub-talker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subtalker_dosample","required":false,"type":"boolean"},{"default":50,"description":"Top-k for sub-talker sampling.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_top_k","required":false,"type":"integer"},{"default":1,"description":"Top-p for sub-talker sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_top_p","required":false,"type":"number"},{"default":0.9,"description":"Temperature for sub-talker sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_temperature","required":false,"type":"number"},{"default":200,"description":"Maximum number of new codec tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":1,"multiline":false,"name":"max_new_tokens","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-01-26T16:24:48.185000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf550/lVS8zCathHyxFPybUe2dc_4afab9bbcdfe49379b8e6d3c05970958.jpg","title":"Qwen 3 TTS - Text to Speech [0.6B]"},{"category":"text-to-speech","description":"Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model","endpoint_id":"fal-ai/qwen-3-tts/text-to-speech/1.7b","family":"Qwen 3","inputs":[{"default":null,"description":"The text to be converted to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Optional prompt to guide the style of the generated speech. This prompt will be ignored if a speaker embedding is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The voice to be used for speech synthesis, will be ignored if a speaker embedding is provided. Check out the **[documentation](https://github.com/QwenLM/Qwen3-TTS/tree/main?tab=readme-ov-file#custom-voice-generate)** for each voice's details and which language they primarily support.","enum":["Vivian","Serena","Uncle_Fu","Dylan","Eric","Ryan","Aiden","Ono_Anna","Sohee"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":"Auto","description":"The language of the voice.","enum":["Auto","English","Chinese","Spanish","French","German","Italian","Japanese","Korean","Portuguese","Russian"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":null,"description":"URL to a speaker embedding file in safetensors format, from `fal-ai/qwen-3-tts/clone-voice` endpoint. If provided, the TTS model will use the cloned voice for synthesis instead of the predefined voices.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"speaker_voice_embedding_file_url","required":false,"type":"string"},{"default":null,"description":"Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"reference_text","required":false,"type":"string"},{"default":50,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"top_k","required":false,"type":"integer"},{"default":1,"description":"Top-p sampling parameter.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":0.9,"description":"Sampling temperature; higher => more random.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1.05,"description":"Penalty to reduce repeated tokens/codes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":true,"description":"Sampling switch for the sub-talker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subtalker_dosample","required":false,"type":"boolean"},{"default":50,"description":"Top-k for sub-talker sampling.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_top_k","required":false,"type":"integer"},{"default":1,"description":"Top-p for sub-talker sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_top_p","required":false,"type":"number"},{"default":0.9,"description":"Temperature for sub-talker sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_temperature","required":false,"type":"number"},{"default":200,"description":"Maximum number of new codec tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":1,"multiline":false,"name":"max_new_tokens","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-01-26T16:26:09.816000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf558/-9L7FupJfteEP98jc8XPM_825292b8601e47b98a34ab5e5f6b3870.jpg","title":"Qwen 3 TTS - Text to Speech [1.7B]"},{"category":"text-to-speech","description":"Create custom voices using Qwen3-TTS Voice Design model and later use Clone Voice model to create your own voices!","endpoint_id":"fal-ai/qwen-3-tts/voice-design/1.7b","family":"Qwen 3","inputs":[{"default":null,"description":"The text to be converted to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"Auto","description":"The language of the voice to be designed.","enum":["Auto","English","Chinese","Spanish","French","German","Italian","Japanese","Korean","Portuguese","Russian"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":null,"description":"Optional prompt to guide the style of the generated speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":50,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"top_k","required":false,"type":"integer"},{"default":1,"description":"Top-p sampling parameter.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":0.9,"description":"Sampling temperature; higher => more random.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":1.05,"description":"Penalty to reduce repeated tokens/codes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":true,"description":"Sampling switch for the sub-talker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subtalker_dosample","required":false,"type":"boolean"},{"default":50,"description":"Top-k for sub-talker sampling.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_top_k","required":false,"type":"integer"},{"default":1,"description":"Top-p for sub-talker sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_top_p","required":false,"type":"number"},{"default":0.9,"description":"Temperature for sub-talker sampling.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"subtalker_temperature","required":false,"type":"number"},{"default":200,"description":"Maximum number of new codec tokens to generate.","enum":null,"is_list":false,"max":8192,"media_kind":null,"min":1,"multiline":false,"name":"max_new_tokens","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-01-26T16:28:35.599000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8bf564/hAR_lGabCTI37uWDVwiAp_64495f3b4ba447e7912cfd327b2cd0f1.jpg","title":"Qwen 3 TTS - Voice Design [1.7B]"},{"category":"text-to-image","description":"Qwen-Image is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing.","endpoint_id":"fal-ai/qwen-image","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":250,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"none","description":"Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"Enable turbo mode for faster generation with high quality. When enabled, uses optimized settings (10 steps, CFG=1.2).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_turbo","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"images","output_props":["images","timings","prompt","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-08-04T17:48:45.350000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b6/68wKdpl_xQVqBi3yNfnrY_ewDq2sZK.png","title":"Qwen Image"},{"category":"image-to-image","description":"Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model","endpoint_id":"fal-ai/qwen-image-2/edit","family":"Qwen Image","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English. Max 800 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.  Total number of pixels must be between 512x512 and 2048x2048.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Enable LLM prompt optimization for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-5000px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), WEBP.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-03-03T15:27:59.231000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90b2fc/Ktwh3M7POlvD59oS7rW2G_b395be4ae04343aaaf35a68bb92502c3.jpg","title":"Qwen Image 2"},{"category":"image-to-image","description":"Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model","endpoint_id":"fal-ai/qwen-image-2/pro/edit","family":"Qwen Image","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English;.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.  Total number of pixels must be between 512x512 and 2048x2048.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Enable LLM prompt optimization for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-5000px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), WEBP.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-03-03T15:29:45.350000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90b308/MaD9dwwc6YSa92Jhkhk0u_e29246f04f9646428d2ea04079417985.jpg","title":"Qwen Image 2"},{"category":"text-to-image","description":"Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model","endpoint_id":"fal-ai/qwen-image-2/pro/text-to-image","family":"Qwen Image","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English;.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image. Total number of pixels must be between 512x512 and 2048x2048.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Enable LLM prompt optimization for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-03-03T15:33:50.635000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90b320/-wZWpEebEQi20T6Z5ewms_ab61b57446c945a4beb6d3cab6b9367c.jpg","title":"Qwen Image 2"},{"category":"text-to-image","description":"Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model","endpoint_id":"fal-ai/qwen-image-2/text-to-image","family":"Qwen Image","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image. Total number of pixels must be between 512x512 and 2048x2048.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Enable LLM prompt optimization for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-03-03T15:32:25.533000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a90b317/m9a3NQEWM3KLDsoytKr9C_39eb7747f7cb475089d31bfee934a120.jpg","title":"Qwen Image 2"},{"category":"text-to-image","description":"Qwen Image 2512 is an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation.","endpoint_id":"fal-ai/qwen-image-2512","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"0.02 per megapixel (rounded up to the nearest megapixel)","published_at":"2025-12-30T18:09:37.348000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a88687b/hYfxa5kVUy6mpm42BBrXD_a2b18111ab6f4189b90f14100605aa85.jpg","title":"Qwen Image 2512"},{"category":"training","description":"Qwen Image 2512 LoRA training","endpoint_id":"fal-ai/qwen-image-2512-trainer","family":"Qwen","inputs":[{"default":null,"description":"URL to the input data zip archive for text-to-image training.\n\n    The zip should contain images with their corresponding text captions:\n\n    image.EXT and image.txt\n    For example:\n    photo.jpg and photo.txt\n\n    The text file contains the caption/prompt describing the target image.\n\n    If no text file is provided for an image, the default_caption will be used.\n\n    If no default_caption is provided and a text file is missing, the training will fail.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":0.0005,"description":"Learning rate for LoRA parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":1000,"description":"Number of steps to train for","enum":null,"is_list":false,"max":30000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"Your request will cost $0.0015 per step (minimum of 500 steps is charged). For $1.5 you can fine-tune a LoRA for 1000 steps.","published_at":"2026-01-01T03:13:13.085000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a88971d/RI2dnHIfi0FJ7BCSy83hh_089d63dbaf4b491ca15894cad8ee4741.jpg","title":"Qwen Image 2512 Trainer"},{"category":"text-to-image","description":"LoRA inference endpoint for Qwen Image 2512, an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation.","endpoint_id":"fal-ai/qwen-image-2512/lora","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2026-01-02T07:15:39.360000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a88be6b/el0hVqbMWfVjFm1jSR81z_311fa68b84444d11b75445e6ecb3f8b3.jpg","title":"Qwen Image 2512"},{"category":"image-to-image","description":"Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.","endpoint_id":"fal-ai/qwen-image-edit","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-08-18T07:37:22.171000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ae/o3GUoAzXNPChWFn7Y0zTV_7bVFtkNW.png","title":"Qwen Image Edit"},{"category":"image-to-image","description":"Endpoint for Qwen's Image Editing Plus model also known as Qwen-Image-Edit-2509. Has superior text editing capabilities and multi-image support.","endpoint_id":"fal-ai/qwen-image-edit-2509","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","seed","prompt"],"pricing":"","published_at":"2025-12-15T21:06:45.628000+00:00","thumbnail":"https://v3.fal.media/files/elephant/pGXxmNi6TrKTe864jBKW8_1bb43c6eab2349ab9c8cefbb24f3fd1b.jpg","title":"Qwen Image Edit 2509"},{"category":"image-to-image","description":"LoRA endpoint for the Qwen Image Edit 2509 model.","endpoint_id":"fal-ai/qwen-image-edit-2509-lora","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used to calculate the size of the output image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["seed","timings","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2025-12-15T21:23:02.927000+00:00","thumbnail":"https://v3.fal.media/files/penguin/X3V08aAYEqPmeSvVdLgN9_6be5ff6349c9459d92e7a5d7db8dadcc.jpg","title":"Qwen Image Edit 2509 Lora"},{"category":"image-to-image","description":"Add a realistic scene behind the object with white background","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/add-background","family":"Qwen","inputs":[{"default":null,"description":"The URLs of the images to edit. Provide an image with a white or clean background.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Remove white background and add a realistic scene behind the object","description":"Describe the background/scene you want to add behind the object. The model will remove the white background and add the specified environment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:37:41.612000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/Elzbk_5FjYriX_he9KRd4_34dd24f301c940f9a7387279be05cd76.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Generate full portrait from a cropped face photo","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait","family":"Qwen","inputs":[{"default":null,"description":"The URL of the cropped face image. Provide a close-up face photo.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Photography. A portrait of the person in professional attire with natural lighting","description":"Describe the full portrait you want to generate from the face. Include clothing, setting, pose, and style details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:39:48.880000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/gsWgQ__Xox_OncquLVuAH_1413fce9fe7c4e2fa59d589f3fc69448.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Create group photos","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/group-photo","family":"Qwen","inputs":[{"default":null,"description":"The URLs of the images to combine into a group photo. Provide 2 or more individual portrait images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Two people standing next to each other outside with a landscape background","description":"Describe the group photo scene, setting, and style. The model will maintain character consistency and add vintage effects like grain, blur, and retro filters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:41:41.859000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/Yzvztf6Z-TQRukl4KC3PH_aac2c75ac20f4ccd9bcf54ad9979c7a2.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Blend products into backgrounds with automatic perspective and lighting correction","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image with product to integrate into background.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Blend and integrate the product into the background","description":"Describe how to blend and integrate the product/element into the background. The model will automatically correct perspective, lighting and shadows for natural integration.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:43:51.495000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/kQP6sIJmyFzXBvEwY4n_g_83d331b99dff4ac58f6d32631a24a774.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to restore lighting for.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:45:10.369000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a860fd6/fyrneTtvBVrhWKMhSc0pj_9589e39060444dee9e7c33be9e16d1bf.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Precise camera position and angle control (rotation, zoom, vertical movement)","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to adjust camera angle for.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":0,"description":"Rotate camera left (positive) or right (negative) in degrees. Positive values rotate left, negative values rotate right.","enum":null,"is_list":false,"max":90,"media_kind":null,"min":-90,"multiline":false,"name":"rotate_right_left","required":false,"type":"number"},{"default":0,"description":"Move camera forward (0=no movement, 10=close-up)","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"move_forward","required":false,"type":"number"},{"default":0,"description":"Adjust vertical camera angle (-1=bird's-eye view/looking down, 0=neutral, 1=worm's-eye view/looking up)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":-1,"multiline":false,"name":"vertical_angle","required":false,"type":"number"},{"default":false,"description":"Enable wide-angle lens effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"wide_angle_lens","required":false,"type":"boolean"},{"default":1.25,"description":"The scale factor for the LoRA model. Controls the strength of the camera control effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:32:35.288000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/JbSGvZquN8vZSqhmHBK9o_6549790441a74cefa9f0afdfbd2a182c.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Create cinematic transitions and scene progressions (camera movements, framing changes)","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/next-scene","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to create the next scene from.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Next Scene: The camera moves forward revealing more of the scene","description":"Describe the camera movement, framing change, or scene transition. Start with 'Next Scene:' for best results. Examples: camera movements (dolly, push-in, pull-back), framing changes (wide to close-up), new elements entering frame.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:35:47.773000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/B2n7UmIRRBtpO5kLRoIg8_5dc0cbc4dd7f4a8aa3c55dd4eca753a8.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Remove unwanted elements (objects, people, text) while maintaining image consistency","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/remove-element","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image containing elements to remove.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Remove the specified element from the scene","description":"Specify what element(s) to remove from the image (objects, people, text, etc.). The model will cleanly remove the element while maintaining consistency of the rest of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:46:58.957000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/qjrxX6uCXnmLSaIK20Ju6_65d0867c22dd4fe6a5e6244062c4d7a1.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Remove existing lighting and apply soft, even illumination","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image with lighting/shadows to remove.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:48:14.384000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/z1Ze46BEziziJyYnGPfMA_411ef5a278eb4a60a4e7afab24167f6d.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"image-to-image","description":"Apply designs/graphics onto people's shirts","endpoint_id":"fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design","family":"Qwen","inputs":[{"default":null,"description":"The URLs of the images: first image is the person wearing a shirt, second image is the design/logo to put on the shirt.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Put this design on their shirt","description":"Describe what design to put on the shirt. The model will apply the design from your input image onto the person's shirt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-15T23:49:16.335000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/Sh9OfYjTHGDA8el8pezwY_754c1fb894234b08b52605905ff9ac2d.jpg","title":"Qwen Image Edit 2509 Lora Gallery"},{"category":"training","description":"LoRA trainer for Qwen Image Edit 2509","endpoint_id":"fal-ai/qwen-image-edit-2509-trainer","family":"Qwen","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n    The zip should contain pairs of images. The images should be named:\n\n    ROOT_start.EXT and ROOT_end.EXT\n    For example:\n    photo_start.jpg and photo_end.jpg\n\n    The zip can also contain more than one reference image for each image pair. The reference images should be named:\n    ROOT_start.EXT, ROOT_start2.EXT, ROOT_start3.EXT, ..., ROOT_end.EXT\n    For example:\n    photo_start.jpg, photo_start2.jpg, photo_end.jpg\n\n    The Reference Image Count field sh","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":0.0001,"description":"Learning rate for LoRA parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":1000,"description":"Number of steps to train for","enum":null,"is_list":false,"max":30000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"Your request will cost $4.0 per 1000-step training run. It scales per step, so a 2000-step training run costs $8. Note: 100 steps is the minimum step count, which will cost $0.40.","published_at":"2025-12-15T21:18:42.940000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/JUf-sx4jdYBPYceTS7zZL_f65366a94795483fad050e560a86513a.jpg","title":"Qwen Image Edit 2509 Trainer"},{"category":"image-to-image","description":"Endpoint for Qwen's Image Editing 2511 model.","endpoint_id":"fal-ai/qwen-image-edit-2511","family":"Qwen","inputs":[{"default":null,"description":"The prompt to edit the image with.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If None, uses the input image dimensions.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4.5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-12-19T19:37:10.346000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875820/o5xKLpZ3or9XkGYggf5wi_7470c2b213204f9eb76589e8958e4e81.jpg","title":"Qwen Image Edit 2511"},{"category":"image-to-image","description":"Generates same scene from different angles (azimuth/elevation) with Qwen image Edit 2511 and the Lora Multiple Angles","endpoint_id":"fal-ai/qwen-image-edit-2511-multiple-angles","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to adjust camera angle for.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":0,"description":"Horizontal rotation angle around the object in degrees. 0°=front view, 90°=right side, 180°=back view, 270°=left side, 360°=front view again.","enum":null,"is_list":false,"max":360,"media_kind":null,"min":0,"multiline":false,"name":"horizontal_angle","required":false,"type":"number"},{"default":0,"description":"Vertical camera angle in degrees. -30°=low-angle shot (looking up), 0°=eye-level, 30°=elevated, 60°=high-angle, 90°=bird's-eye view (looking down).","enum":null,"is_list":false,"max":90,"media_kind":null,"min":-30,"multiline":false,"name":"vertical_angle","required":false,"type":"number"},{"default":5,"description":"Camera zoom/distance. 0=wide shot (far away), 5=medium shot (normal), 10=close-up (very close).","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"zoom","required":false,"type":"number"},{"default":null,"description":"Additional text to append to the automatically generated prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"additional_prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the camera control effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":null,"description":"The size of the generated image. If not provided, the size of the input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"images","output_props":["prompt","seed","images"],"pricing":"","published_at":"2026-01-07T16:36:31.062000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a89744e/euqxNQk3eIDDL3GDS_pkZ.png","title":"Qwen Image Edit 2511 Multiple Angles"},{"category":"image-to-image","description":"Endpoint for Qwen's Image Editing 2511 model with LoRa support.","endpoint_id":"fal-ai/qwen-image-edit-2511/lora","family":"Qwen","inputs":[{"default":null,"description":"The prompt to edit the image with.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If None, uses the input image dimensions.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4.5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-12-30T22:32:05.672000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a887017/5CHxB7UP_2DDDrYwUMY1P_758632ead2224926b213655a720357b0.jpg","title":"Qwen Image Edit 2511"},{"category":"image-to-image","description":"LoRA inference endpoint for the Qwen Image Editing model.","endpoint_id":"fal-ai/qwen-image-edit-lora","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"none","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["seed","timings","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-09-10T12:39:02.983000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a1/LY4__rXKUvRejOQ4LcG8S_TR0f4Aow.png","title":"Qwen Image Edit Lora"},{"category":"image-to-image","description":"Endpoint for Qwen's Image Editing Plus model also known as Qwen-Image-Edit-2509. Has superior text editing capabilities and multi-image support.","endpoint_id":"fal-ai/qwen-image-edit-plus","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":50,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","seed","prompt"],"pricing":"","published_at":"2025-09-22T23:20:39.729000+00:00","thumbnail":"https://v3.fal.media/files/elephant/pGXxmNi6TrKTe864jBKW8_1bb43c6eab2349ab9c8cefbb24f3fd1b.jpg","title":"Qwen Image Edit Plus"},{"category":"image-to-image","description":"LoRA endpoint for the Qwen Image Edit Plus model.","endpoint_id":"fal-ai/qwen-image-edit-plus-lora","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used to calculate the size of the output image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["seed","timings","has_nsfw_concepts","images","prompt"],"pricing":"","published_at":"2025-10-03T21:13:29.106000+00:00","thumbnail":"https://v3.fal.media/files/penguin/X3V08aAYEqPmeSvVdLgN9_6be5ff6349c9459d92e7a5d7db8dadcc.jpg","title":"Qwen Image Edit Plus Lora"},{"category":"image-to-image","description":"Add a realistic scene behind the object with white background","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/add-background","family":"Qwen","inputs":[{"default":null,"description":"The URLs of the images to edit. Provide an image with a white or clean background.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Remove white background and add a realistic scene behind the object","description":"Describe the background/scene you want to add behind the object. The model will remove the white background and add the specified environment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T19:08:44.764000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/Elzbk_5FjYriX_he9KRd4_34dd24f301c940f9a7387279be05cd76.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Generate full portrait from a cropped face photo","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait","family":"Qwen","inputs":[{"default":null,"description":"The URL of the cropped face image. Provide a close-up face photo.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Photography. A portrait of the person in professional attire with natural lighting","description":"Describe the full portrait you want to generate from the face. Include clothing, setting, pose, and style details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T19:58:34.266000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/gsWgQ__Xox_OncquLVuAH_1413fce9fe7c4e2fa59d589f3fc69448.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Create group photos","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/group-photo","family":"Qwen","inputs":[{"default":null,"description":"The URLs of the images to combine into a group photo. Provide 2 or more individual portrait images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Two people standing next to each other outside with a landscape background","description":"Describe the group photo scene, setting, and style. The model will maintain character consistency and add vintage effects like grain, blur, and retro filters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:11:58.194000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/Yzvztf6Z-TQRukl4KC3PH_aac2c75ac20f4ccd9bcf54ad9979c7a2.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Blend products into backgrounds with automatic perspective and lighting correction","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image with product to integrate into background.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Blend and integrate the product into the background","description":"Describe how to blend and integrate the product/element into the background. The model will automatically correct perspective, lighting and shadows for natural integration.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:16:11.899000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/kQP6sIJmyFzXBvEwY4n_g_83d331b99dff4ac58f6d32631a24a774.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to restore lighting for.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-12-12T23:01:29.638000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a860fd6/fyrneTtvBVrhWKMhSc0pj_9589e39060444dee9e7c33be9e16d1bf.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Precise camera position and angle control (rotation, zoom, vertical movement)","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to adjust camera angle for.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":0,"description":"Rotate camera left (positive) or right (negative) in degrees. Positive values rotate left, negative values rotate right.","enum":null,"is_list":false,"max":90,"media_kind":null,"min":-90,"multiline":false,"name":"rotate_right_left","required":false,"type":"number"},{"default":0,"description":"Move camera forward (0=no movement, 10=close-up)","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"move_forward","required":false,"type":"number"},{"default":0,"description":"Adjust vertical camera angle (-1=bird's-eye view/looking down, 0=neutral, 1=worm's-eye view/looking up)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":-1,"multiline":false,"name":"vertical_angle","required":false,"type":"number"},{"default":false,"description":"Enable wide-angle lens effect","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"wide_angle_lens","required":false,"type":"boolean"},{"default":1.25,"description":"The scale factor for the LoRA model. Controls the strength of the camera control effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:40:36.367000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/JbSGvZquN8vZSqhmHBK9o_6549790441a74cefa9f0afdfbd2a182c.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Create cinematic transitions and scene progressions (camera movements, framing changes)","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/next-scene","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image to create the next scene from.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Next Scene: The camera moves forward revealing more of the scene","description":"Describe the camera movement, framing change, or scene transition. Start with 'Next Scene:' for best results. Examples: camera movements (dolly, push-in, pull-back), framing changes (wide to close-up), new elements entering frame.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:29:00.375000+00:00","thumbnail":"https://v3b.fal.media/files/b/elephant/B2n7UmIRRBtpO5kLRoIg8_5dc0cbc4dd7f4a8aa3c55dd4eca753a8.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Remove unwanted elements (objects, people, text) while maintaining image consistency","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/remove-element","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image containing elements to remove.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Remove the specified element from the scene","description":"Specify what element(s) to remove from the image (objects, people, text, etc.). The model will cleanly remove the element while maintaining consistency of the rest of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:32:00.206000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/qjrxX6uCXnmLSaIK20Ju6_65d0867c22dd4fe6a5e6244062c4d7a1.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Remove existing lighting and apply soft, even illumination","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting","family":"Qwen","inputs":[{"default":null,"description":"The URL of the image with lighting/shadows to remove.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:34:59.313000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/z1Ze46BEziziJyYnGPfMA_411ef5a278eb4a60a4e7afab24167f6d.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Apply designs/graphics onto people's shirts","endpoint_id":"fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design","family":"Qwen","inputs":[{"default":null,"description":"The URLs of the images: first image is the person wearing a shirt, second image is the design/logo to put on the shirt.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":6,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. Same seed with same prompt will produce same result.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker for the generated image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"Put this design on their shirt","description":"Describe what design to put on the shirt. The model will apply the design from your input image onto the person's shirt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The scale factor for the LoRA model. Controls the strength of the LoRA effect.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2025-11-11T20:37:16.566000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/Sh9OfYjTHGDA8el8pezwY_754c1fb894234b08b52605905ff9ac2d.jpg","title":"Qwen Image Edit Plus Lora Gallery"},{"category":"image-to-image","description":"Image to Image Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.","endpoint_id":"fal-ai/qwen-image-edit/image-to-image","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":0.94,"description":"Strength of the image-to-image transformation. Lower values preserve more of the original image.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-09-30T17:20:50.035000+00:00","thumbnail":"https://v3.fal.media/files/lion/y1wOAl3dW0LE43drzjWY3_71e9575367b14485b4a5ca83492c0e82.jpg","title":"Qwen Image Edit"},{"category":"image-to-image","description":"Inpainting Endpoint for the Qwen Edit Image editing model.","endpoint_id":"fal-ai/qwen-image-edit/inpaint","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"regular","description":"Acceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"The URL of the mask for inpainting","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":0.93,"description":"Strength of noising process for inpainting","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["prompt","images","timings","seed","has_nsfw_concepts"],"pricing":"","published_at":"2025-09-17T21:37:12.411000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9220/v5XmYo0ki7M9YE0JQ_aP9_s35YXe0h.png","title":"Qwen Image Edit"},{"category":"image-to-image","description":"Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers.","endpoint_id":"fal-ai/qwen-image-layered","family":"Qwen","inputs":[{"default":null,"description":"A caption for the input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of layers to generate.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_layers","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","has_nsfw_concepts","seed","prompt","timings"],"pricing":"Your request will cost $0.05 per image.","published_at":"2025-12-19T15:38:51.622000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a875720/ExJNkqptre1H0dUnnPQBQ_a7b65fa4293d45669d3958280e71b38d.jpg","title":"Qwen Image Layered"},{"category":"image-to-image","description":"Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers. Use loras to get your custom outputs.","endpoint_id":"fal-ai/qwen-image-layered/lora","family":"Qwen","inputs":[{"default":null,"description":"A caption for the input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of layers to generate.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"num_layers","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","has_nsfw_concepts","seed","prompt","timings"],"pricing":"","published_at":"2025-12-24T17:45:40.614000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a879d75/8tZ-zs49go2pWoUCnBy7P_a0de4be2e12e41cea3ad3d1822e877a1.jpg","title":"Qwen Image Layered"},{"category":"image-to-image","description":"Image editing endpoint for Qwen-Image-Max. Qwen Image Max improves upon the Qwen Image Plus series by enhancing the realism and naturalness of images.","endpoint_id":"fal-ai/qwen-image-max/edit","family":"Qwen Image","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English. Max 800 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The size of the generated image. If not provided, the size of the final input image will be used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Enable LLM prompt optimization for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-5000px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), WEBP.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-01-27T20:18:43.738000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1c81/hMoPEMrnsMl-BPesZ3v02_cb7c0df16e074d0fb5959090fc670856.jpg","title":"Qwen Image Max"},{"category":"text-to-image","description":"Text-to-Image endpoint for Qwen-Image-Max. Qwen Image Max improves upon the Qwen Image Plus series by enhancing the realism and naturalness of images.","endpoint_id":"fal-ai/qwen-image-max/text-to-image","family":"Qwen Image","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English. Max 800 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Enable LLM prompt optimization for better results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-01-27T20:21:53.796000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1c98/tClMYMPB6OkHzUHKQC6qf_65124fde152b47c9ab2db7bdf95340a0.jpg","title":"Qwen Image Max"},{"category":"image-to-image","description":"Qwen-Image (Image-to-Image) transforms and edits input images with high fidelity, enabling precise style transfer, enhancement, and creative modification.","endpoint_id":"fal-ai/qwen-image/image-to-image","family":"Qwen","inputs":[{"default":null,"description":"The prompt to generate the image with","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. By default, we will use the provided image for determining the image_size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":30,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":250,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":2.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":" ","description":"The negative prompt for the generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"none","description":"Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use up to 3 LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"Enable turbo mode for faster generation with high quality. When enabled, uses optimized settings (10 steps, CFG=1.2).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_turbo","required":false,"type":"boolean"},{"default":null,"description":"The reference image to guide the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.6,"description":"Denoising strength. 1.0 = fully remake; 0.0 = preserve original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","timings","prompt","seed","has_nsfw_concepts"],"pricing":"Your  request will cost $0.02 per megapixel.","published_at":"2025-08-25T12:14:09.649000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92ce/FpHGK5LeXsUG4lZEV2CIE_WYldevzr.png","title":"Qwen Image"},{"category":"text-to-image","description":"Generate realistic images.","endpoint_id":"fal-ai/realistic-vision","family":"","inputs":[{"default":"(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D ,3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)","description":"The negative prompt to use. Use it to address details that you don't want in the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":{"height":1024,"width":1024},"description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"","published_at":"2024-04-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/realistic-vision.jpeg","title":"Realistic Vision"},{"category":"image-to-3d","description":"Generate 3D models from one or more images using ReconViaGen 0.5","endpoint_id":"fal-ai/reconviagen-0.5","family":"","inputs":[{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1024,"description":"Output resolution; higher is slower but more detailed","enum":[512,1024,1536],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"mesh","description":"Sparse structure source. 'mesh' gives best quality, 'direct' is fastest, 'mvtrellis2' uses multi-view TRELLIS.2.","enum":["direct","mesh","mvtrellis2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ss_source","required":false,"type":"enum"},{"default":7.5,"description":"How closely the initial 3D structure follows the input. Higher values produce more faithful but potentially noisier results.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_strength","required":false,"type":"number"},{"default":0.7,"description":"Dampens artifacts from high guidance in stage 1.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for the initial structure.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"ss_sampling_steps","required":false,"type":"integer"},{"default":5,"description":"Controls noise schedule sharpness for structure generation.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"ss_rescale_t","required":false,"type":"number"},{"default":7.5,"description":"Guidance strength for SLat stage (only used when ss_source='mesh').","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"slat_guidance_strength","required":false,"type":"number"},{"default":0.5,"description":"Guidance rescale for SLat stage (only used when ss_source='mesh').","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"slat_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Sampling steps for SLat stage (only used when ss_source='mesh').","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Rescale T for SLat stage (only used when ss_source='mesh').","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"slat_rescale_t","required":false,"type":"number"},{"default":7.5,"description":"How closely the detailed geometry follows the input.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_strength","required":false,"type":"number"},{"default":0.5,"description":"Dampens artifacts from high guidance in the shape stage.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for shape refinement.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for shape refinement.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_rescale_t","required":false,"type":"number"},{"default":1,"description":"How closely the texture follows the input colors.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_strength","required":false,"type":"number"},{"default":0,"description":"Dampens artifacts from high guidance in the texture stage.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_rescale","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for texture generation.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for texture generation.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_rescale_t","required":false,"type":"number"},{"default":500000,"description":"Target number of vertices in the final mesh.","enum":null,"is_list":false,"max":2000000,"media_kind":null,"min":5000,"multiline":false,"name":"decimation_target","required":false,"type":"integer"},{"default":2048,"description":"Resolution of the texture image baked onto the mesh.","enum":[1024,2048,4096],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"},{"default":null,"description":"One or more views of the same object. Multiple views yield higher-quality 3D reconstruction.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"adaptive_guidance_weight","description":"Strategy for combining multi-view conditioning. 'adaptive_guidance_weight' works best in most cases. Only used when more than one image is provided.","enum":["average_right","weighted_average","sequential","average","adaptive_guidance_weight","fixed_guidance_rescale"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_image_strategy","required":false,"type":"enum"}],"lab":"","output_kind":"file","output_props":["model_glb","seed"],"pricing":"Your request will cost $0.25 for 512, $0.30 for 1024 or $0.35 for 1536.","published_at":"2026-04-07T03:18:27.695000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/iCm7SmeT-ZIOub4oF78G0_3wYazdBw.png","title":"ReconViaGen 0.5"},{"category":"text-to-image","description":"Recraft 20b is a new and affordable text-to-image model.","endpoint_id":"fal-ai/recraft-20b","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"realistic_image","description":"The style of the generated images. Vector images cost 2X as much.","enum":["any","realistic_image","digital_illustration","vector_illustration","realistic_image/b_and_w","realistic_image/enterprise","realistic_image/hard_flash","realistic_image/hdr","realistic_image/motion_blur","realistic_image/natural_light","realistic_image/studio_portrait","digital_illustration/2d_art_poster","digital_illustration/2d_art_poster_2","digital_illustration/3d","digital_illustration/80s","digital_illustration/engraving_color","digital_illustration/glow","digital_illustration/grain","digital_illustration/hand_drawn","digital_illustration/hand_drawn_outline","digital_illustration/handmade_3d","digital_illustration/infantile_sketch","digital_illustration/kawaii","digital_illustration/pixel_art","digital_illustration/psychedelic","digital_illustration/seamless","digital_illustration/voxel","digital_illustration/watercolor","vector_illustration/cartoon","vector_illustration/doodle_line_art","vector_illustration/engraving","vector_illustration/flat_2","vector_illustration/kawaii","vector_illustration/line_art","vector_illustration/line_circuit","vector_illustration/linocut","vector_illustration/seamless"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The ID of the custom style reference (optional)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.022 per image (or $0.044 if you are using a vector style). For $1 you can run this model approximately 45 times.","published_at":"2024-12-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_011.jpg","title":"Recraft 20b"},{"category":"image-to-image","description":"Enhances a given raster image using the 'creative upscale' tool, increasing image resolution, making the image sharper and cleaner.","endpoint_id":"fal-ai/recraft/upscale/creative","family":"","inputs":[{"default":null,"description":"The URL of the image to be upscaled. Must be in PNG format.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-05-07T13:10:35.699000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/recraft-creative-upscale.jpg","title":"Recraft Creative Upscale"},{"category":"image-to-image","description":"Enhances a given raster image using 'crisp upscale' tool, boosting resolution with a focus on refining small details and faces.","endpoint_id":"fal-ai/recraft/upscale/crisp","family":"","inputs":[{"default":null,"description":"The URL of the image to be upscaled. Must be in PNG format.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-05-07T13:07:59.554000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/recraft-creative-upscale.jpg","title":"Recraft Crisp Upscale"},{"category":"training","description":"Recraft V3 Create Style is capable of creating unique styles for Recraft V3 based on your images.","endpoint_id":"fal-ai/recraft/v3/create-style","family":"","inputs":[{"default":null,"description":"URL to zip archive with images, use PNG format. Maximum 5 images are allowed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"images_data_url","required":true,"type":"string"},{"default":"digital_illustration","description":"The base style of the generated images, this topic is covered above.","enum":["any","realistic_image","digital_illustration","vector_illustration","realistic_image/b_and_w","realistic_image/hard_flash","realistic_image/hdr","realistic_image/natural_light","realistic_image/studio_portrait","realistic_image/enterprise","realistic_image/motion_blur","realistic_image/evening_light","realistic_image/faded_nostalgia","realistic_image/forest_life","realistic_image/mystic_naturalism","realistic_image/natural_tones","realistic_image/organic_calm","realistic_image/real_life_glow","realistic_image/retro_realism","realistic_image/retro_snapshot","realistic_image/urban_drama","realistic_image/village_realism","realistic_image/warm_folk","digital_illustration/pixel_art","digital_illustration/hand_drawn","digital_illustration/grain","digital_illustration/infantile_sketch","digital_illustration/2d_art_poster","digital_illustration/handmade_3d","digital_illustration/hand_drawn_outline","digital_illustration/engraving_color","digital_illustration/2d_art_poster_2","digital_illustration/antiquarian","digital_illustration/bold_fantasy","digital_illustration/child_book","digital_illustration/child_books","digital_illustration/cover","digital_illustration/crosshatch","digital_illustration/digital_engraving","digital_illustration/expressionism","digital_illustration/freehand_details","digital_illustration/grain_20","digital_illustration/graphic_intensity","digital_illustration/hard_comics","digital_illustration/long_shadow","digital_illustration/modern_folk","digital_illustration/multicolor","digital_illustration/neon_calm","digital_illustration/noir","digital_illustration/nostalgic_pastel","digital_illustration/outline_details","digital_illustration/pastel_gradient","digital_illustration/pastel_sketch","digital_illustration/pop_art","digital_illustration/pop_renaissance","digital_illustration/street_art","digital_illustration/tablet_sketch","digital_illustration/urban_glow","digital_illustration/urban_sketching","digital_illustration/vanilla_dreams","digital_illustration/young_adult_book","digital_illustration/young_adult_book_2","vector_illustration/bold_stroke","vector_illustration/chemistry","vector_illustration/colored_stencil","vector_illustration/contour_pop_art","vector_illustration/cosmics","vector_illustration/cutout","vector_illustration/depressive","vector_illustration/editorial","vector_illustration/emotional_flat","vector_illustration/infographical","vector_illustration/marker_outline","vector_illustration/mosaic","vector_illustration/naivector","vector_illustration/roundish_flat","vector_illustration/segmented_colors","vector_illustration/sharp_contrast","vector_illustration/thin","vector_illustration/vector_photo","vector_illustration/vivid_shapes","vector_illustration/engraving","vector_illustration/line_art","vector_illustration/line_circuit","vector_illustration/linocut"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"base_style","required":false,"type":"enum"}],"lab":"Recraft","output_kind":"text","output_props":["style_id"],"pricing":"","published_at":"2025-05-07T12:54:56.466000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/recraft-v3-create-style.webp","title":"Recraft V3 Create Style"},{"category":"image-to-image","description":"Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.","endpoint_id":"fal-ai/recraft/v3/image-to-image","family":"","inputs":[{"default":null,"description":"A text description of areas to change.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the image to modify. Must be less than 5 MB in size, have resolution less than 16 MP and max dimension less than 4096 pixels.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":0.5,"description":"Defines the difference with the original image, should lie in [0, 1], where 0 means almost identical, and 1 means miserable similarity","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"realistic_image","description":"The style of the generated images. Vector images cost 2X as much.","enum":["any","realistic_image","digital_illustration","vector_illustration","realistic_image/b_and_w","realistic_image/hard_flash","realistic_image/hdr","realistic_image/natural_light","realistic_image/studio_portrait","realistic_image/enterprise","realistic_image/motion_blur","realistic_image/evening_light","realistic_image/faded_nostalgia","realistic_image/forest_life","realistic_image/mystic_naturalism","realistic_image/natural_tones","realistic_image/organic_calm","realistic_image/real_life_glow","realistic_image/retro_realism","realistic_image/retro_snapshot","realistic_image/urban_drama","realistic_image/village_realism","realistic_image/warm_folk","digital_illustration/pixel_art","digital_illustration/hand_drawn","digital_illustration/grain","digital_illustration/infantile_sketch","digital_illustration/2d_art_poster","digital_illustration/handmade_3d","digital_illustration/hand_drawn_outline","digital_illustration/engraving_color","digital_illustration/2d_art_poster_2","digital_illustration/antiquarian","digital_illustration/bold_fantasy","digital_illustration/child_book","digital_illustration/child_books","digital_illustration/cover","digital_illustration/crosshatch","digital_illustration/digital_engraving","digital_illustration/expressionism","digital_illustration/freehand_details","digital_illustration/grain_20","digital_illustration/graphic_intensity","digital_illustration/hard_comics","digital_illustration/long_shadow","digital_illustration/modern_folk","digital_illustration/multicolor","digital_illustration/neon_calm","digital_illustration/noir","digital_illustration/nostalgic_pastel","digital_illustration/outline_details","digital_illustration/pastel_gradient","digital_illustration/pastel_sketch","digital_illustration/pop_art","digital_illustration/pop_renaissance","digital_illustration/street_art","digital_illustration/tablet_sketch","digital_illustration/urban_glow","digital_illustration/urban_sketching","digital_illustration/vanilla_dreams","digital_illustration/young_adult_book","digital_illustration/young_adult_book_2","vector_illustration/bold_stroke","vector_illustration/chemistry","vector_illustration/colored_stencil","vector_illustration/contour_pop_art","vector_illustration/cosmics","vector_illustration/cutout","vector_illustration/depressive","vector_illustration/editorial","vector_illustration/emotional_flat","vector_illustration/infographical","vector_illustration/marker_outline","vector_illustration/mosaic","vector_illustration/naivector","vector_illustration/roundish_flat","vector_illustration/segmented_colors","vector_illustration/sharp_contrast","vector_illustration/thin","vector_illustration/vector_photo","vector_illustration/vivid_shapes","vector_illustration/engraving","vector_illustration/line_art","vector_illustration/line_circuit","vector_illustration/linocut"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The ID of the custom style reference (optional)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_id","required":false,"type":"string"},{"default":null,"description":"A text description of undesired elements on an image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.04 per image (or $0.08 if you are using a vector style). For $1 you can run this model approximately 25 times.","published_at":"2025-05-07T12:02:09.806000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/recraft-v3.webp","title":"Recraft V3"},{"category":"text-to-image","description":"Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.","endpoint_id":"fal-ai/recraft/v3/text-to-image","family":"","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"realistic_image","description":"The style of the generated images. Vector images cost 2X as much.","enum":["any","realistic_image","digital_illustration","vector_illustration","realistic_image/b_and_w","realistic_image/hard_flash","realistic_image/hdr","realistic_image/natural_light","realistic_image/studio_portrait","realistic_image/enterprise","realistic_image/motion_blur","realistic_image/evening_light","realistic_image/faded_nostalgia","realistic_image/forest_life","realistic_image/mystic_naturalism","realistic_image/natural_tones","realistic_image/organic_calm","realistic_image/real_life_glow","realistic_image/retro_realism","realistic_image/retro_snapshot","realistic_image/urban_drama","realistic_image/village_realism","realistic_image/warm_folk","digital_illustration/pixel_art","digital_illustration/hand_drawn","digital_illustration/grain","digital_illustration/infantile_sketch","digital_illustration/2d_art_poster","digital_illustration/handmade_3d","digital_illustration/hand_drawn_outline","digital_illustration/engraving_color","digital_illustration/2d_art_poster_2","digital_illustration/antiquarian","digital_illustration/bold_fantasy","digital_illustration/child_book","digital_illustration/child_books","digital_illustration/cover","digital_illustration/crosshatch","digital_illustration/digital_engraving","digital_illustration/expressionism","digital_illustration/freehand_details","digital_illustration/grain_20","digital_illustration/graphic_intensity","digital_illustration/hard_comics","digital_illustration/long_shadow","digital_illustration/modern_folk","digital_illustration/multicolor","digital_illustration/neon_calm","digital_illustration/noir","digital_illustration/nostalgic_pastel","digital_illustration/outline_details","digital_illustration/pastel_gradient","digital_illustration/pastel_sketch","digital_illustration/pop_art","digital_illustration/pop_renaissance","digital_illustration/street_art","digital_illustration/tablet_sketch","digital_illustration/urban_glow","digital_illustration/urban_sketching","digital_illustration/vanilla_dreams","digital_illustration/young_adult_book","digital_illustration/young_adult_book_2","vector_illustration/bold_stroke","vector_illustration/chemistry","vector_illustration/colored_stencil","vector_illustration/contour_pop_art","vector_illustration/cosmics","vector_illustration/cutout","vector_illustration/depressive","vector_illustration/editorial","vector_illustration/emotional_flat","vector_illustration/infographical","vector_illustration/marker_outline","vector_illustration/mosaic","vector_illustration/naivector","vector_illustration/roundish_flat","vector_illustration/segmented_colors","vector_illustration/sharp_contrast","vector_illustration/thin","vector_illustration/vector_photo","vector_illustration/vivid_shapes","vector_illustration/engraving","vector_illustration/line_art","vector_illustration/line_circuit","vector_illustration/linocut"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The ID of the custom style reference (optional)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_id","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"Your request will cost $0.04 per image (or $0.08 if you are using a vector style). For $1 you can run this model approximately 25 times.","published_at":"2025-05-07T11:59:27.643000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/recraft-v3.webp","title":"Recraft V3"},{"category":"text-to-image","description":"Recraft V4.1 Pro pushes the V4.1 model into high-resolution territory — up to 2048×2048 and ultra-wide formats. Made for hero imagery, campaign work, and print, it preserves the same design taste at sizes ready for the final deliverable.","endpoint_id":"fal-ai/recraft/v4.1/pro/text-to-image","family":"Recraft V4.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-05-14T15:54:09.506000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a2979/E3rD16GdXp6leLvvGPJZ6_2d0b0a34eb3e4ccc904d0de3c4abb40e.jpg","title":"Recraft V4.1 Text to Image Pro"},{"category":"text-to-image","description":"Recraft V4.1 Pro Vector generates large-format, fully editable SVGs with the structural clarity professional illustrators expect. Built for poster art, complex brand assets, and detailed scene illustration, it scales without losing geometric integrity.","endpoint_id":"fal-ai/recraft/v4.1/pro/text-to-vector","family":"Recraft V4.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-05-14T15:54:18.558000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a2977/jFvo4kOe07LCMIUCNAw0h_6d2cb19d7d954284b45cfa90e7ff66ba.jpg","title":"Recraft V4.1 Text to Vector Pro"},{"category":"text-to-image","description":"Recraft V4.1 builds on the design-first foundation of V4 with sharper prompt control and cleaner composition. Tuned for brand systems and editorial work, it delivers production-ready raster images that hold up next to a designer's hand.","endpoint_id":"fal-ai/recraft/v4.1/text-to-image","family":"Recraft V4.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-05-14T15:54:28.708000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a2972/dIomIOjaf_WjuINZkjGWQ_e2a8500d97f74dfdad75ba8cbd41d6e5.jpg","title":"Recraft V4.1 Text to Image"},{"category":"text-to-image","description":"Recraft V4.1 Vector turns prompts into fully editable SVGs with structured layers and clean geometry. Built for logos, icons, and illustration systems, it produces artwork that goes straight from generation into Figma or Illustrator.","endpoint_id":"fal-ai/recraft/v4.1/text-to-vector","family":"Recraft V4.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-05-14T15:54:43.175000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a2971/-tcT4xrw7bYtB1fwxaBg0_966bd9af562a4c5da33ce11dd7e610c9.jpg","title":"Recraft V4.1 Text to Vector"},{"category":"text-to-image","description":"Recraft V4.1 Utility Pro pairs the high-resolution output of V4.1 Pro with a faster, cost-efficient runtime. Designed for studios shipping large-format work at scale, it makes premium-quality raster generation viable across full creative pipelines.","endpoint_id":"fal-ai/recraft/v4.1/utility/pro/text-to-image","family":"Recraft V4.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-05-14T15:54:51.584000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a296f/a6KliSCyzQRZSnsrNpl02_224ab7fbc6cb43da868bd72a86dd875b.jpg","title":"Recraft V4.1 Utility Text to Image"},{"category":"text-to-image","description":"Recraft V4.1 Utility is a faster, lighter variant of V4.1 made for high-volume creative workflows. Ideal for ideation, A/B exploration, and content pipelines, it keeps Recraft's design sensibility while optimizing for throughput and cost.","endpoint_id":"fal-ai/recraft/v4.1/utility/text-to-image","family":"Recraft V4.1","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-05-14T15:54:59.641000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a296d/nH1d2nlbsZgmf5gJmzZCJ_1c6fe52b5f824c6da37312356320e8a0.jpg","title":"Recraft V4.1 Text to Image Utility"},{"category":"text-to-image","description":"Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy — delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.","endpoint_id":"fal-ai/recraft/v4/pro/text-to-image","family":"Recraft V4","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-02-12T18:30:16.402000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e35b5/OO8LkBQxwwkEj6SVlP3Bl_2ebfa787acba475b883a9f4ad9106032.jpg","title":"Recraft V4 Pro"},{"category":"text-to-image","description":"Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy — delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.","endpoint_id":"fal-ai/recraft/v4/pro/text-to-vector","family":"Recraft V4","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-02-16T21:47:29+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8ec1a0/taZtlNip1KSgwXbU8WQh6_f13cb8f783e24b41a3abc6f36e74f6dc.jpg","title":"Recraft V4 Pro (Vector)"},{"category":"text-to-image","description":"Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.","endpoint_id":"fal-ai/recraft/v4/text-to-image","family":"Recraft V4","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-02-12T18:15:47.502000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e35aa/1iRIhjhfqR0Goyr86qnR-_4bca0e5d677e478e8f5734c1b2cb355a.jpg","title":"Recraft V4"},{"category":"text-to-image","description":"Recraft V4 was developed with designers to bring true visual taste to AI image generation. Built for brand systems and production-ready workflows, it goes beyond prompt accuracy — delivering stronger composition, refined lighting, realistic materials, and a cohesive aesthetic. The result is imagery shaped by professional design judgment, ready for immediate real-world use without additional post-processing.","endpoint_id":"fal-ai/recraft/v4/text-to-vector","family":"Recraft V4","inputs":[{"default":null,"description":"Prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"An array of preferable colors","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"colors","required":false,"type":"json"},{"default":null,"description":"The preferable background color of the generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Recraft","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-02-16T21:45:43.314000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8ec194/M9W9hGsc8fz70XLiwXQ8X_bd67718d6bd146f0a4eff702c214ac9c.jpg","title":"Recraft V4 (Vector)"},{"category":"image-to-image","description":"Converts a given raster image to SVG format using Recraft model.","endpoint_id":"fal-ai/recraft/vectorize","family":"","inputs":[{"default":null,"description":"The URL of the image to be vectorized. Must be in PNG, JPG or WEBP format, less than 5 MB in size, have resolution less than 16 MP and max dimension less than 4096 pixels, min dimension more than 256 pixels.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Recraft","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-06-12T15:27:32.275000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/recraft-v3.webp","title":"Recraft"},{"category":"image-to-image","description":"Automatically retouches faces to smooth skin and remove blemishes.","endpoint_id":"fal-ai/retoucher","family":"","inputs":[{"default":null,"description":"The URL of the image to be retouched.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Seed for reproducibility. Different seeds will make slightly different results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2024-02-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/retoucher/Screenshot%20from%202024-02-13%2011-40-09.png","title":"Face Retoucher"},{"category":"image-to-image","description":"Interpolate images with RIFE - Real-Time Intermediate Flow Estimation","endpoint_id":"fal-ai/rife","family":"","inputs":[{"default":null,"description":"The URL of the first image to use as the starting point for interpolation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the second image to use as the ending point for interpolation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"},{"default":"images","description":"The type of output to generate; either individual images or a video.","enum":["images","video"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_type","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the output images. Only applicable if output_type is 'images'.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":1,"description":"The number of frames to generate between the input images.","enum":null,"is_list":false,"max":64,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"Whether to include the start image in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_start","required":false,"type":"boolean"},{"default":false,"description":"Whether to include the end image in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_end","required":false,"type":"boolean"},{"default":8,"description":"Frames per second for the output video. Only applicable if output_type is 'video'.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["video","images"],"pricing":"Your request will cost $0.0013 per compute second.","published_at":"2025-07-22T20:22:14.996000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939b/mCpBhJW1DeNwsCrhai2mh_0pbBNnrP.png","title":"RIFE"},{"category":"video-to-video","description":"Interpolate videos with RIFE - Real-Time Intermediate Flow Estimation","endpoint_id":"fal-ai/rife/video","family":"","inputs":[{"default":null,"description":"The URL of the video to use for interpolation.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":1,"description":"The number of frames to generate between the input video frames.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If True, the input video will be split into scenes before interpolation. This removes smear frames between scenes, but can result in false positives if the scene detection is not accurate. If False, the entire video will be treated as a single scene.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_scene_detection","required":false,"type":"boolean"},{"default":true,"description":"If True, the function will use the calculated FPS of the input video multiplied by the number of frames to determine the output FPS. If False, the passed FPS will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_calculated_fps","required":false,"type":"boolean"},{"default":8,"description":"Frames per second for the output video. Only applicable if use_calculated_fps is False.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"fps","required":false,"type":"integer"},{"default":false,"description":"If True, the final frame will be looped back to the first frame to create a seamless loop. If False, the final frame will not loop back.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.0013 per compute second.","published_at":"2025-07-22T20:23:08.948000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"RIFE"},{"category":"vision","description":"Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels","endpoint_id":"fal-ai/sa2va/4b/image","family":"","inputs":[{"default":null,"description":"Prompt to be used for the chat completion","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Url for the Input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"json","output_props":["masks","output"],"pricing":"","published_at":"2025-01-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sa2va.webp","title":"Sa2VA 4B Image"},{"category":"vision","description":"Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels","endpoint_id":"fal-ai/sa2va/4b/video","family":"","inputs":[{"default":null,"description":"Prompt to be used for the chat completion","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Number of frames to sample from the video. Defaults to 32 if not provided. Minimum 5, maximum 100.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":5,"multiline":false,"name":"num_frames_to_sample","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["masks","output"],"pricing":"","published_at":"2025-01-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sa2va.webp","title":"Sa2VA 4B Video"},{"category":"vision","description":"Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels","endpoint_id":"fal-ai/sa2va/8b/image","family":"","inputs":[{"default":null,"description":"Prompt to be used for the chat completion","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Url for the Input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"json","output_props":["masks","output"],"pricing":"","published_at":"2025-01-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sa2va.webp","title":"Sa2VA 8B Image"},{"category":"vision","description":"Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels","endpoint_id":"fal-ai/sa2va/8b/video","family":"","inputs":[{"default":null,"description":"Prompt to be used for the chat completion","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Number of frames to sample from the video. Defaults to 32 if not provided. Minimum 5, maximum 100.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":5,"multiline":false,"name":"num_frames_to_sample","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["masks","output"],"pricing":"","published_at":"2025-01-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sa2va.webp","title":"Sa2VA 8B Video"},{"category":"image-to-video","description":"Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","endpoint_id":"fal-ai/sadtalker","family":"","inputs":[{"default":null,"description":"URL of the source image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"source_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the driven audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"driven_audio_url","required":true,"type":"string"},{"default":0,"description":"The style of the pose","enum":null,"is_list":false,"max":45,"media_kind":null,"min":0,"multiline":false,"name":"pose_style","required":false,"type":"integer"},{"default":"256","description":"The resolution of the face model","enum":["256","512"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_model_resolution","required":false,"type":"enum"},{"default":1,"description":"The scale of the expression","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"expression_scale","required":false,"type":"number"},{"default":null,"description":"The type of face enhancer to use","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_enhancer","required":false,"type":"string"},{"default":false,"description":"Whether to use still mode. Fewer head motion, works with preprocess `full`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"still_mode","required":false,"type":"boolean"},{"default":"crop","description":"The type of preprocessing to use","enum":["crop","extcrop","resize","full","extfull"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-04-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sadtalker.jpeg","title":"Sad Talker"},{"category":"image-to-video","description":"Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","endpoint_id":"fal-ai/sadtalker/reference","family":"","inputs":[{"default":null,"description":"URL of the source image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"source_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the driven audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"driven_audio_url","required":true,"type":"string"},{"default":null,"description":"URL of the reference video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"reference_pose_video_url","required":true,"type":"string"},{"default":0,"description":"The style of the pose","enum":null,"is_list":false,"max":45,"media_kind":null,"min":0,"multiline":false,"name":"pose_style","required":false,"type":"integer"},{"default":"256","description":"The resolution of the face model","enum":["256","512"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_model_resolution","required":false,"type":"enum"},{"default":1,"description":"The scale of the expression","enum":null,"is_list":false,"max":3,"media_kind":null,"min":0,"multiline":false,"name":"expression_scale","required":false,"type":"number"},{"default":null,"description":"The type of face enhancer to use","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_enhancer","required":false,"type":"string"},{"default":false,"description":"Whether to use still mode. Fewer head motion, works with preprocess `full`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"still_mode","required":false,"type":"boolean"},{"default":"crop","description":"The type of preprocessing to use","enum":["crop","extcrop","resize","full","extfull"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"enum"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-12-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sadtalker.jpeg","title":"Sad Talker"},{"category":"image-to-image","description":"SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.","endpoint_id":"fal-ai/sam-3-1/image","family":"","inputs":[{"default":null,"description":"URL of the image to be segmented","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"wheel","description":"Text prompt for segmentation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":true,"description":"Apply the mask on the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"If True, upload and return multiple generated masks as defined by `max_masks`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_multiple_masks","required":false,"type":"boolean"},{"default":3,"description":"Maximum number of masks to return when `return_multiple_masks` is enabled.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"max_masks","required":false,"type":"integer"},{"default":false,"description":"Whether to include mask confidence scores.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_scores","required":false,"type":"boolean"},{"default":false,"description":"Whether to include bounding boxes for each mask (when available).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_boxes","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["masks","boxes","image","metadata","scores"],"pricing":"Your request will cost $0.01 per request.","published_at":"2026-03-30T16:22:58.421000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a944385/lr68yq78ZUUsBb6jo1wyv_34caef38c38747f9a97fb1f4f9b1d1c0.jpg","title":"Sam 3 1"},{"category":"image-to-image","description":"SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.","endpoint_id":"fal-ai/sam-3-1/image-rle","family":"","inputs":[{"default":null,"description":"URL of the image to be segmented","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"wheel","description":"Text prompt for segmentation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":true,"description":"Apply the mask on the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"If True, upload and return multiple generated masks as defined by `max_masks`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_multiple_masks","required":false,"type":"boolean"},{"default":3,"description":"Maximum number of masks to return when `return_multiple_masks` is enabled.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"max_masks","required":false,"type":"integer"},{"default":false,"description":"Whether to include mask confidence scores.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_scores","required":false,"type":"boolean"},{"default":false,"description":"Whether to include bounding boxes for each mask (when available).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_boxes","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["boxes","rle","boundingbox_frames_zip","scores","metadata"],"pricing":"Your request will cost $0.01 per request.","published_at":"2026-03-30T16:26:48.794000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a944396/rMQ6SmDh7Hv8-e-uFyGGC_b000684027e14c19ab846e24db060823.jpg","title":"Sam 3 1"},{"category":"video-to-video","description":"SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.","endpoint_id":"fal-ai/sam-3-1/video","family":"","inputs":[{"default":null,"description":"The URL of the video to be segmented.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"List of box prompt coordinates (x_min, y_min, x_max, y_max).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":true,"description":"Apply the mask on the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":0.5,"description":"Detection confidence threshold (0.0-1.0). Lower = more detections but less precise.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"detection_threshold","required":false,"type":"number"},{"default":16,"description":"Maximum number of objects to track in the video.","enum":null,"is_list":false,"max":128,"media_kind":null,"min":1,"multiline":false,"name":"max_num_objects","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["boundingbox_frames_zip","video"],"pricing":"Your request will cost $0.01 per 16 frames of video input.","published_at":"2026-03-30T16:39:11.488000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9443e9/RmwjI0HoW665F-GtnNKl5_81f96370160b47b6afd291fb7c80f8bb.jpg","title":"Sam 3 1"},{"category":"video-to-video","description":"SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.","endpoint_id":"fal-ai/sam-3-1/video-rle","family":"","inputs":[{"default":null,"description":"The URL of the video to be segmented.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask to be applied initially.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":"","description":"Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts with frame indices.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"List of box prompts with optional frame_index.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":false,"description":"Apply the mask on the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":false,"description":"Return per-frame bounding box overlays as a zip archive.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"boundingbox_zip","required":false,"type":"boolean"},{"default":0.5,"description":"Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Defaults: 0.5 for existing, 0.7 for new objects. Try 0.2-0.3 if text prompts fail.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"detection_threshold","required":false,"type":"number"},{"default":0,"description":"Frame index used for initial interaction when mask_url is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"frame_index","required":false,"type":"integer"},{"default":16,"description":"Maximum number of objects to track in the video.","enum":null,"is_list":false,"max":128,"media_kind":null,"min":1,"multiline":false,"name":"max_num_objects","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["boundingbox_frames_zip","video"],"pricing":"Your request will cost $0.01 per 16 frames of video input.","published_at":"2026-03-30T16:44:14.182000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9443fd/-KUrT4NrhzwdSIGt_0W2u_5284543c5010453a92d55013584c1334.jpg","title":"Sam 3 1"},{"category":"3d-to-3d","description":"SAM 3D enables full scene reconstructions, placing objects and humans in a shared context together.","endpoint_id":"fal-ai/sam-3/3d-align","family":"","inputs":[{"default":null,"description":"URL of the original image used for MoGe depth estimation","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the SAM-3D Body mesh file (.ply or .glb) to align","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"body_mesh_url","required":true,"type":"string"},{"default":null,"description":"URL of the human mask image. If not provided, uses full image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"body_mask_url","required":false,"type":"string"},{"default":null,"description":"Optional URL of SAM-3D Object mesh (.glb) to create combined scene","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"object_mesh_url","required":false,"type":"string"},{"default":null,"description":"Focal length from SAM-3D Body metadata. If not provided, estimated from MoGe.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"focal_length","required":false,"type":"number"}],"lab":"","output_kind":"file","output_props":["body_mesh_ply","model_glb","scene_glb","visualization","metadata"],"pricing":"Your request will cost $0.02 per unit.","published_at":"2025-12-02T20:56:43.845000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84bb71/k2b6czMQphI5lV6zjLj8z_ea2a892775d745b08a01ba6ecfa6ca43.jpg","title":"Sam 3"},{"category":"image-to-3d","description":"SAM 3D allows for accurate 3D reconstruction of human body shape and position from a single image.","endpoint_id":"fal-ai/sam-3/3d-body","family":"","inputs":[{"default":null,"description":"URL of the image containing humans","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of a binary mask image (white=person, black=background). When provided, skips auto human detection and uses this mask instead. Bbox is auto-computed from the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_url","required":false,"type":"string"},{"default":true,"description":"Export individual mesh files (.ply) per person","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"export_meshes","required":false,"type":"boolean"},{"default":true,"description":"Include 3D keypoint markers (spheres) in the GLB mesh for visualization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_3d_keypoints","required":false,"type":"boolean"},{"default":true,"description":"Include the full MHR (Meta Human Representation) parameter set per person in the response metadata (shape, pose, expression, global rotations, joint coordinates, packed model params, raw pose). Set to `false` to return a leaner metadata block with only keypoints and camera parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_mhr_params","required":false,"type":"boolean"}],"lab":"","output_kind":"file","output_props":["model_glb","meshes","visualization","metadata"],"pricing":"Your request will cost $0.02 per unit.","published_at":"2025-12-02T20:52:11.002000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a859c26/IT2mAlL6O7dkCEwVk9ba8_875e9beae3b646b0b38e83def3ff9a79.jpg","title":"Sam 3"},{"category":"image-to-3d","description":"SAM 3D enables precise 3D reconstruction of objects from real images, while accurately reconstructing their geometry and texture.","endpoint_id":"fal-ai/sam-3/3d-objects","family":"","inputs":[{"default":null,"description":"URL of the image to reconstruct in 3D","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional list of mask URLs (one per object). If not provided, use prompt/point_prompts/box_prompts to auto-segment, or entire image will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_urls","required":false,"type":"string"},{"default":"car","description":"Text prompt for auto-segmentation when no masks provided (e.g., 'chair', 'lamp')","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"[]","description":"Point prompts for auto-segmentation when no masks provided","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"Box prompts for auto-segmentation when no masks provided. Multiple boxes supported - each produces a separate object mask for 3D reconstruction.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Optional URL to external pointmap/depth data (NPY or NPZ format) for improved 3D reconstruction depth estimation","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"pointmap_url","required":false,"type":"string"},{"default":null,"description":"Detection confidence threshold (0.1-1.0). Lower = more detections but less precise. If not set, uses the model's default.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"detection_threshold","required":false,"type":"number"},{"default":false,"description":"If True, exports GLB with baked texture and UVs instead of vertex colors.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"export_textured_glb","required":false,"type":"boolean"}],"lab":"","output_kind":"file","output_props":["gaussian_splat","model_glb","individual_glbs","artifacts_zip","individual_splats","metadata"],"pricing":"Your request will cost $0.02 per unit.","published_at":"2025-12-02T20:49:49.159000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84bb3e/wqkR8Gs7K2y82b7XDaNLt_4c480ee51bf94761b8f769d5b27a1921.jpg","title":"Sam 3"},{"category":"image-to-image","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.","endpoint_id":"fal-ai/sam-3/image","family":"","inputs":[{"default":null,"description":"URL of the image to be segmented","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"wheel","description":"Text prompt for segmentation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":true,"description":"Apply the mask on the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"If True, upload and return multiple generated masks as defined by `max_masks`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_multiple_masks","required":false,"type":"boolean"},{"default":3,"description":"Maximum number of masks to return when `return_multiple_masks` is enabled.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"max_masks","required":false,"type":"integer"},{"default":false,"description":"Whether to include mask confidence scores.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_scores","required":false,"type":"boolean"},{"default":false,"description":"Whether to include bounding boxes for each mask (when available).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_boxes","required":false,"type":"boolean"}],"lab":"","output_kind":"image","output_props":["boxes","scores","masks","image","metadata"],"pricing":"Your request will cost $0.005 per request.","published_at":"2025-11-20T19:45:11.630000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/kJhu6OfXaBwWYM1PUrWAL_6519f8ea79d649a9bead2e6118f4b997.jpg","title":"Segment Anything Model 3"},{"category":"image-to-image","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.","endpoint_id":"fal-ai/sam-3/image-rle","family":"","inputs":[{"default":null,"description":"URL of the image to be segmented","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"wheel","description":"Text prompt for segmentation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":true,"description":"Apply the mask on the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"If True, upload and return multiple generated masks as defined by `max_masks`.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_multiple_masks","required":false,"type":"boolean"},{"default":3,"description":"Maximum number of masks to return when `return_multiple_masks` is enabled.","enum":null,"is_list":false,"max":32,"media_kind":null,"min":1,"multiline":false,"name":"max_masks","required":false,"type":"integer"},{"default":false,"description":"Whether to include mask confidence scores.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_scores","required":false,"type":"boolean"},{"default":false,"description":"Whether to include bounding boxes for each mask (when available).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_boxes","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["boxes","scores","rle","boundingbox_frames_zip","metadata"],"pricing":"","published_at":"2025-11-20T20:28:17.206000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/ZrvWvXbFBabIS0XEJqJ3m_03f5ca0dc15241719ca5ee131da584a2.jpg","title":"Sam 3"},{"category":"vision","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.","endpoint_id":"fal-ai/sam-3/image/embed","family":"","inputs":[{"default":null,"description":"URL of the image to embed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"","output_kind":"text","output_props":["embedding_b64"],"pricing":"Your request will cost $0.005 per request.","published_at":"2025-11-20T20:21:00.592000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/nV3tuTldL1rK_c-slZGQ7_a5ad14e94b304162be3202f54a1671f7.jpg","title":"Sam 3"},{"category":"video-to-video","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.","endpoint_id":"fal-ai/sam-3/video","family":"","inputs":[{"default":null,"description":"The URL of the video to be segmented.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"List of box prompt coordinates (x_min, y_min, x_max, y_max).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":true,"description":"Apply the mask on the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"X264 (.mp4)","description":"The output type of the generated video.","enum":["X264 (.mp4)","VP9 (.webm)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_output_type","required":false,"type":"enum"},{"default":0.5,"description":"Detection confidence threshold (0.0-1.0). Lower = more detections but less precise.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.1,"multiline":false,"name":"detection_threshold","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video","boundingbox_frames_zip"],"pricing":"Your request will cost $0.005 per 16 frames of video input.","published_at":"2025-11-20T20:08:20.592000+00:00","thumbnail":"https://v3b.fal.media/files/b/panda/sg8Fv6dzqdXAAgbAvxTta_814b4d079f5942d1b6cfb0f90ece9f36.jpg","title":"Sam 3"},{"category":"video-to-video","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.","endpoint_id":"fal-ai/sam-3/video-rle","family":"","inputs":[{"default":null,"description":"The URL of the video to be segmented.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask to be applied initially.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":"","description":"Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"[]","description":"List of point prompts with frame indices.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"point_prompts","required":false,"type":"json"},{"default":"[]","description":"List of box prompts with optional frame_index.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":false,"description":"Apply the mask on the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":false,"description":"Return per-frame bounding box overlays as a zip archive.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"boundingbox_zip","required":false,"type":"boolean"},{"default":0.5,"description":"Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Defaults: 0.5 for existing, 0.7 for new objects. Try 0.2-0.3 if text prompts fail.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"detection_threshold","required":false,"type":"number"},{"default":0,"description":"Frame index used for initial interaction when mask_url is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"frame_index","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video","boundingbox_frames_zip"],"pricing":"Your request will cost $0.005 per 16 frames of video.","published_at":"2025-11-20T20:18:27.813000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/OOePxI1jvWaABuigKMkrl_c5195735531a4c9887a415bfc7cf0b74.jpg","title":"Sam 3"},{"category":"audio-to-audio","description":"Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.","endpoint_id":"fal-ai/sam-audio/separate","family":"","inputs":[{"default":null,"description":"URL of the audio file to process (WAV, MP3, FLAC supported)","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Text prompt describing the sound to isolate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Automatically predict temporal spans where the target sound occurs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"predict_spans","required":false,"type":"boolean"},{"default":1,"description":"Number of candidates to generate and rank. Higher improves quality but increases latency and cost.","enum":null,"is_list":false,"max":7,"media_kind":null,"min":1,"multiline":false,"name":"reranking_candidates","required":false,"type":"integer"},{"default":"balanced","description":"The acceleration level to use.","enum":["fast","balanced","quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":60,"description":"Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":10,"multiline":false,"name":"max_chunk_duration","required":false,"type":"number"},{"default":5,"description":"Overlap duration (in seconds) between chunks for crossfade blending.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"chunk_overlap","required":false,"type":"number"},{"default":"wav","description":"Output audio format.","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"json","output_props":["residual","target","sample_rate","duration"],"pricing":"You request will be billed $0.05 per 30s of output audio. Note: You'll be charged $0.025 per 30s per additional reranking candidate.","published_at":"2025-12-30T16:38:04.429000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a88664f/wKE1EUP15yGhKAFhCA_7C_f889f14440d64e70b1c0b08403dfb3bf.jpg","title":"Sam Audio"},{"category":"audio-to-audio","description":"Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.","endpoint_id":"fal-ai/sam-audio/span-separate","family":"","inputs":[{"default":null,"description":"URL of the audio file to process.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Text prompt describing the sound to isolate. Optional but recommended - helps the model identify what type of sound to extract from the span.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Time spans where the target sound occurs which should be isolated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"spans","required":true,"type":"json"},{"default":1,"description":"Number of candidates to generate and rank. Higher improves quality but increases latency and cost. Requires text prompt; ignored for span-only separation.","enum":null,"is_list":false,"max":7,"media_kind":null,"min":1,"multiline":false,"name":"reranking_candidates","required":false,"type":"integer"},{"default":"balanced","description":"The acceleration level to use.","enum":["fast","balanced","quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":60,"description":"Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":10,"multiline":false,"name":"max_chunk_duration","required":false,"type":"number"},{"default":5,"description":"Overlap duration (in seconds) between chunks for crossfade blending.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"chunk_overlap","required":false,"type":"number"},{"default":false,"description":"Use sound activity detection to rank reranking candidates based on how well each candidate's non-silent regions match the provided spans. Enables effective reranking even without a text prompt (span-only separation). Requires reranking_candidates > 1.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_sound_activity_ranking","required":false,"type":"boolean"},{"default":false,"description":"Trim output audio to only include the specified span time range. If False, returns the full audio length with the target sound isolated throughout.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trim_to_span","required":false,"type":"boolean"},{"default":"wav","description":"Output audio format.","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"json","output_props":["residual","target","sample_rate","duration"],"pricing":"You request will be billed $0.05 per 30s of output audio. Note: You'll be charged $0.025 per 30s per additional reranking candidate.","published_at":"2025-12-30T16:24:56.311000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8865ea/mJyuh2TOMRndveMfF6BQY_863a43ac54ea4d3db11f18a6856a8cf6.jpg","title":"Sam Audio"},{"category":"video-to-audio","description":"Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.","endpoint_id":"fal-ai/sam-audio/visual-separate","family":"","inputs":[{"default":null,"description":"URL of the video file to process (MP4, MOV, etc.)","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the mask video (binary mask indicating target object). Black=target, White=background.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":false,"type":"string"},{"default":"","description":"Text prompt to assist with separation. Use natural language to describe the target sound.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"Number of candidates to generate and rank. Higher improves quality but increases latency and cost.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"reranking_candidates","required":false,"type":"integer"},{"default":"balanced","description":"The acceleration level to use.","enum":["fast","balanced","quality"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":60,"description":"Maximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":10,"multiline":false,"name":"max_chunk_duration","required":false,"type":"number"},{"default":5,"description":"Overlap duration (in seconds) between chunks for crossfade blending.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0,"multiline":false,"name":"chunk_overlap","required":false,"type":"number"},{"default":"wav","description":"Output audio format.","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"json","output_props":["residual","target","sample_rate","duration"],"pricing":"You request will be billed $0.05 per 30s of output audio. Note: You'll be charged $0.025 per 30s per additional reranking candidate.","published_at":"2025-12-30T16:16:20.141000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8865ba/oZ7GwnFaLuxD6NEEWYkcM_84e3d234884b41bea323b1bcb5a168e9.jpg","title":"Sam Audio"},{"category":"image-to-image","description":"SAM 2 is a model for segmenting images automatically. It can return individual masks or a single mask for the entire image.","endpoint_id":"fal-ai/sam2/auto-segment","family":"","inputs":[{"default":null,"description":"URL of the image to be automatically segmented","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":32,"description":"Number of points to sample along each side of the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"points_per_side","required":false,"type":"integer"},{"default":0.88,"description":"Threshold for predicted IOU score.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pred_iou_thresh","required":false,"type":"number"},{"default":0.95,"description":"Threshold for stability score.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"stability_score_thresh","required":false,"type":"number"},{"default":100,"description":"Minimum area of a mask region.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"min_mask_region_area","required":false,"type":"integer"}],"lab":"","output_kind":"json","output_props":["individual_masks","combined_mask"],"pricing":"","published_at":"2025-02-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sam2.gif","title":"Segment Anything Model 2"},{"category":"image-to-image","description":"SAM 2 is a model for segmenting images and videos in real-time.","endpoint_id":"fal-ai/sam2/image","family":"","inputs":[{"default":null,"description":"URL of the image to be segmented","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"[]","description":"List of prompts to segment the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompts","required":false,"type":"json"},{"default":"[]","description":"Coordinates for boxes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":false,"description":"Apply the mask on the image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2024-08-15T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sam2.gif","title":"Segment Anything Model 2"},{"category":"video-to-video","description":"SAM 2 is a model for segmenting images and videos in real-time.","endpoint_id":"fal-ai/sam2/video","family":"","inputs":[{"default":null,"description":"The URL of the video to be segmented.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The URL of the mask to be applied initially.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"},{"default":"[]","description":"List of prompts to segment the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompts","required":false,"type":"json"},{"default":"[]","description":"Coordinates for boxes","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"box_prompts","required":false,"type":"json"},{"default":false,"description":"Apply the mask on the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"apply_mask","required":false,"type":"boolean"},{"default":false,"description":"Return per-frame bounding box overlays as a zip archive.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"boundingbox_zip","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","boundingbox_frames_zip"],"pricing":"","published_at":"2024-08-15T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sam2.gif","title":"Segment Anything Model 2"},{"category":"text-to-image","description":"Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, with the ability to generate 4K images in less than a second.","endpoint_id":"fal-ai/sana","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":2160,"width":3840},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":18,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"(No style)","description":"The style to generate the image in.","enum":["(No style)","Cinematic","Photographic","Anime","Manga","Digital Art","Pixel art","Fantasy art","Neonpunk","3D Model"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_name","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","seed","prompt"],"pricing":"","published_at":"2024-08-01T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sana.webp","title":"Sana"},{"category":"text-to-image","description":"Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.","endpoint_id":"fal-ai/sana/sprint","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":2160,"width":3840},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":2,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"(No style)","description":"The style to generate the image in.","enum":["(No style)","Cinematic","Photographic","Anime","Manga","Digital Art","Pixel art","Fantasy art","Neonpunk","3D Model"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_name","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","seed","prompt"],"pricing":"","published_at":"2025-03-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-6.jpeg","title":"Sana Sprint"},{"category":"text-to-image","description":"Sana v1.5 1.6B is a lightweight text-to-image model that delivers 4K image generation with impressive efficiency.","endpoint_id":"fal-ai/sana/v1.5/1.6b","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":2160,"width":3840},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":18,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"(No style)","description":"The style to generate the image in.","enum":["(No style)","Cinematic","Photographic","Anime","Manga","Digital Art","Pixel art","Fantasy art","Neonpunk","3D Model"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_name","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","seed","prompt"],"pricing":"","published_at":"2025-03-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sana.webp","title":"Sana v1.5 1.6B"},{"category":"text-to-image","description":"Sana v1.5 4.8B is a powerful text-to-image model that generates ultra-high quality 4K images with remarkable detail.","endpoint_id":"fal-ai/sana/v1.5/4.8b","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":{"height":2160,"width":3840},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":18,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"(No style)","description":"The style to generate the image in.","enum":["(No style)","Cinematic","Photographic","Anime","Manga","Digital Art","Pixel art","Fantasy art","Neonpunk","3D Model"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style_name","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","seed","prompt"],"pricing":"","published_at":"2025-03-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sana.webp","title":"Sana v1.5 4.8B"},{"category":"video-to-video","description":"SCAIL-2 is an end-to-end character animation model that drives a reference character from a source video without relying on intermediate pose representations like skeleton maps.","endpoint_id":"fal-ai/scail-2","family":"Scail 2","inputs":[{"default":null,"description":"The prompt describing the final video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the reference character image. The character in this image is animated (or used to replace a subject) according to the driving video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the driving (motion) video. The subject can be a human, multiple humans, or an animal.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"animation","description":"`animation` animates the reference character with the driving motion. `replacement` replaces the driving subject with the reference character while keeping the original scene.","enum":["animation","replacement"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":"end_to_end","description":"Driving signal for animation mode. `end_to_end` (default) drives directly from the SAM3-masked driving video and is the recommended, most robust path. `pose` renders an explicit NLF/DWPose skeleton from the driving video (more control for challenging inputs).","enum":["end_to_end","pose"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"driving_type","required":false,"type":"enum"},{"default":"human","description":"Type of subject in the driving video. `animal` switches the SAM3 detection prompt to non-human subjects.","enum":["human","animal"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subject_type","required":false,"type":"enum"},{"default":"512p","description":"Output resolution. 512p outputs 896x512 (landscape) or 512x896 (portrait); 704p outputs 1280x704 or 704x1280. Orientation is chosen automatically from the reference image aspect ratio.","enum":["512p","704p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":40,"description":"Number of diffusion sampling steps. Higher improves quality but is slower.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. Controls prompt adherence versus creativity.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Flow-matching noise schedule shift. 3.0 is recommended for the 512p tier.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"Random seed. Leave empty for a random seed. The seed used is returned in the response.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"z AI","output_kind":"video","output_props":["video","preprocessing_mask_video","preprocessing_video","seed"],"pricing":"SCAIL-2 is billed per second of generated video at a flat rate of $0.20 per second, the same for both output resolutions (512p and 704p).\n\nGenerated video is always produced at 16 fps, so billed seconds = total output frames ÷ 16 — which is simply the duration of the output video in seconds.\n\nHow your cost is calculated:\n\n1. Billed seconds = output duration (total frames ÷ 16 fps)\n2. Cost = billed seconds × $0.20\n\nExample — 5-second output: 5 × $0.20 = $1.00\n\nEach request is capped at 10 seconds of video (160 frames at 16 fps), so the maximum cost per request is $2.00.","published_at":"2026-06-18T13:24:42.161000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ec767/Gq27vVNNB_xMK8pspiYS1_b88edf4ba92e4f0ea3780b28387e71a2.jpg","title":"Scail 2"},{"category":"vision","description":"Search any video with a text prompt - Scene Finder locates the matching moments and returns their time segments and extracted frames.","endpoint_id":"fal-ai/scene-finder","family":"","inputs":[{"default":null,"description":"URL of the video to search through.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Text description of the event or scene to find in the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":2,"description":"Frames per second to sample from the video. Higher values give more precision but use more memory.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"mid","description":"Which frame(s) to extract from each detected segment. 'mid' returns the midpoint frame, 'start' the first frame, 'end' the last frame, 'all' returns start + mid + end.","enum":["mid","start","end","all"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"frame_selection","required":false,"type":"enum"}],"lab":"Fal","output_kind":"images","output_props":["segments","images"],"pricing":"Scene Finder is billed by the length of the input video — $0.0042 per second of input video.","published_at":"2026-06-03T22:42:22.042000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9cde0e/TlRSiNFPg-ph2M1bYsQyb_880fdf7b85354180a536889eb4320c5d.jpg","title":"Scene Finder"},{"category":"text-to-image","description":"An efficent SDXL multi-controlnet text-to-image model.","endpoint_id":"fal-ai/sdxl-controlnet-union","family":"","inputs":[{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to preprocess the segmentation image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segmentation_preprocess","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":true,"description":"Whether to preprocess the normal image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normal_preprocess","required":false,"type":"boolean"},{"default":true,"description":"Whether to preprocess the canny image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"canny_preprocess","required":false,"type":"boolean"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the control image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"canny_image_url","required":false,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Whether to preprocess the openpose image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"openpose_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"openpose_image_url","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"depth_image_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":0.5,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"normal_image_url","required":false,"type":"string"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"segmentation_image_url","required":false,"type":"string"},{"default":true,"description":"Whether to preprocess the teed image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"teed_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"teed_image_url","required":false,"type":"string"},{"default":true,"description":"Whether to preprocess the depth image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"depth_preprocess","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2024-07-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/controlnet-union/000004_openpose_scribble_concat.jpg","title":"SDXL ControlNet Union"},{"category":"image-to-image","description":"An efficent SDXL multi-controlnet image-to-image model.","endpoint_id":"fal-ai/sdxl-controlnet-union/image-to-image","family":"","inputs":[{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to preprocess the segmentation image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segmentation_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the control image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Whether to preprocess the canny image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"canny_preprocess","required":false,"type":"boolean"},{"default":true,"description":"Whether to preprocess the openpose image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"openpose_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"openpose_image_url","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"depth_image_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.05,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the depth image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"depth_preprocess","required":false,"type":"boolean"},{"default":false,"description":"If set to true, the aspect ratio of the generated image will be preserved even\n        if the image size is too large. However, if the image is not a multiple of 32\n        in width or height, it will be resized to the nearest multiple of 32. By default,\n        this snapping to the nearest multiple of 32 will not preserve the aspect ratio.\n        Set crop_output to True, to crop the output to the proper aspect ratio\n        after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preserve_aspect_ratio","required":false,"type":"boolean"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":true,"description":"Whether to preprocess the normal image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normal_preprocess","required":false,"type":"boolean"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"canny_image_url","required":false,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"normal_image_url","required":false,"type":"string"},{"default":0.5,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"segmentation_image_url","required":false,"type":"string"},{"default":true,"description":"Whether to preprocess the teed image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"teed_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"teed_image_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the output cropped to the proper aspect ratio after generating.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_output","required":false,"type":"boolean"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2024-07-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/controlnet-union/000004_openpose_scribble_concat.jpg","title":"SDXL ControlNet Union"},{"category":"image-to-image","description":"An efficent SDXL multi-controlnet inpainting model.","endpoint_id":"fal-ai/sdxl-controlnet-union/inpainting","family":"","inputs":[{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to preprocess the segmentation image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segmentation_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the mask to use for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"},{"default":null,"description":"The size of the generated image. Leave it none to automatically infer from the control image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Whether to preprocess the canny image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"canny_preprocess","required":false,"type":"boolean"},{"default":true,"description":"Whether to preprocess the openpose image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"openpose_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"openpose_image_url","required":false,"type":"string"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"","description":"The negative prompt to use.Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"depth_image_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":0.95,"description":"determines how much the generated image resembles the initial image","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":true,"description":"Whether to preprocess the depth image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"depth_preprocess","required":false,"type":"boolean"},{"default":35,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":70,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":true,"description":"Whether to preprocess the normal image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"normal_preprocess","required":false,"type":"boolean"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"canny_image_url","required":false,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":0.5,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"controlnet_conditioning_scale","required":false,"type":"number"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"normal_image_url","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"segmentation_image_url","required":false,"type":"string"},{"default":true,"description":"Whether to preprocess the teed image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"teed_preprocess","required":false,"type":"boolean"},{"default":null,"description":"The URL of the control image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"teed_image_url","required":false,"type":"string"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2024-07-31T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/controlnet-union/000004_openpose_scribble_concat.jpg","title":"SDXL ControlNet Union"},{"category":"image-to-image","description":"Use SeedVR2 to upscale your images","endpoint_id":"fal-ai/seedvr/upscale/image","family":"Upscale","inputs":[{"default":null,"description":"The input image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"factor","description":"The mode to use for the upscale. If 'target', the upscale factor will be calculated based on the target resolution. If 'factor', the upscale factor will be used directly.","enum":["target","factor"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_mode","required":false,"type":"enum"},{"default":2,"description":"Upscaling factor to be used. Will multiply the dimensions with this factor when `upscale_mode` is `factor`.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":"1080p","description":"The target resolution to upscale to when `upscale_mode` is `target`.","enum":["720p","1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_resolution","required":false,"type":"enum"},{"default":null,"description":"The random seed used for the generation process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":0.1,"description":"The noise scale to use for the generation process.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"noise_scale","required":false,"type":"number"},{"default":"jpg","description":"The format of the output image.","enum":["png","jpg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"SeedVR","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2025-09-22T18:19:28.476000+00:00","thumbnail":"https://v3.fal.media/files/panda/_-1rRy0_I6w-fbt3q0RDL_2f47fece6e2b433994dda482e8d20bb9.jpg","title":"SeedVR2"},{"category":"image-to-image","description":"Use SeedVR2 to upscale images, retaining seamless tiling","endpoint_id":"fal-ai/seedvr/upscale/image/seamless","family":"Upscale","inputs":[{"default":null,"description":"The input image to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"factor","description":"The mode to use for the upscale. If 'target', the upscale factor will be calculated based on the target resolution. If 'factor', the upscale factor will be used directly.","enum":["target","factor"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_mode","required":false,"type":"enum"},{"default":2,"description":"Upscaling factor to be used. Will multiply the dimensions with this factor when `upscale_mode` is `factor`.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":"1080p","description":"The target resolution to upscale to when `upscale_mode` is `target`.","enum":["720p","1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_resolution","required":false,"type":"enum"},{"default":null,"description":"The random seed used for the generation process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":0.1,"description":"The noise scale to use for the generation process.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"noise_scale","required":false,"type":"number"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the output image.","enum":["png","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"SeedVR","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2026-03-23T01:56:07.964000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9342f3/FTb2upNEElzwvTcDCKTM__aac81f90fdf84f5ca436e5e3c48022d3.jpg","title":"SeedVR2"},{"category":"video-to-video","description":"Upscale your videos using SeedVR2 with temporal consistency!","endpoint_id":"fal-ai/seedvr/upscale/video","family":"Upscale","inputs":[{"default":null,"description":"The input video to be processed","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"factor","description":"The mode to use for the upscale. If 'target', the upscale factor will be calculated based on the target resolution. If 'factor', the upscale factor will be used directly.","enum":["target","factor"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upscale_mode","required":false,"type":"enum"},{"default":2,"description":"Upscaling factor to be used. Will multiply the dimensions with this factor when `upscale_mode` is `factor`.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":"1080p","description":"The target resolution to upscale to when `upscale_mode` is `target`.","enum":["720p","1080p","1440p","2160p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_resolution","required":false,"type":"enum"},{"default":null,"description":"The random seed used for the generation process.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":0.1,"description":"The noise scale to use for the generation process.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"noise_scale","required":false,"type":"number"},{"default":"X264 (.mp4)","description":"The format of the output video.","enum":["X264 (.mp4)","VP9 (.webm)","PRORES4444 (.mov)","GIF (.gif)"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_write_mode","required":false,"type":"enum"}],"lab":"SeedVR","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.001 per megapixel of video data (width × height × frames).\nFor example, if your upscaled video is 1920×1080 with 121 frames, the total cost will be $0.25.","published_at":"2025-09-22T18:29:49.293000+00:00","thumbnail":"https://v3.fal.media/files/koala/cAs3xUC9Lx-jlQh-27-60_4dddbb5a9bac42da86ddf20a5b9d30b3.jpg","title":"SeedVR2"},{"category":"text-to-image","description":"Generate Infographic Image with Sensenova U1","endpoint_id":"fal-ai/sensenova-u1-infographic","family":"","inputs":[{"default":null,"description":"Text prompt describing the infographic to generate. Detailed prompts that specify layout, sections, color palette, typography, and the data being visualized work best.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio for the generated image. Maps to the trained resolution buckets — using ratios outside this set is not supported. Defaults to 16:9, which fits most poster / presentation-style infographics.","enum":["1:1","16:9","9:16","3:2","2:3","4:3","3:4","1:2","2:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":50,"description":"Number of flow-matching denoising steps.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3,"description":"Timestep shifting factor for the flow-matching sampler. Higher values bias sampling towards earlier timesteps.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"timestep_shift","required":false,"type":"number"},{"default":false,"description":"If True, run chain-of-thought before image generation. Improves complex-prompt fidelity but is slower and billed at 1.2x.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_thinking","required":false,"type":"boolean"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","thinking","timings","prompt","seed","has_nsfw_concepts"],"pricing":"Your request will cost $0.05 per generated image. Enabling thinking mode applies a 1.2x multiplier, so a request with thinking mode will cost $0.06 per image.","published_at":"2026-06-17T23:26:31.826000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9eb773/53GXcFTH_61CtXnwN6MiL_40c8a8a9477344e0bfc93d94eb91e445.jpg","title":"Sensenova U1 Infographic"},{"category":"audio-to-text","description":"Detect speech presence and timestamps with accuracy and speed using the ultra-lightweight Silero VAD model","endpoint_id":"fal-ai/silero-vad","family":"","inputs":[{"default":null,"description":"The URL of the audio to get speech timestamps from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"","output_kind":"json","output_props":["timestamps","has_speech"],"pricing":"","published_at":"2026-01-08T19:19:45.098000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8999ea/LpSxj3lpoR_1RIxsAw4Z0_bfe5fc31ca6442679cefa0d11a486833.jpg","title":"Silero VAD"},{"category":"image-to-image","description":"Smart image resize to arbitrary dimensions, powered by Nano Banana Pro with vision-LLM-guided prompting for composition-aware recomposition. Crop, cropping, resize ads.","endpoint_id":"fal-ai/smart-resize","family":"","inputs":[{"default":null,"description":"The URL of the source image to resize.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The list of target dimensions to generate, each written as ``<width>x<height>`` (e.g. ``\"1920x1080\"``). One output image is produced per target size (multiplied by ``num_images_per_size``). The endpoint internally picks the smallest nano-banana-pro preset that fully covers each target so the final image is a pixel-perfect match with no upscaling.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"target_sizes","required":true,"type":"string"},{"default":"","description":"Optional extra instruction that is forwarded to nano-banana-pro alongside the auto-generated resize prompt. Leave empty to let the model preserve the original image content as closely as possible.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":1,"description":"The number of nano-banana-pro variants to produce for each target size. The response images list will contain ``len(target_sizes) * num_images_per_size`` images in total.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images_per_size","required":false,"type":"integer"},{"default":"1K","description":"Hint for the minimum resolution tier to use internally. The smart-resize algorithm may pick a higher tier automatically when the requested target size is too large for this tier. This field does not affect the final output dimensions — those come from ``target_sizes``.","enum":["1K","2K","4K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"png","description":"The output image format.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level applied to the inner nano-banana-pro /edit calls. Higher numbers loosen safety filtering.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"Optional random seed forwarded to the inner nano-banana-pro /edit calls for reproducibility. The same seed is used for every target size when set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","results","description"],"pricing":"Your request will cost $0.15 per output image (charged double for 4K outputs), plus a $0.05 minimum vision analysis fee per request. For $1.00, you can run this model 5 times at standard resolution.","published_at":"2026-04-29T17:10:30.999000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a981669/r1zMeYYE4grqhs4oXwMQu_d180e59394ab4e29b84cf5adf648977f.jpg","title":"Smart Resize"},{"category":"speech-to-text","description":"An open source, community-driven and native audio turn detection model by Pipecat AI.","endpoint_id":"fal-ai/smart-turn","family":"","inputs":[{"default":null,"description":"The URL of the audio file to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"","output_kind":"json","output_props":["probability","metrics","prediction"],"pricing":"","published_at":"2025-04-21T23:54:12.905000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Pipecat's Smart Turn model"},{"category":"image-to-video","description":"Generate character ids to use with Sora 2 generations","endpoint_id":"fal-ai/sora-2/characters","family":"","inputs":[{"default":null,"description":"URL of an MP4 video (minimum 720p, max ~2.67:1 aspect ratio) to define the character. Videos exceeding 1080p are automatically scaled down. Non-standard aspect ratios are automatically padded to 16:9 (landscape) or 9:16 (portrait). Videos longer than 4 seconds are trimmed to the first 4 seconds.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Name for the character (1–80 characters). Refer to this name in prompts when using the character.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"name","required":true,"type":"string"}],"lab":"OpenAI","output_kind":"text","output_props":["id","name"],"pricing":"","published_at":"2026-03-12T23:42:46.575000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91ee57/xEfDqX8_tr5k0oO591ShR_5a1a6c98c58e47f2b909421387e44423.jpg","title":"Sora 2"},{"category":"image-to-video","description":"Image-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.","endpoint_id":"fal-ai/sora-2/image-to-video","family":"Sora 2","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The resolution of the generated video","enum":["auto","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video","enum":["auto","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":4,"description":"Duration of the generated video in seconds","enum":[4,8,12,16,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to delete the video after generation for privacy reasons. If True, the video cannot be used for remixing and will be permanently deleted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"delete_video","required":false,"type":"boolean"},{"default":"sora-2","description":"The model to use for the generation. When the default model is selected, the latest snapshot of the model will be used - otherwise, select a specific snapshot of the model.","enum":["sora-2","sora-2-2025-12-08","sora-2-2025-10-06"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":false,"description":"If enabled, the prompt (and image for image-to-video) will be checked for known intellectual property references and the request will be blocked if any are detected.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detect_and_block_ip","required":false,"type":"boolean"},{"default":null,"description":"Up to two character IDs (from create-character) to use in the video. Refer to characters by name in the prompt. When set, only the OpenAI provider is used.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"character_ids","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"OpenAI","output_kind":"video","output_props":["video_id","spritesheet","video","thumbnail"],"pricing":"The pricing is $0.1/s for Sora 2.","published_at":"2025-10-06T19:34:52.329000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/8n-yLTQvW5q0BEvW0H2J3_8233c7e127124290b6dfa965f44ebc79.jpg","title":"Sora 2"},{"category":"image-to-video","description":"Image-to-video endpoint for Sora 2 Pro, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.","endpoint_id":"fal-ai/sora-2/image-to-video/pro","family":"Sora 2","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The resolution of the generated video","enum":["auto","720p","1080p","true_1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The aspect ratio of the generated video","enum":["auto","9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":4,"description":"Duration of the generated video in seconds","enum":[4,8,12,16,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to delete the video after generation for privacy reasons. If True, the video cannot be used for remixing and will be permanently deleted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"delete_video","required":false,"type":"boolean"},{"default":false,"description":"If enabled, the prompt (and image for image-to-video) will be checked for known intellectual property references and the request will be blocked if any are detected.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detect_and_block_ip","required":false,"type":"boolean"},{"default":null,"description":"Up to two character IDs (from create-character) to use in the video. Refer to characters by name in the prompt. When set, only the OpenAI provider is used.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"character_ids","required":false,"type":"string"},{"default":null,"description":"The URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"OpenAI","output_kind":"video","output_props":["video_id","spritesheet","video","thumbnail"],"pricing":"The pricing is $0.30/s for 720p, $0.50/s for legacy 1080p (1792x1024 or 1024x1792) or $0.70/s for true 1080p (1920x1080 or 1080x1920).","published_at":"2025-10-06T22:02:41.752000+00:00","thumbnail":"https://v3.fal.media/files/koala/19D6ouLhOE6EKGbUTnfzf_b958de62e48c4356a1c58abef534060b.jpg","title":"Sora 2"},{"category":"text-to-video","description":"Text-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.","endpoint_id":"fal-ai/sora-2/text-to-video","family":"Sora 2","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"720p","description":"The resolution of the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":4,"description":"Duration of the generated video in seconds","enum":[4,8,12,16,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to delete the video after generation for privacy reasons. If True, the video cannot be used for remixing and will be permanently deleted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"delete_video","required":false,"type":"boolean"},{"default":"sora-2","description":"The model to use for the generation. When the default model is selected, the latest snapshot of the model will be used - otherwise, select a specific snapshot of the model.","enum":["sora-2","sora-2-2025-12-08","sora-2-2025-10-06"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":false,"description":"If enabled, the prompt (and image for image-to-video) will be checked for known intellectual property references and the request will be blocked if any are detected.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detect_and_block_ip","required":false,"type":"boolean"},{"default":null,"description":"Up to two character IDs (from create-character) to use in the video. Refer to characters by name in the prompt. When set, only the OpenAI provider is used.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"character_ids","required":false,"type":"string"}],"lab":"OpenAI","output_kind":"video","output_props":["video_id","spritesheet","video","thumbnail"],"pricing":"The pricing is $0.1/s for Sora 2.","published_at":"2025-10-06T19:34:55.710000+00:00","thumbnail":"https://v3.fal.media/files/penguin/eOGowiQKXIKwyDfwgeWQO_b80784431c524553a564ebdd7550d7e6.jpg","title":"Sora 2"},{"category":"text-to-video","description":"Text-to-video endpoint for Sora 2 Pro, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.","endpoint_id":"fal-ai/sora-2/text-to-video/pro","family":"Sora 2","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1080p","description":"The resolution of the generated video","enum":["720p","1080p","true_1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":4,"description":"Duration of the generated video in seconds","enum":[4,8,12,16,20],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":true,"description":"Whether to delete the video after generation for privacy reasons. If True, the video cannot be used for remixing and will be permanently deleted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"delete_video","required":false,"type":"boolean"},{"default":false,"description":"If enabled, the prompt (and image for image-to-video) will be checked for known intellectual property references and the request will be blocked if any are detected.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detect_and_block_ip","required":false,"type":"boolean"},{"default":null,"description":"Up to two character IDs (from create-character) to use in the video. Refer to characters by name in the prompt. When set, only the OpenAI provider is used.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"character_ids","required":false,"type":"string"}],"lab":"OpenAI","output_kind":"video","output_props":["video_id","spritesheet","video","thumbnail"],"pricing":"The pricing is $0.30/s for 720p, $0.50/s for legacy 1080p (1792x1024 or 1024x1792) or $0.70/s for true 1080p (1920x1080 or 1080x1920).","published_at":"2025-10-06T21:56:38.344000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/0bXyMS_zSKpeaG3LM6ARv_d4ee6acbfd9a4168b012a848c33b154d.jpg","title":"Sora 2"},{"category":"video-to-video","description":"Video-to-video remix endpoint for Sora 2, OpenAI’s advanced model that transforms existing videos based on new text or image prompts allowing rich edits, style changes, and creative reinterpretations while preserving motion and structure","endpoint_id":"fal-ai/sora-2/video-to-video/remix","family":"Sora 2","inputs":[{"default":null,"description":"The video_id from a previous Sora 2 generation. Note: You can only remix videos that were generated by Sora (via text-to-video or image-to-video endpoints), not arbitrary uploaded videos.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"video_id","required":true,"type":"string"},{"default":null,"description":"Updated text prompt that directs the remix generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":true,"description":"Whether to delete the video after generation for privacy reasons. If True, the video cannot be used for remixing and will be permanently deleted.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"delete_video","required":false,"type":"boolean"}],"lab":"OpenAI","output_kind":"video","output_props":["video_id","spritesheet","video","thumbnail"],"pricing":"The pricing is $0.1/s for Sora 2.","published_at":"2025-10-08T23:13:08.227000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/Wz6FyBTYFs2Lf8e9AoXED_966c4e27910e4979b2628d5666dd2ea0.jpg","title":"Sora 2"},{"category":"speech-to-text","description":"Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.","endpoint_id":"fal-ai/speech-to-text","family":"","inputs":[{"default":null,"description":"Local filesystem path (or remote URL) to a long audio file","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":true,"description":"Whether to use Canary's built-in punctuation & capitalization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_pnc","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["partial","output"],"pricing":"","published_at":"2025-04-04T15:08:54.913000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/canary.webp","title":"Speech-to-Text"},{"category":"speech-to-text","description":"Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.","endpoint_id":"fal-ai/speech-to-text/stream","family":"","inputs":[{"default":null,"description":"Local filesystem path (or remote URL) to a long audio file","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":true,"description":"Whether to use Canary's built-in punctuation & capitalization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_pnc","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-04-04T16:01:08.836000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/canary.webp","title":"Speech-To-text"},{"category":"speech-to-text","description":"Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.","endpoint_id":"fal-ai/speech-to-text/turbo","family":"","inputs":[{"default":null,"description":"Local filesystem path (or remote URL) to a long audio file","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":true,"description":"Whether to use Canary's built-in punctuation & capitalization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_pnc","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":["partial","output"],"pricing":"","published_at":"2025-04-04T19:35:54.848000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/canary.webp","title":"Speech-to-Text"},{"category":"speech-to-text","description":"Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.","endpoint_id":"fal-ai/speech-to-text/turbo/stream","family":"","inputs":[{"default":null,"description":"Local filesystem path (or remote URL) to a long audio file","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":true,"description":"Whether to use Canary's built-in punctuation & capitalization","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_pnc","required":false,"type":"boolean"}],"lab":"","output_kind":"json","output_props":[],"pricing":"","published_at":"2025-04-04T19:13:10.736000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/canary.webp","title":"Speech-to-Text"},{"category":"text-to-audio","description":"Open source text-to-audio model.","endpoint_id":"fal-ai/stable-audio","family":"","inputs":[{"default":null,"description":"The prompt to generate audio from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0,"description":"The start point of the audio clip to generate","enum":null,"is_list":false,"max":47,"media_kind":null,"min":0,"multiline":false,"name":"seconds_start","required":false,"type":"integer"},{"default":30,"description":"The duration of the audio clip to generate","enum":null,"is_list":false,"max":47,"media_kind":null,"min":0,"multiline":false,"name":"seconds_total","required":false,"type":"integer"},{"default":100,"description":"The number of steps to denoise the audio for","enum":null,"is_list":false,"max":1000,"media_kind":null,"min":2,"multiline":false,"name":"steps","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"json","output_props":["audio_file"],"pricing":"","published_at":"2024-01-04T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ac/Y4wJF8Zssld_xUqoxrUFL_SRbvyWYq.png","title":"Stable Audio Open"},{"category":"audio-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","endpoint_id":"fal-ai/stable-audio-25/audio-to-audio","family":"","inputs":[{"default":null,"description":"The prompt to guide the audio generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The audio clip to transform","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.8,"description":"Sometimes referred to as denoising, this parameter controls how much influence the `audio_url` parameter has on the generated audio. A value of 0 would yield audio that is identical to the input. A value of 1 would be as if you passed in no audio at all.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":8,"description":"The number of steps to denoise the audio for","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The duration of the audio clip to generate. If not provided, it will be set to the duration of the input audio.","enum":null,"is_list":false,"max":190,"media_kind":null,"min":1,"multiline":false,"name":"total_seconds","required":false,"type":"integer"},{"default":1,"description":"How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt).","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Seed","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"audio","output_props":["audio","seed"],"pricing":"","published_at":"2025-09-10T11:51:47.856000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92e0/AZXaxD049-BtyQY433DPD_hA9hXLtT.png","title":"Stable Audio 2.5"},{"category":"audio-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","endpoint_id":"fal-ai/stable-audio-25/inpaint","family":"","inputs":[{"default":null,"description":"The prompt to guide the audio generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The audio clip to inpaint","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":190,"description":"The duration of the audio clip to generate. If not provided, it will be set to the duration of the input audio.","enum":null,"is_list":false,"max":190,"media_kind":null,"min":1,"multiline":false,"name":"seconds_total","required":false,"type":"integer"},{"default":1,"description":"How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt).","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":30,"description":"The start point of the audio mask","enum":null,"is_list":false,"max":190,"media_kind":null,"min":0,"multiline":false,"name":"mask_start","required":false,"type":"integer"},{"default":190,"description":"The end point of the audio mask","enum":null,"is_list":false,"max":190,"media_kind":null,"min":0,"multiline":false,"name":"mask_end","required":false,"type":"integer"},{"default":8,"description":"The number of steps to denoise the audio for","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"Seed","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"audio","output_props":["audio","seed"],"pricing":"","published_at":"2025-09-10T11:46:09.286000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f939c/Ylxvt7v73QKZ0FWrD-HVA_5qMPrdpT.png","title":"Stable Audio 25"},{"category":"text-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","endpoint_id":"fal-ai/stable-audio-25/text-to-audio","family":"","inputs":[{"default":null,"description":"The prompt to generate audio from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":190,"description":"The duration of the audio clip to generate","enum":null,"is_list":false,"max":190,"media_kind":null,"min":1,"multiline":false,"name":"seconds_total","required":false,"type":"integer"},{"default":8,"description":"The number of steps to denoise the audio for","enum":null,"is_list":false,"max":8,"media_kind":null,"min":4,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt).","enum":null,"is_list":false,"max":25,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Seed","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"audio","output_props":["audio","seed"],"pricing":"","published_at":"2025-09-10T11:50:27.666000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91ae/mtqDUea-jzlnWg_odMe1j_bB5cIBlf.png","title":"Stable Audio 2.5"},{"category":"training","description":"Stable Audio 3 LoRA Trainer fine-tunes Stable Audio 3 base models on paired audio-caption datasets, producing compact LoRA weights that adapt generation toward a custom music style, sound palette, or domain.","endpoint_id":"fal-ai/stable-audio-3-trainer","family":"Stable Audio 3","inputs":[{"default":null,"description":"URL to a zip archive containing audio files and matching `.txt` captions. Each audio file must have a sibling caption file with the same basename, for example `clip.wav` and `clip.txt`.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_data_url","required":true,"type":"string"},{"default":"medium-base","description":"Stable Audio 3 base checkpoint to fine-tune.","enum":["medium-base","small-music-base","small-sfx-base"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":1000,"description":"Number of LoRA training steps.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":1,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0001,"description":"AdamW learning rate for LoRA parameters.","enum":null,"is_list":false,"max":0.01,"media_kind":null,"min":0,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":16,"description":"LoRA rank.","enum":null,"is_list":false,"max":256,"media_kind":null,"min":1,"multiline":false,"name":"rank","required":false,"type":"integer"},{"default":"dora-rows","description":"LoRA adapter family to train.","enum":["lora","dora","dora-rows","dora-cols","bora","lora-xs","dora-rows-xs","dora-cols-xs","bora-xs"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adapter_type","required":false,"type":"enum"},{"default":null,"description":"Clip duration in seconds for crop/pad sizing. Leave unset to auto-detect from the dataset (the longest clip). Always capped at the chosen model's native training length.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":1,"description":"Training batch size. Runs with batch_size > 1 are billed additional units proportional to batch_size x clip duration.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"batch_size","required":false,"type":"integer"},{"default":42,"description":"Random seed.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"bf16","description":"Precision for frozen base weights; LoRA params stay fp32.","enum":["bf16","bfloat16","fp16","float16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"base_precision","required":false,"type":"enum"},{"default":null,"description":"Only add LoRA to modules whose names contain these substrings.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include","required":false,"type":"string"},{"default":null,"description":"Skip modules whose names contain these substrings.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"exclude","required":false,"type":"string"},{"default":null,"description":"Optional `.safetensors` LoRA checkpoint URL to resume from.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"lora_checkpoint_url","required":false,"type":"string"},{"default":false,"description":"Pre-encode the audio archive to SAME latents before LoRA training.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pre_encode","required":false,"type":"boolean"}],"lab":"Stability AI","output_kind":"json","output_props":["config_file","lora_file"],"pricing":"Your request will cost $3.00 per 1000-step training run. It scales per step, so a 2000-step training run will cost $6.00. Training with `batch_size` > 1 bills additional units proportional to `batch_size × clip duration`.","published_at":"2026-06-12T15:20:20.743000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dde78/H-0IiF_EcppSobAaoIZKt_f8595f702fbd4a228de9f4e00f209934.jpg","title":"Stable Audio 3 Trainer"},{"category":"audio-to-audio","description":"Stable Audio 3 Medium audio inpainting is a 1.4 billion parameter latent diffusion model that fills in or reworks selected segments of a stereo track guided by text prompts, supporting single- and multi-segment editing.","endpoint_id":"fal-ai/stable-audio-3/medium/audio-inpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio. Only the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Start of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"mask_start_seconds","required":true,"type":"number"},{"default":null,"description":"End of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"mask_end_seconds","required":true,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:39:47.552000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afef0/H2bN2xVPWM8--GfW-yMIU_b0184c33ce8840c0b0753d75d175296d.jpg","title":"Stable Audio 3 Medium Audio Inpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Medium audio outpainting is a 1.4 billion parameter latent diffusion model that extends existing stereo audio beyond its original endpoint via causal continuation guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/medium/audio-outpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding the extension content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to extend.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Seconds of new audio to generate before the source audio.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_before","required":false,"type":"number"},{"default":0,"description":"Seconds of new audio to generate after the source audio.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_after","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:00.647000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afee9/cCyARZ8Pw73aJn39EoLmc_22690100f16441dd9632690e8f77e127.jpg","title":"Stable Audio 3 Medium Audio Outpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Medium audio-to-audio is a 1.4 billion parameter latent diffusion model that transforms an input audio clip into new stereo variations up to 6 minutes guided by a text prompt.","endpoint_id":"fal-ai/stable-audio-3/medium/audio-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s).","enum":null,"is_list":false,"max":380,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the source audio should be transformed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to transform.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.9,"description":"How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"init_noise_level","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:39:38.721000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afef1/8rJnLVKVJOGYqou66eQ2G_17f2e5dd59c14c659955bf3404f9d6a5.jpg","title":"Stable Audio 3 Medium Audio to Audio"},{"category":"audio-to-audio","description":"Stable Audio 3 Medium Base audio inpainting is the foundational 1.4 billion parameter checkpoint for editing or filling selected stereo audio segments guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/medium/base/audio-inpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio. Only the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Start of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"mask_start_seconds","required":true,"type":"number"},{"default":null,"description":"End of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"mask_end_seconds","required":true,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:41:32.040000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afeeb/bg-YuQIOPmZZgJj6OgW-k_f6720ee47c684abfb67105d0164385ba.jpg","title":"Stable Audio 3 Medium Base Audio Inpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Medium Base audio outpainting is the foundational 1.4 billion parameter checkpoint that extends existing stereo audio with causal continuation guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/medium/base/audio-outpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding the extension content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to extend.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Seconds of new audio to generate before the source audio.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_before","required":false,"type":"number"},{"default":0,"description":"Seconds of new audio to generate after the source audio.","enum":null,"is_list":false,"max":380,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_after","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:41:40.487000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afee9/cOp5v1BcWtmgnpIxX8Sy7_450aa391c16e48bb9052769c7f293537.jpg","title":"Stable Audio 3 Medium Base Audio Outpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Medium Base audio-to-audio is the foundational 1.4 billion parameter checkpoint that transforms input audio into new stereo variations up to 6 minutes guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/medium/base/audio-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s).","enum":null,"is_list":false,"max":380,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the source audio should be transformed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to transform.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.9,"description":"How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"init_noise_level","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:41:25.351000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afeee/Wj_uxy9sYVa6cMuxJueyT_0589558bdc874c7c838ed89bc6f4daaa.jpg","title":"Stable Audio 3 Medium Base Audio to Audio"},{"category":"text-to-audio","description":"Stable Audio 3 Medium Base is the foundational 1.4 billion parameter text-to-audio checkpoint generating stereo music up to 6 minutes, intended as the unmodified base for custom fine-tuning workflows.","endpoint_id":"fal-ai/stable-audio-3/medium/base/text-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s).","enum":null,"is_list":false,"max":380,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description of the audio to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:41:17.683000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afef7/T9QQlYMsBV4QUMzKXNl1T_fc97eeec050f46548ae2276c4599aaea.jpg","title":"Stable Audio 3 Medium Base Text to Audio"},{"category":"text-to-audio","description":"Stable Audio 3 Medium is a 1.4 billion parameter latent diffusion model that generates high-quality stereo music up to 6 minutes from text prompts, trained on fully licensed data for safe commercial use.","endpoint_id":"fal-ai/stable-audio-3/medium/text-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s).","enum":null,"is_list":false,"max":380,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description of the audio to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:39:28.991000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b2029/-fLLWd3eyZFK2trS5WZSm_3fcc28379b8e43cba15bd36bf4e573d3.jpg","title":"Stable Audio 3"},{"category":"audio-to-audio","description":"Stable Audio 3 Small Music audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a music track guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/music/audio-inpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio. Only the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Start of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_start_seconds","required":true,"type":"number"},{"default":null,"description":"End of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_end_seconds","required":true,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:39:06.570000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b0f/N2740TzF9Szx8jXGxpLmP_65f836db1db94202948361b0c99232e4.jpg","title":"Stable Audio 3 Small Music Audio Inpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small Music audio outpainting is a 459 million parameter latent diffusion model that extends music compositions beyond their original endpoint via causal continuation.","endpoint_id":"fal-ai/stable-audio-3/small/music/audio-outpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding the extension content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to extend.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Seconds of new audio to generate before the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_before","required":false,"type":"number"},{"default":0,"description":"Seconds of new audio to generate after the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_after","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:39:21.204000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b0d/Kh-tnlUj_gy0u61oHqq56_fd08d0fe65544232975c56508110aa0e.jpg","title":"Stable Audio 3 Small Music Audio Outpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small Music audio-to-audio is a 459 million parameter latent diffusion model that transforms input music into new variations up to 2 minutes guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/music/audio-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the source audio should be transformed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to transform.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.9,"description":"How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"init_noise_level","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:38:50.458000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afef4/YhJSYE2movbXiqKa-cIfh_bb2831ac8a374cceac99fdfea79ebdbc.jpg","title":"Stable Audio 3"},{"category":"audio-to-audio","description":"Stable Audio 3 Small Music Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected music segments guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/music/base/audio-inpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio. Only the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Start of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_start_seconds","required":true,"type":"number"},{"default":null,"description":"End of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_end_seconds","required":true,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:50.552000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b0d/4uEUhNCfIlvttfEsO9w8U_f367e57452f44cbda40ffcaf2bb6a9f4.jpg","title":"Stable Audio 3 Small Music Base Audio Inpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small Music Base audio outpainting is the foundational 459 million parameter checkpoint that extends music tracks via causal continuation guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/music/base/audio-outpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding the extension content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to extend.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Seconds of new audio to generate before the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_before","required":false,"type":"number"},{"default":0,"description":"Seconds of new audio to generate after the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_after","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:41:07.095000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b0c/2gdxA9DEL1uyWlprJCdq8_fc0f082c9b354f6e9befbc9813d6b891.jpg","title":"Stable Audio 3 Small Music Base Audio Outpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small Music Base audio-to-audio is the foundational 459 million parameter checkpoint that transforms input music into new variations up to 2 minutes guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/music/base/audio-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the source audio should be transformed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to transform.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.9,"description":"How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"init_noise_level","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:35.010000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b10/scDouGSsSQQF7yHNTa5hX_156730bac7c1485896425347d095b77b.jpg","title":"Stable Audio 3 Small Music Base Audio to Audio"},{"category":"text-to-audio","description":"Stable Audio 3 Small Music Base is the foundational 459 million parameter checkpoint generating full music compositions up to 2 minutes from text prompts, intended as the unmodified base for fine-tuning.","endpoint_id":"fal-ai/stable-audio-3/small/music/base/text-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description of the audio to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:18.337000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b202c/-1VabDgY8w--qmHnWfvTi_f76bd896adb540eb9c26b21ed83cc2c7.jpg","title":"Stable Audio 3"},{"category":"text-to-audio","description":"Stable Audio 3 Small Music is a 459 million parameter latent diffusion model that generates full stereo music compositions up to 2 minutes from text prompts, lightweight enough for on-device deployment.","endpoint_id":"fal-ai/stable-audio-3/small/music/text-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description of the audio to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:38:34.502000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9afee6/G8pcVD9MpzzHo2binrk2Q_24695711c8d54f76bef2b83ad27e8b7b.jpg","title":"Stable Audio 3 Small Music Text to Audio"},{"category":"audio-to-audio","description":"Stable Audio 3 Small SFX audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a sound-effect track guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/audio-inpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio. Only the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Start of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_start_seconds","required":true,"type":"number"},{"default":null,"description":"End of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_end_seconds","required":true,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:38:58.299000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b02/FsS9WTkEnyJtebU94i1XK_5ecc11cdb7054f93b9cdd0c5c461e52d.jpg","title":"Stable Audio 3 Small SFX Audio Inpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small SFX audio outpainting is a 459 million parameter latent diffusion model that extends sound-effect tracks beyond their original endpoint via causal continuation.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/audio-outpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding the extension content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to extend.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Seconds of new audio to generate before the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_before","required":false,"type":"number"},{"default":0,"description":"Seconds of new audio to generate after the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_after","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:39:14.161000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b00/qeJOeuCWkS7pU9FMfLE_q_1302cc712005454fb9b8cecc862f34b1.jpg","title":"Stable Audio 3 Small SFX Audio Outpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small SFX audio-to-audio is a 459 million parameter latent diffusion model that transforms input audio into new sound-effect variations guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/audio-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the source audio should be transformed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to transform.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.9,"description":"How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"init_noise_level","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:38:41.254000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b04/FVC0dnu20pZNNYQBhbi6E_0580bc2c9b35476fa956f1544708b3c4.jpg","title":"Stable Audio 3"},{"category":"audio-to-audio","description":"Stable Audio 3 Small SFX Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected sound-effect segments guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/base/audio-inpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio. Only the masked region is regenerated.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Start of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_start_seconds","required":true,"type":"number"},{"default":null,"description":"End of the region to regenerate, in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"mask_end_seconds","required":true,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:42.295000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b01/ltMw-_ZqrJBsfQrRt1GB1_a093719ec7e449488aec333c7a074fd5.jpg","title":"Stable Audio 3 Small SFX Base Audio Inpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small SFX Base audio outpainting is the foundational 459 million parameter checkpoint that extends sound-effect tracks via causal continuation guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/base/audio-outpainting","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding the extension content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to extend.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0,"description":"Seconds of new audio to generate before the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_before","required":false,"type":"number"},{"default":0,"description":"Seconds of new audio to generate after the source audio.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":0,"multiline":false,"name":"extend_seconds_after","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:58.008000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9afe/Qnmzr6trqXOOWM_QGjO7B_e9976fbcc60a415389b26ffe32ed091a.jpg","title":"Stable Audio 3 Small SFX Base Audio Outpainting"},{"category":"audio-to-audio","description":"Stable Audio 3 Small SFX Base audio-to-audio is the foundational 459 million parameter checkpoint that transforms input audio into new sound-effect variations guided by text prompts.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/base/audio-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description guiding how the source audio should be transformed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Source audio to transform.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":0.9,"description":"How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"init_noise_level","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:27.969000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b04/L9ZlfONfHVw2xbk7h6Lu2_c9565826f8af4827851a7b8e73fc8cf8.jpg","title":"Stable Audio 3 Small SFX Base Audio to Audio"},{"category":"text-to-audio","description":"Stable Audio 3 Small SFX Base is the foundational 459 million parameter checkpoint generating sound effects from text prompts, intended as the unmodified base for fine-tuning.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/base/text-to-audio","family":"","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":50,"description":"Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description of the audio to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:40:08.207000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b06/tZ4fiDfepf2IxUlLSsWLV_92d35c37c4134dd0a83e5704dd4993c4.jpg","title":"Stable Audio 3 Small SFX Base Text to Audio"},{"category":"text-to-audio","description":"Stable Audio 3 Small SFX is a 459 million parameter latent diffusion model that generates high-quality sound effects from text prompts, designed for on-device deployment on mobile phones and consumer laptops.","endpoint_id":"fal-ai/stable-audio-3/small/sfx/text-to-audio","family":"Stable Audio 3","inputs":[{"default":"","description":"Text description of qualities to avoid in the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":8,"description":"Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.","enum":null,"is_list":false,"max":25,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducible outputs. Omit for a random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"If True, the prompt will be expanded using an LLM for more detailed and higher quality results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"Enable NSFW content safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"mp3","description":"Container format for the generated audio output.","enum":["mp3","wav","flac","ogg","opus","m4a","aac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"192k","description":"Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"bitrate","required":false,"type":"string"},{"default":null,"description":"Text description of the audio to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"Stability AI","output_kind":"audio","output_props":["prompt","audio","seed"],"pricing":"","published_at":"2026-06-03T23:38:26.099000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b0b/MlMe2qf34crcM0KQEa25r_dd4d55242f204da6a0c2cf4341bafd4c.jpg","title":"Stable Audio 3 Small SFX Text to Audio"},{"category":"text-to-image","description":"Stable Cascade: Image generation on a smaller & cheaper latent space.","endpoint_id":"fal-ai/stable-cascade","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":20,"description":"Number of steps to run the first stage for.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":4,"multiline":false,"name":"first_stage_steps","required":false,"type":"integer"},{"default":10,"description":"Number of steps to run the second stage for.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":4,"multiline":false,"name":"second_stage_steps","required":false,"type":"integer"},{"default":4,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":0,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"second_stage_guidance_scale","required":false,"type":"number"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Cascade\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"images","output_props":["prompt","seed","timings","has_nsfw_concepts","images"],"pricing":"","published_at":"2024-06-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/stable-cascade.jpeg","title":"Stable Cascade"},{"category":"text-to-image","description":"Anime finetune of Würstchen V3.","endpoint_id":"fal-ai/stable-cascade/sote-diffusion","family":"","inputs":[{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":25,"description":"Number of steps to run the first stage for.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":4,"multiline":false,"name":"first_stage_steps","required":false,"type":"integer"},{"default":10,"description":"Number of steps to run the second stage for.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":4,"multiline":false,"name":"second_stage_steps","required":false,"type":"integer"},{"default":8,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"second_stage_guidance_scale","required":false,"type":"number"},{"default":{"height":1536,"width":1024},"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Cascade\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to false, the safety checker will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"images","output_props":["prompt","seed","timings","has_nsfw_concepts","images"],"pricing":"","published_at":"2024-06-10T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sotediffusion.jpeg","title":"SoteDiffusion"},{"category":"text-to-image","description":"Stable Diffusion v1.5","endpoint_id":"fal-ai/stable-diffusion-v15","family":"","inputs":[{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"","description":"An id bound to a request, can be used with response to identify the request\n            itself.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"request_id","required":false,"type":"string"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"square","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"v1","description":"The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.","enum":["v1","v2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_checker_version","required":false,"type":"enum"},{"default":"[]","description":"The list of embeddings to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"embeddings","required":false,"type":"json"},{"default":25,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, the prompt will be expanded with additional prompts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_prompt","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"format","required":false,"type":"enum"},{"default":null,"description":"The prompt to use for generating the image. Be as descriptive as possible for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"[]","description":"The list of LoRA weights to use.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":7.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"","published_at":"2024-04-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/sd-loras.jpeg","title":"Stable Diffusion v1.5"},{"category":"text-to-image","description":"Stable Diffusion 3 Medium (Text to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.","endpoint_id":"fal-ai/stable-diffusion-v3-medium","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, prompt will be upsampled with more details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_expansion","required":false,"type":"boolean"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Stability AI","output_kind":"images","output_props":["timings","seed","has_nsfw_concepts","images","prompt","num_images"],"pricing":"","published_at":"2024-08-20T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/landing/sd3-sample-03.webp","title":"Stable Diffusion V3"},{"category":"image-to-image","description":"Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.","endpoint_id":"fal-ai/stable-diffusion-v3-medium/image-to-image","family":"","inputs":[{"default":null,"description":"The image URL to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If set to true, prompt will be upsampled with more details.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"The size of the generated image. Defaults to the conditioning image's size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":0.9,"description":"The strength of the image-to-image transformation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Stability AI","output_kind":"images","output_props":["timings","seed","has_nsfw_concepts","images","prompt","num_images"],"pricing":"","published_at":"2024-06-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/florence-2-large.jpeg","title":"Stable Diffusion V3"},{"category":"text-to-image","description":"Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.","endpoint_id":"fal-ai/stable-diffusion-v35-large","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"ControlNet for inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controlnet","required":false,"type":"json"},{"default":null,"description":"The size of the generated image. Defaults to landscape_4_3 if no controlnet has been passed, otherwise defaults to the size of the controlnet conditioning image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":null,"description":"IP-Adapter to use during inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ip_adapter","required":false,"type":"json"}],"lab":"Stability AI","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2024-10-27T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b5/7yzc_pCuxnBZg_SpQRji7_vIEPYJ8y.png","title":"Stable Diffusion 3.5 Large"},{"category":"text-to-image","description":"Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.","endpoint_id":"fal-ai/stable-diffusion-v35-medium","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"If true (default), the requested `image_size` is silently rounded to the nearest compatible value for this model. If false, the request returns a 422 error when the requested `image_size` is not directly compatible.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"}],"lab":"Stability AI","output_kind":"images","output_props":["prompt","timings","seed","images","has_nsfw_concepts"],"pricing":"","published_at":"2024-10-27T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/stable-diffusion-v35-medium.webp","title":"Stable Diffusion 3.5 Medium"},{"category":"image-to-video","description":"Generate short video clips from your images using SVD v1.1","endpoint_id":"fal-ai/stable-video","family":"","inputs":[{"default":null,"description":"The URL of the image to use as a starting point for the generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of Stable Diffusion\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":127,"description":"The motion bucket id determines the motion of the generated video. The\n            higher the number, the more motion there will be.","enum":null,"is_list":false,"max":255,"media_kind":null,"min":1,"multiline":false,"name":"motion_bucket_id","required":false,"type":"integer"},{"default":0.02,"description":"The conditoning augmentation determines the amount of noise that will be\n            added to the conditioning frame. The higher the number, the more noise\n            there will be, and the less the video will look like the initial image.\n            Increase it for more motion.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"cond_aug","required":false,"type":"number"},{"default":25,"description":"The frames per second of the generated video.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":10,"multiline":false,"name":"fps","required":false,"type":"integer"}],"lab":"Stability AI","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2024-09-16T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/fast-svd.webp","title":"High Quality Stable Video Diffusion"},{"category":"image-to-image","description":"Image-to-image editing with Step1X-Edit v2 from StepFun. Reasoning-enhanced modifications through a thinking–editing–reflection loop with MLLM world knowledge for abstract instruction comprehension.","endpoint_id":"fal-ai/stepx-edit2","family":"","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The image URL to generate an image from. Needs to match the dimensions of the mask.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"The negative prompt to use. Use it to address details that you don't want\n            in the image. This could be colors, objects, scenery and even the small details\n            (e.g. moustache, blurry, low resolution).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":6,"description":"The true CFG scale. Controls how closely the model follows the prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":50,"description":"The number of inference steps to perform. Recommended: 50.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":true,"description":"Enable thinking mode. Uses multimodal language model knowledge to interpret abstract editing instructions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_thinking_mode","required":false,"type":"boolean"},{"default":true,"description":"Enable reflection mode. Reviews outputs, corrects unintended changes, and determines when editing is complete.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_reflection_mode","required":false,"type":"boolean"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","reformat_prompt","timings","prompt","best_info","images","think_info","has_nsfw_concepts"],"pricing":"Your request will cost $0.2 per megapixel.","published_at":"2025-12-09T17:42:27.719000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85a321/vCMVfJpHcA6CdIfx3oi6b_3a43c50dbe5a486ea123cb283d57b074.jpg","title":"Stepx Edit2"},{"category":"video-to-video","description":"Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization.","endpoint_id":"fal-ai/sync-lipsync","family":"","inputs":[{"default":"lipsync-1.9.0-beta","description":"The model to use for lipsyncing","enum":["lipsync-1.8.0","lipsync-1.7.1","lipsync-1.9.0-beta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Syncso","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-01-13T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b7/f46PJEg_jLY5eFroMw1C6_GDlUPgmH.png","title":"sync.so -- lipsync 1.9.0-beta"},{"category":"video-to-video","description":"Use React-1 from SyncLabs to refine human emotions and do realistic lip-sync without losing details!","endpoint_id":"fal-ai/sync-lipsync/react-1","family":"","inputs":[{"default":null,"description":"URL to the input video. Must be **15 seconds or shorter**.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL to the input audio. Must be **15 seconds or shorter**.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Emotion prompt for the generation. Currently supports single-word emotions only.","enum":["happy","sad","angry","disgusted","surprised","neutral"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"emotion","required":true,"type":"enum"},{"default":"face","description":"Controls the edit region and movement scope for the model. Available options:\n- `lips`: Only lipsync using react-1 (minimal facial changes).\n- `face`: Lipsync + facial expressions without head movements.\n- `head`: Lipsync + facial expressions + natural talking head movements.","enum":["lips","face","head"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_mode","required":false,"type":"enum"},{"default":"bounce","description":"Lipsync mode when audio and video durations are out of sync.","enum":["cut_off","loop","bounce","silence","remap"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"lipsync_mode","required":false,"type":"enum"},{"default":0.5,"description":"Controls the expresiveness of the lipsync.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"}],"lab":"Syncso","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-12-10T14:23:05.777000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85c033/t_KdQQe8bt53TwIbJwiHX_63eac44271e847bbbe24a93b1a859bfd.jpg","title":"Sync React-1"},{"category":"video-to-video","description":"Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with Sync Lipsync 2.0 model","endpoint_id":"fal-ai/sync-lipsync/v2","family":"Lipsync 2","inputs":[{"default":"lipsync-2","description":"The model to use for lipsyncing. `lipsync-2-pro` will cost roughly 1.67 times as much as `lipsync-2` for the same duration.","enum":["lipsync-2","lipsync-2-pro"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Syncso","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $3 per minute of video.","published_at":"2025-04-01T18:57:06.699000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a45/-kfzjmJkk91iujX9QQTT3_nAfB0uuc.png","title":"Sync Lipsync 2.0"},{"category":"video-to-video","description":"Generate high-quality realistic lipsync animations from audio while preserving unique details like natural teeth and unique facial features using the state-of-the-art Sync Lipsync 2 Pro model.","endpoint_id":"fal-ai/sync-lipsync/v2/pro","family":"","inputs":[{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Syncso","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-09-02T16:39:37.207000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f91b0/lmANsOOA7MBmiALyLgc9r_0t3I7Ypw.png","title":"Sync Lipsync"},{"category":"video-to-video","description":"sync-3 most powerful lipsync model yet, featuring native visual intelligence for professional-quality video.","endpoint_id":"fal-ai/sync-lipsync/v3","family":"Lipsync 3","inputs":[{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input audio","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Additional Sync.so generation options. If options.sync_mode is set, it overrides the top-level sync_mode field.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"options","required":false,"type":"json"}],"lab":"Syncso","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-04-06T11:59:40.659000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9460ff/hUjOvIu-6_JSEZr9SeFN5_8f82f538ee3246f3942ba081b0e28d3c.jpg","title":"sync-3 Lipsync"},{"category":"image-to-video","description":"sync-3 image to video turns a single still into a talking character, and works with any illustration or animated frame paired with a voice track","endpoint_id":"fal-ai/sync-lipsync/v3/image-to-video","family":"Lipsync 3","inputs":[{"default":null,"description":"URL of the input image. sync-3 animates the face in the image so it lip-syncs to the provided audio (image-to-video). Supported image formats: JPEG, PNG and WebP.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the input audio. The output video matches its duration.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Syncso","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.1333 per output second.","published_at":"2026-06-22T18:42:24.951000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f5836/AuJPMp_Mj03AlRY0-sjy9_65d33ab7767344b7ba7e44d14319e189.jpg","title":"sync-3 Avatar Image to Video"},{"category":"text-to-video","description":"Generate short video clips from your prompts","endpoint_id":"fal-ai/t2v-turbo","family":"","inputs":[{"default":null,"description":"The prompt to generate images from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The seed to use for the random number generator","enum":null,"is_list":false,"max":203279,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"The number of steps to sample","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":7.5,"description":"The guidance scale","enum":null,"is_list":false,"max":30,"media_kind":null,"min":0.1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":16,"description":"The number of frames to generate","enum":null,"is_list":false,"max":32,"media_kind":null,"min":16,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":8,"description":"The FPS of the exported video","enum":null,"is_list":false,"max":24,"media_kind":null,"min":1,"multiline":false,"name":"export_fps","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-03-08T00:00:00+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9393/jAKN5DBAPv33QT1S6fQcm_nL85xDPc.png","title":"T2V Turbo - Video Crafter"},{"category":"audio-to-audio","description":"A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. Lighter 1B variant","endpoint_id":"fal-ai/tada/1b/text-to-speech","family":"","inputs":[{"default":null,"description":"URL of the reference audio file for voice cloning. The model will replicate this speaker's voice characteristics.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"","description":"Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"transcript","required":false,"type":"string"},{"default":null,"description":"The text to synthesize into speech using the reference speaker's voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"en","description":"Language for text alignment. Use the appropriate code for non-English synthesis.","enum":["en","ar","ch","de","es","fr","it","ja","pl","pt"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":0,"description":"Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"num_extra_steps","required":false,"type":"integer"},{"default":0.6,"description":"Sampling temperature for text token generation. Must be greater than 0. Higher values produce more varied output.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.9,"description":"Top-p (nucleus) sampling parameter for text generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":1.1,"description":"Penalty applied to repeated tokens during generation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":1.6,"description":"Classifier-free guidance scale for acoustic feature generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"acoustic_cfg_scale","required":false,"type":"number"},{"default":0.9,"description":"Temperature for noise in the flow matching diffusion process.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"noise_temperature","required":false,"type":"number"},{"default":20,"description":"Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.5,"multiline":false,"name":"speed_up_factor","required":false,"type":"number"},{"default":"wav","description":"The format of the output audio file.","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Hume AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-03-12T18:02:14.510000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91e64c/oCpNOVtEP5jybdJVnd8Ho_fc6a2be1d11547aab60c3bf8cdddf00e.jpg","title":"Tada TTS 1B"},{"category":"audio-to-audio","description":"A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.","endpoint_id":"fal-ai/tada/3b/text-to-speech","family":"","inputs":[{"default":null,"description":"URL of the reference audio file for voice cloning. The model will replicate this speaker's voice characteristics.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"","description":"Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"transcript","required":false,"type":"string"},{"default":null,"description":"The text to synthesize into speech using the reference speaker's voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"en","description":"Language for text alignment. Use the appropriate code for non-English synthesis.","enum":["en","ar","ch","de","es","fr","it","ja","pl","pt"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":0,"description":"Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0,"multiline":false,"name":"num_extra_steps","required":false,"type":"integer"},{"default":0.6,"description":"Sampling temperature for text token generation. Must be greater than 0. Higher values produce more varied output.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.9,"description":"Top-p (nucleus) sampling parameter for text generation.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":1.1,"description":"Penalty applied to repeated tokens during generation.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":1.6,"description":"Classifier-free guidance scale for acoustic feature generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"acoustic_cfg_scale","required":false,"type":"number"},{"default":0.9,"description":"Temperature for noise in the flow matching diffusion process.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"noise_temperature","required":false,"type":"number"},{"default":20,"description":"Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.5,"multiline":false,"name":"speed_up_factor","required":false,"type":"number"},{"default":"wav","description":"The format of the output audio file.","enum":["wav","mp3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-03-12T18:06:14.801000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91e668/dfhOA1ecgEmIvHbLX5jOJ_92c464b7cacc4543ba40f868e742481d.jpg","title":"Tada"},{"category":"image-to-image","description":"Restyle any image with TeleStyle v2 — provide an original image and a styling reference, and the model re-renders the original in the reference's visual style while preserving its content and composition.","endpoint_id":"fal-ai/telestyle-v2","family":"","inputs":[{"default":null,"description":"URL of the content image — the image whose subject and structure are preserved while the style is applied.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"content_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the style reference image — the artistic style, material, lighting and color of this image are transferred onto the content image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"style_image_url","required":true,"type":"string"},{"default":1,"description":"Strength of the TeleStyleV2 style adapter. 1.0 matches the reference implementation; lower values apply the style more subtly.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":true,"description":"If true, use the Lightning LoRA in addition to the default LoRA.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_lightning_lora","required":false,"type":"boolean"},{"default":1,"description":"Strength of the Lightning LoRA. 1.0 matches the reference implementation; lower values apply the style more subtly.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"lightning_lora_scale","required":false,"type":"number"},{"default":true,"description":"If true, describe the content image with a VLM and add the description to the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_content_description","required":false,"type":"boolean"},{"default":true,"description":"If true, describe the style image with a VLM and add the description to the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_style_description","required":false,"type":"boolean"},{"default":null,"description":"The size of the generated image. If not provided, the size of the content image is used.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"The negative prompt for the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"none","description":"Acceleration level for image generation. 'none' (the default) honors the requested num_inference_steps, so the default 4-step Lightning configuration runs in 4 steps. 'regular' engages the downstream accelerated path, which runs a fixed 10 steps regardless of num_inference_steps.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same inputs given to the same version of the model will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2026-06-22T19:15:11.196000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f5a1c/XtiPJ-pDnTydQ9MMqs2KU_7e48fc023ed3453cbc6ed480df26c062.jpg","title":"Telestyle V2 Style Transfer"},{"category":"video-to-video","description":"Generate realistic audio for a video with an optional text prompt and combine","endpoint_id":"fal-ai/thinksound","family":"","inputs":[{"default":null,"description":"The URL of the video to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"A prompt to guide the audio generation. If not provided, it will be extracted from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":24,"description":"The number of inference steps for audio generation.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The classifier-free guidance scale for audio generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["prompt","video"],"pricing":"Your request will cost $0.001 per compute second.","published_at":"2025-07-01T20:56:42.665000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"ThinkSound"},{"category":"video-to-video","description":"Generate realistic audio from a video with an optional text prompt","endpoint_id":"fal-ai/thinksound/audio","family":"","inputs":[{"default":null,"description":"The URL of the video to generate the audio for.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"A prompt to guide the audio generation. If not provided, it will be extracted from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"The seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":24,"description":"The number of inference steps for audio generation.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"The classifier-free guidance scale for audio generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["prompt","audio"],"pricing":"Your request will cost $0.001 per compute second.","published_at":"2025-07-02T22:58:54.729000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"ThinkSound"},{"category":"image-to-image","description":"Use the powerful and accurate topaz image enhancer to enhance your images.","endpoint_id":"fal-ai/topaz/upscale/image","family":"Upscale","inputs":[{"default":"Standard V2","description":"Model to use for image enhancement.","enum":["Low Resolution V2","Standard V2","CGI","High Fidelity V2","Text Refine","Recovery","Redefine","Recovery V2","Standard MAX","Wonder","Wonder 3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":2,"description":"Factor to upscale the image by (e.g. 2.0 doubles width and height)","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":false,"description":"Crop To Fill","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"crop_to_fill","required":false,"type":"boolean"},{"default":null,"description":"Url of the image to be upscaled","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"jpeg","description":"Output format of the upscaled image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"All","description":"Subject detection mode for the image enhancement. Applies to standard enhance and Recovery V2 models.","enum":["All","Foreground","Background"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subject_detection","required":false,"type":"enum"},{"default":true,"description":"Whether to apply face enhancement to the image. Applies to standard enhance and Recovery V2 models.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_enhancement","required":false,"type":"boolean"},{"default":0,"description":"Creativity level for face enhancement. 0.0 means no creativity, 1.0 means maximum creativity. Ignored if face enhancement is disabled.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"face_enhancement_creativity","required":false,"type":"number"},{"default":0.8,"description":"Strength of the face enhancement. 0.0 means no enhancement, 1.0 means maximum enhancement. Ignored if face enhancement is disabled.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"face_enhancement_strength","required":false,"type":"number"},{"default":null,"description":"Sharpening level (0.0-1.0). Applies to Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine, and Redefine models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"sharpen","required":false,"type":"number"},{"default":null,"description":"Denoising level (0.0-1.0). Applies to Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine, and Redefine models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"denoise","required":false,"type":"number"},{"default":null,"description":"Compression artifact removal level (0.0-1.0). Applies to Standard V2, Low Resolution V2, High Fidelity V2, and Text Refine models.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"fix_compression","required":false,"type":"number"},{"default":null,"description":"Enhancement strength (0.01-1.0). Applies to Text Refine model only.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"Creativity level for generative upscaling (1-6). Higher values produce more creative/hallucinated details. Applies to Redefine model only.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"creativity","required":false,"type":"integer"},{"default":null,"description":"Texture detail level for generative upscaling (1-5). Applies to Redefine model only.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":1,"multiline":false,"name":"texture","required":false,"type":"integer"},{"default":null,"description":"Text prompt to guide generative upscaling (max 1024 chars). Applies to Redefine model only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Enable automatic prompt generation for generative upscaling. Applies to Redefine model only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"autoprompt","required":false,"type":"boolean"},{"default":null,"description":"Detail recovery level (0.0-1.0). Applies to Recovery V2 model only.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"detail","required":false,"type":"number"},{"default":null,"description":"Enhancement strength for generative upscaling. Applies to Wonder 3 model only. When omitted, Topaz auto-configures it.","enum":["low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhancement_strength","required":false,"type":"enum"}],"lab":"Topaz Labs","output_kind":"image","output_props":["image"],"pricing":"For a single image, your request will cost $0.08 for up to 24MP, $0.16 for up to 48MP, $0.32 for up to 96MP, and up to $1.36 for 512MP output resolution.","published_at":"2025-06-27T20:22:54.457000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"Topaz"},{"category":"video-to-video","description":"Professional-grade video upscaling using Topaz technology. Enhance your videos with high-quality upscaling.","endpoint_id":"fal-ai/topaz/upscale/video","family":"Upscale","inputs":[{"default":null,"description":"URL of the video to upscale","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"Proteus","description":"Video enhancement model. Proteus is best for most videos, Artemis for denoise+sharpen, Nyx for dedicated denoising, Gaia HQ/CG for rendered content, Gaia 2 for animation and motion graphics at 2x, and Starlight for generative diffusion-based upscaling and enhancement.","enum":["Proteus","Artemis HQ","Artemis MQ","Artemis LQ","Nyx","Nyx Fast","Nyx XL","Nyx HF","Gaia HQ","Gaia CG","Gaia 2","Starlight Precise 1","Starlight Precise 2","Starlight Precise 2.5","Starlight HQ","Starlight Mini","Starlight Sharp","Starlight Fast 1","Starlight Fast 2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":2,"description":"Factor to upscale the video by (e.g. 2.0 doubles width and height)","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"upscale_factor","required":false,"type":"number"},{"default":null,"description":"Target FPS for frame interpolation. If set, frame interpolation will be enabled.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":16,"multiline":false,"name":"target_fps","required":false,"type":"integer"},{"default":null,"description":"Compression artifact removal level (0.0-1.0). Default varies by model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"compression","required":false,"type":"number"},{"default":null,"description":"Noise reduction level (0.0-1.0). Default varies by model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"noise","required":false,"type":"number"},{"default":null,"description":"Halo reduction level (0.0-1.0). Default varies by model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"halo","required":false,"type":"number"},{"default":null,"description":"Film grain amount (0.0-0.1). Default varies by model.","enum":null,"is_list":false,"max":0.1,"media_kind":null,"min":0,"multiline":false,"name":"grain","required":false,"type":"number"},{"default":null,"description":"Recover original detail level (0.0-1.0). Higher values preserve more original detail.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"recover_detail","required":false,"type":"number"},{"default":false,"description":"Whether to use H264 codec for output video. Default is H265.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"H264_output","required":false,"type":"boolean"}],"lab":"Topaz Labs","output_kind":"video","output_props":["video"],"pricing":"For every second a video your request will cost $0.01 for up to 720p, $0.02 for 720p to 1080p, and $0.08 for above 1080p output. Price doubles for 60fps output. For Gaia 2 output costs half of the prices.","published_at":"2025-03-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/topaz-video-upscale.png","title":"Topaz Video Upscale"},{"category":"image-to-3d","description":"Generate 3D models from your images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/trellis","family":"","inputs":[{"default":null,"description":"URL of the input image to convert to 3D","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"Guidance strength for sparse structure generation","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_strength","required":false,"type":"number"},{"default":12,"description":"Sampling steps for sparse structure generation","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"ss_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Guidance strength for structured latent generation","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"slat_guidance_strength","required":false,"type":"number"},{"default":12,"description":"Sampling steps for structured latent generation","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"slat_sampling_steps","required":false,"type":"integer"},{"default":0.95,"description":"Mesh simplification factor","enum":null,"is_list":false,"max":0.98,"media_kind":null,"min":0.9,"multiline":false,"name":"mesh_simplify","required":false,"type":"number"},{"default":1024,"description":"Texture resolution","enum":[512,1024,2048],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"}],"lab":"Trellis","output_kind":"file","output_props":["model_mesh","timings"],"pricing":"","published_at":"2024-12-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/trellis/trellis-photo.jpg","title":"Trellis"},{"category":"image-to-3d","description":"Generate 3D models from your images using Trellis 2. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/trellis-2","family":"","inputs":[{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1024,"description":"Output resolution; higher is slower but more detailed","enum":[512,1024,1536],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":7.5,"description":"How closely the initial 3D structure follows the input image. Higher values produce more faithful but potentially noisier results.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_strength","required":false,"type":"number"},{"default":0.7,"description":"Dampens artifacts from high guidance in stage 1. Lower values allow stronger guidance effects, higher values stabilize the output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Fraction of the denoising process at which classifier-free guidance starts for stage 1 (sparse structure). Guidance is only applied between interval_start and interval_end; outside this window the model runs unguided. Lower values apply guidance earlier.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_interval_start","required":false,"type":"number"},{"default":1,"description":"Fraction of the denoising process at which classifier-free guidance ends for stage 1 (sparse structure). Must be >= ss_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for the initial structure. More steps = slower but potentially higher quality.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"ss_sampling_steps","required":false,"type":"integer"},{"default":5,"description":"Controls noise schedule sharpness for structure generation. Higher values produce sharper transitions.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"ss_rescale_t","required":false,"type":"number"},{"default":7.5,"description":"How closely the detailed geometry follows the input image. Higher values add more detail but may introduce noise.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_strength","required":false,"type":"number"},{"default":0.5,"description":"Dampens artifacts from high guidance in the shape stage. Increase if you see noisy geometry.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Fraction of the denoising process at which classifier-free guidance starts for stage 2 (shape refinement). Guidance is only applied between interval_start and interval_end.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_interval_start","required":false,"type":"number"},{"default":1,"description":"Fraction of the denoising process at which classifier-free guidance ends for stage 2 (shape refinement). Must be >= shape_slat_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for shape refinement. More steps = slower but potentially smoother geometry.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for shape refinement. Higher values produce sharper geometric details.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_rescale_t","required":false,"type":"number"},{"default":1,"description":"How closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_strength","required":false,"type":"number"},{"default":0,"description":"Dampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Fraction of the denoising process at which classifier-free guidance starts for stage 3 (texture). Guidance is only applied between interval_start and interval_end.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_interval_start","required":false,"type":"number"},{"default":0.9,"description":"Fraction of the denoising process at which classifier-free guidance ends for stage 3 (texture). Must be >= tex_slat_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for texture generation. More steps = slower but potentially cleaner textures.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for texture generation. Higher values produce sharper texture details.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_rescale_t","required":false,"type":"number"},{"default":500000,"description":"Target number of vertices in the final mesh. Lower values produce smaller files but less detail. 500k is good for most uses, reduce to 20k-50k for web/mobile.","enum":null,"is_list":false,"max":2000000,"media_kind":null,"min":5000,"multiline":false,"name":"decimation_target","required":false,"type":"integer"},{"default":2048,"description":"Resolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files.","enum":[1024,2048,4096],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"},{"default":true,"description":"Rebuild the mesh topology for cleaner triangles. Slower but usually produces better results for downstream use (animation, 3D printing, etc).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"remesh","required":false,"type":"boolean"},{"default":1,"description":"Controls how far remeshing can move vertices from the original surface. Higher values allow more smoothing but may lose fine details.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"remesh_band","required":false,"type":"number"},{"default":0,"description":"How much to project remeshed vertices back onto the original surface. 0 = no projection (smoother), 1 = full projection (preserves detail).","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"remesh_project","required":false,"type":"number"},{"default":90,"description":"Maximum angle (in degrees) between adjacent face normals allowed within a single UV chart. Lower values produce more charts with less distortion; higher values produce fewer, larger charts with potentially more stretching.","enum":null,"is_list":false,"max":180,"media_kind":null,"min":0,"multiline":false,"name":"uv_unwrap_angle_threshold_deg","required":false,"type":"number"},{"default":0,"description":"Number of local refinement passes during UV chart computation. Higher values produce cleaner chart boundaries at the cost of additional UV-unwrap time.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"uv_unwrap_refine_iterations","required":false,"type":"integer"},{"default":1,"description":"Number of global clustering passes during UV chart computation. More passes produce more balanced charts.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"uv_unwrap_global_iterations","required":false,"type":"integer"},{"default":1,"description":"Smoothing strength applied to UV chart boundaries. Higher values reduce visible seams but may introduce UV distortion.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"uv_unwrap_smooth_strength","required":false,"type":"number"},{"default":null,"description":"URL of the input image to convert to 3D","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Trellis","output_kind":"file","output_props":["model_glb"],"pricing":"Your request will cost 0.25 $ for 512p resolution, 0.3 $ for 1024p resolution and 0.35 $ for 1536p resolution.","published_at":"2025-12-17T21:49:28.133000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87573c/DwQCx7YBl36dnFSHaU8OT_bfc26b64d210462489530b5d5d5d98e1.jpg","title":"Trellis 2"},{"category":"image-to-3d","description":"Run inference on LoRA adapters for TRELLIS.2 model","endpoint_id":"fal-ai/trellis-2-lora","family":"TRELLIS.2","inputs":[{"default":null,"description":"URL of the input image to convert to a 3D model.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Optional safetensors LoRA checkpoint trained for the sparse structure denoiser.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"sparse_structure_lora_url","required":false,"type":"string"},{"default":null,"description":"Optional safetensors LoRA checkpoint trained for the geometry denoiser.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"geometry_lora_url","required":false,"type":"string"},{"default":null,"description":"Optional safetensors LoRA checkpoint trained for the texture denoiser.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"texture_lora_url","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":512,"description":"Generation resolution. Must match the resolution the provided LoRA adapters were trained at (1024 runs the cascade pipeline).","enum":[512,1024],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":7.5,"description":"Classifier-free guidance strength for the sparse-structure stage.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_strength","required":false,"type":"number"},{"default":0.7,"description":"Guidance rescale for the sparse-structure stage; higher stabilizes output.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Denoising fraction at which guidance starts for the sparse-structure stage.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_interval_start","required":false,"type":"number"},{"default":1,"description":"Denoising fraction at which guidance ends for the sparse-structure stage. Must be >= ss_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for the sparse-structure stage.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"ss_sampling_steps","required":false,"type":"integer"},{"default":5,"description":"Noise-schedule sharpness for the sparse-structure stage.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"ss_rescale_t","required":false,"type":"number"},{"default":7.5,"description":"Classifier-free guidance strength for the shape stage.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_strength","required":false,"type":"number"},{"default":0.5,"description":"Guidance rescale for the shape stage; increase if geometry looks noisy.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Denoising fraction at which guidance starts for the shape stage.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_interval_start","required":false,"type":"number"},{"default":1,"description":"Denoising fraction at which guidance ends for the shape stage. Must be >= shape_slat_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"shape_slat_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for the shape stage.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Noise-schedule sharpness for the shape stage.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"shape_slat_rescale_t","required":false,"type":"number"},{"default":1,"description":"Classifier-free guidance strength for the texture stage.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_strength","required":false,"type":"number"},{"default":0,"description":"Guidance rescale for the texture stage; increase if textures look noisy.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Denoising fraction at which guidance starts for the texture stage.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_interval_start","required":false,"type":"number"},{"default":0.9,"description":"Denoising fraction at which guidance ends for the texture stage. Must be >= tex_slat_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for the texture stage.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Noise-schedule sharpness for the texture stage.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_rescale_t","required":false,"type":"number"},{"default":500000,"description":"Target vertex count for the exported GLB.","enum":null,"is_list":false,"max":2000000,"media_kind":null,"min":5000,"multiline":false,"name":"decimation_target","required":false,"type":"integer"},{"default":2048,"description":"Texture resolution baked into the exported GLB.","enum":[1024,2048,4096],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"}],"lab":"Trellis","output_kind":"file","output_props":["geometry_lora_url","decimation_target","texture_size","seed","model_glb","sparse_structure_lora_url","resolution","texture_lora_url"],"pricing":"Your request will cost 0.25 $ for 512p resolution, and 0.3 $ for 1024p resolution.","published_at":"2026-07-01T20:58:30.144000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f7d8d/AtIe0TEKUoOSoeh-K3ygR_0df3076ed37647ebab2f2a127aa94181.jpg","title":"TRELLIS.2 LoRA Inference"},{"category":"image-to-3d","description":"Train LoRA adapters for TRELLIS.2 model","endpoint_id":"fal-ai/trellis-2-lora-trainer","family":"TRELLIS.2","inputs":[{"default":null,"description":"URL to a .zip archive containing raw 3D assets or a TRELLIS.2 preprocessed dataset zip returned by the data_preprocessing endpoint.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":true,"name":"data_url","required":true,"type":"string"},{"default":null,"description":"TRELLIS.2 denoisers to fine-tune. One LoRA adapter is trained per entry, and all selected denoisers are trained in parallel from the same preprocessed dataset. Provide 1-3 unique values out of sparse_structure, geometry, and texture.","enum":["sparse_structure","geometry","texture"],"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"denoisers","required":false,"type":"enum"},{"default":512,"description":"Training resolution. Must match the resolution the dataset is preprocessed at. Sparse-structure training uses the same config at both resolutions; geometry and texture have dedicated 512/1024 configs.","enum":[512,1024],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":32,"description":"LoRA rank. Higher values increase adapter capacity.","enum":[16,32,64],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rank","required":false,"type":"enum"},{"default":0.0001,"description":"Learning rate for LoRA optimization.","enum":null,"is_list":false,"max":0.01,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":1000,"description":"Number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"training_steps","required":false,"type":"integer"}],"lab":"Trellis","output_kind":"json","output_props":["adapters","preprocessed_data_file","failed"],"pricing":"Each request is billed a one-time dataset-preparation charge of $0.10023 per input object (10-object minimum, waived when you reuse a prepared dataset) plus a per-denoiser training charge of $8.34 / $3.25 / $3.38 per 1,000 steps for sparse_structure / geometry / texture, scaled by your rank (×0.5 / ×1 / ×2 for 16 / 32 / 64) and resolution (×1 / ×2 for 512 / 1024).","published_at":"2026-07-01T20:58:19.987000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f7d53/TA0CzQH2ejQAMRf7X5RfC_60880bc3d5b14fe49f8ec1d4fbcb1a27.jpg","title":"TRELLIS.2 Trainer"},{"category":"image-to-3d","description":"Generate 3D models from your images using Trellis 2. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/trellis-2/retexture","family":"","inputs":[{"default":null,"description":"URL of the reference image for texturing","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the untextured 3D mesh to retexture. Supports GLB, OBJ, PLY, and STL formats.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"mesh_url","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1024,"description":"Internal resolution for texture generation. Higher produces finer texture details but is slower.","enum":[512,1024],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":1,"description":"How closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_strength","required":false,"type":"number"},{"default":0,"description":"Dampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_rescale","required":false,"type":"number"},{"default":0.6,"description":"Fraction of the denoising process at which classifier-free guidance starts for the texture stage. Guidance is only applied between interval_start and interval_end.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_interval_start","required":false,"type":"number"},{"default":0.9,"description":"Fraction of the denoising process at which classifier-free guidance ends for the texture stage. Must be >= tex_slat_guidance_interval_start.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"tex_slat_guidance_interval_end","required":false,"type":"number"},{"default":12,"description":"Number of denoising steps for texture generation. More steps = slower but potentially cleaner textures.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Controls noise schedule sharpness for texture generation. Higher values produce sharper texture details.","enum":null,"is_list":false,"max":6,"media_kind":null,"min":1,"multiline":false,"name":"tex_slat_rescale_t","required":false,"type":"number"},{"default":2048,"description":"Resolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files.","enum":[1024,2048,4096],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"}],"lab":"Trellis","output_kind":"file","output_props":["model_glb"],"pricing":"Your request will cost 0.2 $ for 512p resolution, 0.24 $ for 1024p resolution and above.","published_at":"2026-03-02T05:51:42.196000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9083b7/m8pfqMD4bOySvPhWU2QgL_71dcad27868f4b3bbb5c78b86d9d10d4.jpg","title":"Trellis 2"},{"category":"image-to-3d","description":"Generate 3D models from multiple images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.","endpoint_id":"fal-ai/trellis/multi","family":"","inputs":[{"default":null,"description":"List of URLs of input images to convert to 3D","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":7.5,"description":"Guidance strength for sparse structure generation","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"ss_guidance_strength","required":false,"type":"number"},{"default":12,"description":"Sampling steps for sparse structure generation","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"ss_sampling_steps","required":false,"type":"integer"},{"default":3,"description":"Guidance strength for structured latent generation","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"slat_guidance_strength","required":false,"type":"number"},{"default":12,"description":"Sampling steps for structured latent generation","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"slat_sampling_steps","required":false,"type":"integer"},{"default":0.95,"description":"Mesh simplification factor","enum":null,"is_list":false,"max":0.98,"media_kind":null,"min":0.9,"multiline":false,"name":"mesh_simplify","required":false,"type":"number"},{"default":1024,"description":"Texture resolution","enum":[512,1024,2048],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_size","required":false,"type":"enum"},{"default":"stochastic","description":"Algorithm for multi-image generation","enum":["stochastic","multidiffusion"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multiimage_algo","required":false,"type":"enum"}],"lab":"Trellis","output_kind":"file","output_props":["model_mesh","timings"],"pricing":"","published_at":"2025-05-02T01:45:42.664000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training.jpg","title":"Trellis"},{"category":"image-to-3d","description":"State of the art Image to 3D Object generation","endpoint_id":"fal-ai/triposr","family":"","inputs":[{"default":null,"description":"Path for the image file to be processed.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"glb","description":"Output format for the 3D model.","enum":["glb","obj"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"Whether to remove the background from the input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"do_remove_background","required":false,"type":"boolean"},{"default":0.9,"description":"Ratio of the foreground image to the original image.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.5,"multiline":false,"name":"foreground_ratio","required":false,"type":"number"},{"default":256,"description":"Resolution of the marching cubes. Above 512 is not recommended.","enum":null,"is_list":false,"max":1024,"media_kind":null,"min":32,"multiline":false,"name":"mc_resolution","required":false,"type":"integer"}],"lab":"","output_kind":"file","output_props":["timings","model_mesh","remeshing_dir"],"pricing":"","published_at":"2024-01-30T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/triposr.jpeg","title":"TripoSR"},{"category":"training","description":"A blazing fast FLUX dev LoRA trainer for subjects and styles.","endpoint_id":"fal-ai/turbo-flux-trainer","family":"","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images, although more is better.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"images_data_url","required":true,"type":"string"},{"default":"ohwx","description":"Trigger phrase to be used in the captions. If None, a trigger word will not be used.\n        If no captions are provide the trigger_work will be used instead of captions. If captions are provided, the trigger word will replace the `[trigger]` string in the captions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"trigger_phrase","required":false,"type":"string"},{"default":1000,"description":"Number of steps to train the LoRA on.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":1,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":0.00115,"description":"Learning rate for the training.","enum":null,"is_list":false,"max":0.01,"media_kind":null,"min":1e-07,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"subject","description":"Training style to use.","enum":["subject","style"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"training_style","required":false,"type":"enum"},{"default":true,"description":"Whether to try to detect the face and crop the images to the face.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_crop","required":false,"type":"boolean"}],"lab":"Black Forest Labs","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"Your request will cost $2.40 per 1000-step training run. It scales per step, so a 2000-step training run costs $4.80. For $2.40 you can run this model with approximately 1 times.","published_at":"2025-04-17T17:40:19.122000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","title":"Turbo Flux Trainer"},{"category":"image-to-image","description":"An AI model that transforms input images into new ones based on text prompts, blending reference visuals with your creative directions.","endpoint_id":"fal-ai/uno","family":"","inputs":[{"default":null,"description":"URL of images to use while generating the image.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image. You can choose between some presets or custom height and width\n            that **must be multiples of 8**.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducible generation. If set none, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"images","output_props":["timings","seed","images","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-04-24T15:42:26.644000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-3.jpeg","title":"Uno"},{"category":"image-to-image","description":"Use USO to perform subject driven generations using reference image.","endpoint_id":"fal-ai/uso","family":"","inputs":[{"default":"","description":"Text prompt for generation. Can be empty for pure style transfer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"List of image URLs in order: [content_image, style_image, extra_style_image].","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"input_image_urls","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"","description":"What you don't want in the image. Use it to exclude unwanted elements, styles, or artifacts.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":28,"description":"Number of denoising steps. More steps can improve quality but increase generation time.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"How closely to follow the prompt. Higher values stick closer to the prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":false,"description":"Preserve the layout and dimensions of the input content image. Useful for style transfer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keep_size","required":false,"type":"boolean"},{"default":1,"description":"Number of images to generate in parallel.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducible generation. Use same seed for consistent results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable NSFW content detection and filtering.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"Output image format. PNG preserves transparency, JPEG is smaller.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["timings","images","has_nsfw_concepts","seed","prompt"],"pricing":"","published_at":"2025-08-30T11:28:00.742000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d7/2u_2YAkIWhp8WhZ9TtAFw_eTNKJhjG.png","title":"Uso"},{"category":"text-to-image","description":"Vector font generation with VecGlypher. Create custom glyphs from text descriptions or reference images—outputs clean SVG paths directly without raster-to-vector conversion.","endpoint_id":"fal-ai/vecglypher","family":"","inputs":[{"default":null,"description":"The target text to generate as vector glyphs. Each character is rendered as a separate SVG path element.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"italic style, 400 weight, serif, text, elegant","description":"Font style description using typography terms such as weight (100-900), style (italic, oblique), category (serif, sans-serif, display, handwriting, monospace), and characteristics (geometric, humanist, condensed, rounded).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"style_description","required":false,"type":"string"},{"default":0.1,"description":"Sampling temperature. Lower values produce more deterministic output.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable input safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":0.95,"description":"Top-p (nucleus) sampling parameter.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":5,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-1,"multiline":false,"name":"top_k","required":false,"type":"integer"},{"default":1,"description":"Repetition penalty to reduce repeated SVG path segments.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":8192,"description":"Maximum tokens to generate. Increase for longer text.","enum":null,"is_list":false,"max":16384,"media_kind":null,"min":256,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":512,"description":"Maximum dimension (width or height) of the output SVG in pixels. The aspect ratio is preserved.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":64,"multiline":false,"name":"output_size","required":false,"type":"integer"},{"default":"black","description":"Fill color for the generated glyphs. Accepts any valid SVG/CSS color value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_color","required":false,"type":"string"},{"default":null,"description":"Optional stroke (outline) color for the generated glyphs. When set, adds an outline around each glyph path.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"stroke_color","required":false,"type":"string"},{"default":1,"description":"Stroke width in SVG units. Only applies when stroke_color is set.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0.1,"multiline":false,"name":"stroke_width","required":false,"type":"number"}],"lab":"","output_kind":"image","output_props":["svg_content","image","seed","timings"],"pricing":"","published_at":"2026-03-10T18:59:53.121000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91a434/p1JeV9wEtYCVNj0lk8WDC_96d2268e79fd4d719129475804c98afc.jpg","title":"Vecglypher"},{"category":"image-to-image","description":"Vector font generation with VecGlypher. Create custom glyphs from text descriptions or reference images—outputs clean SVG paths directly without raster-to-vector conversion.","endpoint_id":"fal-ai/vecglypher/image-to-svg","family":"","inputs":[{"default":null,"description":"The target text to generate as vector glyphs, styled to match the reference images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of reference glyph images whose style should be matched. Provide 1 to 8 images of individual glyph characters.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":0.1,"description":"Sampling temperature.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable input safety checking.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":0.95,"description":"Top-p (nucleus) sampling parameter.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":5,"description":"Top-k sampling parameter.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":-1,"multiline":false,"name":"top_k","required":false,"type":"integer"},{"default":1,"description":"Repetition penalty.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"repetition_penalty","required":false,"type":"number"},{"default":8192,"description":"Maximum tokens to generate.","enum":null,"is_list":false,"max":16384,"media_kind":null,"min":256,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":512,"description":"Maximum dimension (width or height) of the output SVG in pixels. The aspect ratio is preserved.","enum":null,"is_list":false,"max":4096,"media_kind":null,"min":64,"multiline":false,"name":"output_size","required":false,"type":"integer"},{"default":"black","description":"Fill color for the generated glyphs. Accepts any valid SVG/CSS color value.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fill_color","required":false,"type":"string"},{"default":null,"description":"Optional stroke (outline) color for the generated glyphs. When set, adds an outline around each glyph path.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"stroke_color","required":false,"type":"string"},{"default":1,"description":"Stroke width in SVG units. Only applies when stroke_color is set.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":0.1,"multiline":false,"name":"stroke_width","required":false,"type":"number"}],"lab":"","output_kind":"image","output_props":["svg_content","image","seed","timings"],"pricing":"","published_at":"2026-03-10T19:02:20.732000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a91a444/qeByp1NsOsAZiuxSxk6TG_43a15def55bb4c78b38f6f4b8ed8e6f7.jpg","title":"Vecglypher"},{"category":"text-to-video","description":"Veo 2 creates videos with realistic motion and high quality output. Explore different styles and find your own with extensive camera controls.","endpoint_id":"fal-ai/veo2","family":"Veo 2","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["9:16","16:9","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video in seconds","enum":["5s","6s","7s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enhance the video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_prompt","required":false,"type":"boolean"},{"default":null,"description":"A seed to use for the video generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $2.50. For every aditional second you will be charged $0.50.","published_at":"2025-02-21T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/veo2/veo2.webp","title":"Veo 2"},{"category":"image-to-video","description":"Veo 2 creates videos from images with realistic motion and very high quality output.","endpoint_id":"fal-ai/veo2/image-to-video","family":"Veo 2","inputs":[{"default":null,"description":"The text prompt describing how the image should be animated","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":"5s","description":"The duration of the generated video in seconds","enum":["5s","6s","7s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $2.50. For every aditional second you will be charged $0.50.","published_at":"2025-03-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/veo2-image-to-video.webp","title":"Veo 2 (Image to Video)"},{"category":"text-to-video","description":"Veo 3 by Google, the most advanced AI video generation model in the world. With sound on!","endpoint_id":"fal-ai/veo3","family":"Veo 3","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.20 (audio off) or $0.40 (audio on). For example, a 5s video with audio on will cost $2.","published_at":"2025-06-05T20:59:51.339000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Veo 3"},{"category":"text-to-video","description":"Veo 3.1 by Google, the most advanced AI video generation model in the world. With sound on!","endpoint_id":"fal-ai/veo3.1","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.20 without audio or $0.40 with audio for 720p or 1080p. At 4k, you will be charged $0.40 per second without audio, or $0.60 with. For example, a 5 second video at 1080p with audio on will cost $2.00.","published_at":"2025-10-08T17:01:21.561000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/TGTZBJyLk9HdwjB6SB90e.png","title":"Veo 3.1"},{"category":"video-to-video","description":"Extend Veo-Created Videos up to 30 seconds","endpoint_id":"fal-ai/veo3.1/extend-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing how the video should be extended","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"7s","description":"The duration of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"string"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the video to extend. The video should be 720p or 1080p resolution in 16:9 or 9:16 aspect ratio.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.20 (audio off) or $0.40 (audio on). For example, a 5s video with audio on will cost $2.","published_at":"2025-12-15T22:50:52.774000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8674d8/bsNAkImO8tHGm28k4uMMZ_6c677c316f174eef8553ecdc67377ba6.jpg","title":"Veo 3.1"},{"category":"text-to-video","description":"Faster and more cost effective version of Google's Veo 3.1!","endpoint_id":"fal-ai/veo3.1/fast","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.10 without audio or $0.15 with audio for 720p or 1080p. At 4k, you will be charged $0.30 per second without audio, or $0.35 with. For example, a 5 second video at 1080p with audio on will cost $0.75.","published_at":"2025-10-08T17:05:11.177000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/o5x4rjXr3fAEwQgr4Y5vp_69ee214c658e428ba2f8f8b054d70a0e.jpg","title":"Veo 3.1 Fast"},{"category":"video-to-video","description":"Extend Veo-Created Videos up to 30 seconds","endpoint_id":"fal-ai/veo3.1/fast/extend-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing how the video should be extended","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"7s","description":"The duration of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"string"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the video to extend. The video should be 720p or 1080p resolution in 16:9 or 9:16 aspect ratio.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.10 (audio off) or $0.15 (audio on). For example, a 5s video with audio on will cost $0.75.","published_at":"2025-12-15T22:55:47.939000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8674fa/XbhmACHhbyXpu2YHjob0-_cf9e946ef4df427cbf3111197d7a092a.jpg","title":"Veo 3.1 Fast"},{"category":"image-to-video","description":"Generate videos from a first/last frame using Google's Veo 3.1 Fast","endpoint_id":"fal-ai/veo3.1/fast/first-last-frame-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the first frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":true,"type":"string"},{"default":null,"description":"URL of the last frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.10 without audio or $0.15 with audio for 720p or 1080p. At 4k, you will be charged $0.30 per second without audio, or $0.35 with. For example, a 5 second video at 1080p with audio on will cost $0.75.","published_at":"2025-10-08T17:10:43.612000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/8tRJcj1P_EtIcpbdkP3m7_f9984366e4054165a8919d0671acbcb3.jpg","title":"Veo 3.1 Fast"},{"category":"image-to-video","description":"Generate videos from your image prompts using Veo 3.1 fast.","endpoint_id":"fal-ai/veo3.1/fast/image-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video. Only 16:9 and 9:16 are supported.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.10 without audio or $0.15 with audio for 720p or 1080p. At 4k, you will be charged $0.30 per second without audio, or $0.35 with. For example, a 5 second video at 1080p with audio on will cost $0.75.","published_at":"2025-10-08T17:04:11.604000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/CcVVXXOo5stpgsAJV_6UO_74aa2dbdc79447e7ae69b533a7863038.jpg","title":"Veo 3.1 Fast"},{"category":"image-to-video","description":"Generate videos from reference images using Google's Veo 3.1 Fast","endpoint_id":"fal-ai/veo3.1/fast/reference-to-video","family":"","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URLs of the reference images to use for consistent subject appearance","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.10 (audio off) or $0.15 (audio on). For example, a 5s video with audio on will cost $0.75.","published_at":"2026-05-11T15:37:05.906000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/G4gMW4C57OPjhZxeHjr5n_afcc67d98aa7435aa3c3e0fcb3f76d12.jpg","title":"Veo 3.1 Fast"},{"category":"image-to-video","description":"Generate videos from a first and last framed using Google's Veo 3.1","endpoint_id":"fal-ai/veo3.1/first-last-frame-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the first frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":true,"type":"string"},{"default":null,"description":"URL of the last frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.20 without audio or $0.40 with audio for 720p or 1080p. At 4k, you will be charged $0.40 per second without audio, or $0.60 with. For example, a 5 second video at 1080p with audio on will cost $2.00.","published_at":"2025-10-08T17:09:32.703000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/5YSsAJ8Fbwuj97_9vBiTW.jpg","title":"Veo 3.1"},{"category":"image-to-video","description":"Veo 3.1 is the latest state-of-the art video generation model from Google DeepMind","endpoint_id":"fal-ai/veo3.1/image-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video. Only 16:9 and 9:16 are supported.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.20 without audio or $0.40 with audio for 720p or 1080p. At 4k, you will be charged $0.40 per second without audio, or $0.60 with. For example, a 5 second video at 1080p with audio on will cost $2.00.","published_at":"2025-10-08T17:02:47.996000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/G680VZS5VpMMQO1pSt2uj_dfbae33f738344aa98a62cf2022c427c.jpg","title":"Veo 3.1"},{"category":"text-to-video","description":"Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video","endpoint_id":"fal-ai/veo3.1/lite","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.05 for 720p with audio, $0.03 for 720p without audio, $0.08 for 1080p with audio or $0.05 for 1080p without audio. For example, a 4 second video at 720p with audio will cost $0.20.","published_at":"2026-03-31T18:33:44.437000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a946102/2xgttJeG8mvXo4sZCyUWG_d59c1e8028224e278f47fb7cb3f8d878.jpg","title":"Veo3.1 Lite Text to Video"},{"category":"image-to-video","description":"Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video","endpoint_id":"fal-ai/veo3.1/lite/first-last-frame-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the first frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":true,"type":"string"},{"default":null,"description":"URL of the last frame of the video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.05 for 720p with audio, $0.03 for 720p without audio, $0.08 for 1080p with audio or $0.05 for 1080p without audio. For example, a 4 second video at 720p with audio will cost $0.20.","published_at":"2026-03-31T18:36:21.180000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9460ff/_H3biJgSOvAGtxsxEVvCo_509e251f717a47cd9b5bad4a878551cd.jpg","title":"Veo3.1 Lite FLF"},{"category":"image-to-video","description":"Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video","endpoint_id":"fal-ai/veo3.1/lite/image-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing how the image should be animated","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.05 for 720p with audio, $0.03 for 720p without audio, $0.08 for 1080p with audio or $0.05 for 1080p without audio. For example, a 4 second video at 720p with audio will cost $0.20.","published_at":"2026-03-31T18:35:02.766000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a946101/jRTUp9enYBh3ypsb0Ux0a_fe5ca5e28e704976bfff127c5d23f6a9.jpg","title":"Veo3.1 Lite Image to Video"},{"category":"image-to-video","description":"Generate Videos from images using Google's Veo 3.1","endpoint_id":"fal-ai/veo3.1/reference-to-video","family":"Veo 3.1","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p","4k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URLs of the reference images to use for consistent subject appearance","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generate you will be charged $0.20 without audio or $0.40 with audio for 720p or 1080p. At 4k, you will be charged $0.40 per second without audio, or $0.60 with audio. For example, 8 second video at 1080p with audio on will cost $3.20","published_at":"2025-10-08T17:07:06.022000+00:00","thumbnail":"https://v3b.fal.media/files/b/tiger/IwzOGSbzp6e8N00QuLtFF_129417bb24f248298e95c3fa2b1b82fb.jpg","title":"Veo 3.1"},{"category":"text-to-video","description":"Faster and more cost effective version of Google's Veo 3!","endpoint_id":"fal-ai/veo3/fast","family":"Veo 3","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.10 (audio off) or $0.15 (audio on). For example, a 5s video with audio on will cost $0.75.","published_at":"2025-07-09T16:38:31.244000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-3.jpg","title":"Veo 3 Fast"},{"category":"image-to-video","description":"Now with a 50% price drop. Generate videos from your image prompts using Veo 3 fast.","endpoint_id":"fal-ai/veo3/fast/image-to-video","family":"Veo 3","inputs":[{"default":null,"description":"The text prompt describing how the image should be animated","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.10 (audio off) or $0.15 (audio on). For example, a 5s video with audio on will cost $0.75.","published_at":"2025-07-09T16:46:52.274000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","title":"Veo 3 Fast [Image to Video]"},{"category":"image-to-video","description":"Veo 3 is the latest state-of-the art video generation model from Google DeepMind","endpoint_id":"fal-ai/veo3/image-to-video","family":"Veo 3","inputs":[{"default":null,"description":"The text prompt describing how the image should be animated","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The aspect ratio of the generated video.","enum":["auto","16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"8s","description":"The duration of the generated video.","enum":["4s","6s","8s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"A negative prompt to guide the video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"720p","description":"The resolution of the generated video.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to generate audio for the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":false,"description":"Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_fix","required":false,"type":"boolean"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"For every second of video you generated, you will be charged $0.20 (audio off) or $0.40 (audio on). For example, a 5s video with audio on will cost $2.","published_at":"2025-08-01T16:21:19.645000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-5.jpg","title":"Veo3"},{"category":"text-to-speech","description":"Generate long, expressive multi-voice speech using Microsoft's powerful TTS","endpoint_id":"fal-ai/vibevoice","family":"","inputs":[{"default":null,"description":"The script to convert to speech. Can be formatted with 'Speaker X:' prefixes for multi-speaker dialogues.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"script","required":true,"type":"string"},{"default":null,"description":"List of speakers to use for the script. If not provided, will be inferred from the script or voice samples.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speakers","required":true,"type":"json"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1.3,"description":"CFG (Classifier-Free Guidance) scale for generation. Higher values increase adherence to text.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["generation_time","rtf","audio","sample_rate","duration"],"pricing":"Your request will cost $0.04 per generated minute, rounded to the nearest 15 seconds. For $1.00 you can generate up to 25 minutes of speech.","published_at":"2025-08-27T14:33:10.717000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d9/WnzkNpzz6KVbHnrKtdZ-a_nwHJMdHa.png","title":"VibeVoice 1.5B"},{"category":"text-to-speech","description":"Generate long speech snippets fast using Microsoft's powerful TTS.","endpoint_id":"fal-ai/vibevoice/0.5b","family":"","inputs":[{"default":null,"description":"The script to convert to speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"script","required":true,"type":"string"},{"default":null,"description":"Voice to use for speaking.","enum":["Frank","Wayne","Carter","Emma","Grace","Mike"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speaker","required":true,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1.3,"description":"CFG (Classifier-Free Guidance) scale for generation. Higher values increase adherence to text.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["generation_time","rtf","audio","sample_rate","duration"],"pricing":"","published_at":"2025-12-17T17:49:53.269000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87578a/YHiVLig00ZQrC_arc0biD_1f8eb20e928e4bc2b29499c7cb0eae5b.jpg","title":"Vibevoice"},{"category":"text-to-speech","description":"Generate long, expressive multi-voice speech using Microsoft's powerful TTS","endpoint_id":"fal-ai/vibevoice/7b","family":"","inputs":[{"default":null,"description":"The script to convert to speech. Can be formatted with 'Speaker X:' prefixes for multi-speaker dialogues.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"script","required":true,"type":"string"},{"default":null,"description":"List of speakers to use for the script. If not provided, will be inferred from the script or voice samples.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"speakers","required":true,"type":"json"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1.3,"description":"CFG (Classifier-Free Guidance) scale for generation. Higher values increase adherence to text.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":1,"multiline":false,"name":"cfg_scale","required":false,"type":"number"}],"lab":"","output_kind":"audio","output_props":["generation_time","rtf","audio","sample_rate","duration"],"pricing":"Your request will cost $0.04 per generated minute, rounded to the nearest 15 seconds. For $1.00 you can generate up to 25 minutes of speech.","published_at":"2025-08-27T16:22:23.854000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922c/Le1Ew_vsGx5bydPV_dyf__EK5P9oHG.png","title":"VibeVoice 7B"},{"category":"llm","description":"Generate video prompts using a variety of techniques including camera direction, style, pacing, special effects and more.","endpoint_id":"fal-ai/video-prompt-generator","family":"","inputs":[{"default":null,"description":"Core concept or thematic input for the video prompt","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"input_concept","required":true,"type":"string"},{"default":"Simple","description":"Style of the video prompt","enum":["Minimalist","Simple","Detailed","Descriptive","Dynamic","Cinematic","Documentary","Animation","Action","Experimental"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":"None","description":"Camera movement style","enum":["None","Steadicam flow","Drone aerials","Handheld urgency","Crane elegance","Dolly precision","VR 360","Multi-angle rig","Static tripod","Gimbal smoothness","Slider motion","Jib sweep","POV immersion","Time-slice array","Macro extreme","Tilt-shift miniature","Snorricam character","Whip pan dynamics","Dutch angle tension","Underwater housing","Periscope lens"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_style","required":false,"type":"enum"},{"default":"None","description":"Camera direction","enum":["None","Zoom in","Zoom out","Pan left","Pan right","Tilt up","Tilt down","Orbital rotation","Push in","Pull out","Track forward","Track backward","Spiral in","Spiral out","Arc movement","Diagonal traverse","Vertical rise","Vertical descent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"camera_direction","required":false,"type":"enum"},{"default":"None","description":"Pacing rhythm","enum":["None","Slow burn","Rhythmic pulse","Frantic energy","Ebb and flow","Hypnotic drift","Time-lapse rush","Stop-motion staccato","Gradual build","Quick cut rhythm","Long take meditation","Jump cut energy","Match cut flow","Cross-dissolve dreamscape","Parallel action","Slow motion impact","Ramping dynamics","Montage tempo","Continuous flow","Episodic breaks"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pacing","required":false,"type":"enum"},{"default":"None","description":"Special effects approach","enum":["None","Practical effects","CGI enhancement","Analog glitches","Light painting","Projection mapping","Nanosecond exposures","Double exposure","Smoke diffusion","Lens flare artistry","Particle systems","Holographic overlay","Chromatic aberration","Digital distortion","Wire removal","Motion capture","Miniature integration","Weather simulation","Color grading","Mixed media composite","Neural style transfer"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"special_effects","required":false,"type":"enum"},{"default":"","description":"Custom technical elements (optional)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"custom_elements","required":false,"type":"string"},{"default":null,"description":"URL of an image to analyze and incorporate into the video prompt (optional)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":"google/gemini-2.0-flash-001","description":"Model to use","enum":["anthropic/claude-3.5-sonnet","anthropic/claude-3-5-haiku","anthropic/claude-3-haiku","google/gemini-2.5-flash-lite","google/gemini-2.0-flash-001","meta-llama/llama-3.2-1b-instruct","meta-llama/llama-3.2-3b-instruct","meta-llama/llama-3.1-8b-instruct","meta-llama/llama-3.1-70b-instruct","openai/gpt-4o-mini","openai/gpt-4o","deepseek/deepseek-r1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":false,"type":"enum"},{"default":"Medium","description":"Length of the prompt","enum":["Short","Medium","Long"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"prompt_length","required":false,"type":"enum"}],"lab":"","output_kind":"text","output_props":["prompt"],"pricing":"","published_at":"2025-02-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/video-prompt/vprompt.jpg","title":"Video Prompt Generator"},{"category":"vision","description":"A video understanding model to analyze video content and answer questions about what's happening in the video based on user prompts.","endpoint_id":"fal-ai/video-understanding","family":"","inputs":[{"default":null,"description":"URL of the video to analyze","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The question or prompt about the video content.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Whether to request a more detailed analysis of the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"detailed_analysis","required":false,"type":"boolean"}],"lab":"","output_kind":"text","output_props":["output"],"pricing":"","published_at":"2025-06-20T22:35:38.016000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","title":"Video Understanding"},{"category":"video-to-video","description":"The video upscaler endpoint uses RealESRGAN on each frame of the input video to upscale the video to a higher resolution.","endpoint_id":"fal-ai/video-upscaler","family":"","inputs":[{"default":null,"description":"The URL of the video to upscale","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":2,"description":"The scale factor","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"scale","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2024-12-04T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/video-upscaler-thumbnail.jpg","title":"Video Upscaler"},{"category":"image-to-video","description":"Vidu Image to Video generates high-quality videos with exceptional visual quality and motion diversity from a single image","endpoint_id":"fal-ai/vidu/image-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 4s video your request will cost $0.20.","published_at":"2025-03-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/vidu/vidu.webp","title":"Vidu Image to Video"},{"category":"image-to-video","description":"Vidu Q1 Image to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity from a single image","endpoint_id":"fal-ai/vidu/q1/image-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.40.","published_at":"2025-05-09T03:08:30.159000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"Vidu Image to Video"},{"category":"image-to-video","description":"Generate video clips from your multiple image references using Vidu Q1","endpoint_id":"fal-ai/vidu/q1/reference-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of the reference images to use for consistent subject appearance. Q1 model supports up to 7 reference images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"},{"default":false,"description":"Whether to add background music to the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bgm","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.40.","published_at":"2025-07-08T11:41:46.993000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"Vidu"},{"category":"image-to-video","description":"Vidu Q1 Start-End to Video generates smooth transition 1080p videos between specified start and end images.","endpoint_id":"fal-ai/vidu/q1/start-end-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 4s video your request will cost $0.40.","published_at":"2025-05-09T03:12:59.443000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"Vidu Start End to Video"},{"category":"text-to-video","description":"Vidu Q1 Text to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity","endpoint_id":"fal-ai/vidu/q1/text-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"general","description":"The style of output video","enum":["general","anime"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"Seed for the random number generator","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 5s video your request will cost $0.40.","published_at":"2025-05-09T03:10:36.806000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","title":"Vidu Text to Video"},{"category":"image-to-video","description":"Use the latest Vidu Q2 models which much more better quality and control on your videos.","endpoint_id":"fal-ai/vidu/q2/image-to-video/pro","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 3000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the starting frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the ending frame. When provided, generates a transition video between start and end frames.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Duration of the video in seconds","enum":[2,3,4,5,6,7,8],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"},{"default":false,"description":"Whether to add background music to the video (only for 4-second videos)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bgm","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 720 p your video request would cost 0.1 $ along with a 0.05 $ for every video second. For 1080 p each request will cost 0.3 $ along with 0.1 $ for every video second.","published_at":"2025-10-24T09:11:00.692000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/9ZFHimyaNGh_0WHvVLfOn_67d61fe778bd4257a402b467aaff6f66.jpg","title":"Vidu"},{"category":"image-to-video","description":"Use the latest Vidu Q2 models which much more better quality and control on your videos.","endpoint_id":"fal-ai/vidu/q2/image-to-video/turbo","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 3000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the starting frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the ending frame. When provided, generates a transition video between start and end frames.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Duration of the video in seconds","enum":[2,3,4,5,6,7,8],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"},{"default":false,"description":"Whether to add background music to the video (only for 4-second videos)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bgm","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 720 p each video second will cost 0.05 $. For 1080 p each request will cost 0.2 $ along with 0.05 $ for every video second.","published_at":"2025-10-24T09:28:39.019000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/pV-tsWf3pDIWfSzE8Y8QD_405c6376ad454bdd9aec52cfcc23a97e.jpg","title":"Vidu"},{"category":"image-to-image","description":"Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.","endpoint_id":"fal-ai/vidu/q2/reference-to-image","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of the reference images to use for consistent subject appearance","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Vidu","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.1 per image.","published_at":"2025-12-02T15:15:16.476000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a859c0c/hJyZYTr1Sq5HbwhEJWXid_90a9e24d19b4422cbb62fe49229a9266.jpg","title":"Vidu"},{"category":"image-to-video","description":"Use the latest Vidu Q2 Pro models which much more better quality and control on your videos.","endpoint_id":"fal-ai/vidu/q2/reference-to-video/pro","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 2000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of the reference images for subject appearance. If videos are provided, up to 4 images are allowed; otherwise up to 7 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":false,"type":"string"},{"default":null,"description":"URLs of the reference videos for video editing or motion reference. Supports up to 2 videos.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"reference_video_urls","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Duration of the video in seconds (0 for automatic duration)","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"720p","description":"Output video resolution","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the output video (e.g., auto, 16:9, 9:16, 1:1, or any W:H)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"string"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"},{"default":false,"description":"Whether to add background music to the generated video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bgm","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"The model will cost 0.1 $ for every 360p video, 0.2 $ for every 520p video, 0.3 $ for 720 p video. For 1080 p the cost would be 0.2 $ along with 0.1 $ for every video second.","published_at":"2026-01-19T19:49:20.023000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b0dde/etLT9wcPxiw9gdfI1asZ2_4d84e99d288340748ed4af813552e8f1.jpg","title":"Vidu"},{"category":"text-to-image","description":"Use vidu Text-to-Image to turn your prompts into reality.","endpoint_id":"fal-ai/vidu/q2/text-to-image","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Vidu","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.1 per image.","published_at":"2025-12-02T15:12:08.030000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85892d/ODEhamwEyaZ8NSG6ShAdS_055c7fbf76db47deb35ee6042014bc91.jpg","title":"Vidu"},{"category":"text-to-video","description":"Use the latest Vidu Q2 models which much more better quality and control on your videos.","endpoint_id":"fal-ai/vidu/q2/text-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 3000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Duration of the video in seconds","enum":[2,3,4,5,6,7,8],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["360p","520p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"},{"default":false,"description":"Whether to add background music to the video (only for 4-second videos)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"bgm","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"The model will cost 0.1 $ for every 360p video, 0.2 $ for every 520p video, 0.3 $ for 720 p video. For 1080 p the cost would be 0.2 $ along with 0.1 $ for every video second.","published_at":"2025-10-22T16:40:07.242000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/ui3mJj8_Fmxg22mCDuesY_38c8acb860cf4072899ec0c062efcf9e.jpg","title":"Vidu"},{"category":"video-to-video","description":"Use the latest Vidu Q2 models which much more better quality and control on your videos.","endpoint_id":"fal-ai/vidu/q2/video-extension/pro","family":"","inputs":[{"default":null,"description":"URL of the video to extend","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"text prompt to guide the video extension","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":4,"description":"Duration of the extension in seconds","enum":[2,3,4,5,6,7],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Each 360 p video will cost 0.15 $, each 520p video will cost 0.22 $. For 720 p each video second will cost 0.075 $. For 1080 p each video will cost 0.28 $ along with 0.075 $ per video second.","published_at":"2025-10-24T10:03:48.146000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/w0OmEqIT3ttJ87CyIv4YE_9fef0096f9f44fa7af8012a25eae3fa7.jpg","title":"Vidu"},{"category":"image-to-video","description":"Vidu's latest Q3 pro models.","endpoint_id":"fal-ai/vidu/q3/image-to-video","family":"","inputs":[{"default":"","description":"Text prompt for video generation, max 2000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL or base64 image to use as the starting frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the ending frame. When provided, generates a transition video between start and end frames.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":5,"description":"Duration of the video in seconds (1-16 for Q3 models)","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Output video resolution. Note: 360p is not available when end_image_url is provided.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to use direct audio-video generation. When true, outputs video with sound (including dialogue and sound effects).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Your request will cost 0.07 $ per video second for 360p and 540 p, cost will be 2.2x for 720p and 1080p resolution.","published_at":"2026-01-31T07:34:05.888000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c915a/He8Pvpz77hcWVcUYC5hRZ_98109f8630944133a904fad6fe3a701d.jpg","title":"Vidu"},{"category":"image-to-video","description":"Vidu's Q3 Turbo Model","endpoint_id":"fal-ai/vidu/q3/image-to-video/turbo","family":"","inputs":[{"default":"","description":"Text prompt for video generation, max 2000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL or base64 image to use as the starting frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the ending frame. When provided, generates a transition video between start and end frames.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":5,"description":"Duration of the video in seconds (1-16 for Q3 models)","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Output video resolution. Note: 360p is not available when end_image_url is provided.","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to use direct audio-video generation. When true, outputs video with sound (including dialogue and sound effects).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Your request will cost 0.035 $ per video second for 360p and 540 p, cost will be 2.2x for 720p and 1080p resolution.","published_at":"2026-02-06T20:23:42.516000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d6e07/fD4jASVWB2HcQCVy2wpCd_857d6e5041134ad3a094285c4adb2e94.jpg","title":"Vidu"},{"category":"image-to-video","description":"Vidu's latest Q3 Reference to Video Mix model","endpoint_id":"fal-ai/vidu/q3/reference-to-video/mix","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 2000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of 1 to 4 reference images used to keep subjects or scenes consistent","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":5,"description":"Duration of the video in seconds (1-16 for Q3 models)","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","4:3","3:4","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to use direct audio-video generation. When true, outputs video with sound.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Your request will cost 0.07 $ per video second for 360p and 540 p, cost will be 2.2x for 720p and 1080p resolution.","published_at":"2026-04-08T16:23:13.982000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a957345/pZ89MiBhy31s0LcoTlN0N_895614a220bb4020a3e1410421a18b26.png","title":"Vidu"},{"category":"text-to-video","description":"Vidu's latest Q3 pro models","endpoint_id":"fal-ai/vidu/q3/text-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 2000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":5,"description":"Duration of the video in seconds","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","4:3","3:4","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to use direct audio-video generation. When true, outputs video with sound.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Your request will cost 0.07 $ per video second for 360p and 540 p, cost will be 2.2x for 720p and 1080p resolution.","published_at":"2026-01-31T07:32:31.870000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c9162/vH4Zl7noFCQBFqWM-eu9I_802e7d65387f44f0ae3eb0587b38422f.jpg","title":"Vidu"},{"category":"text-to-video","description":"Vidu's Q3 Turbo Model.","endpoint_id":"fal-ai/vidu/q3/text-to-video/turbo","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 2000 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":5,"description":"Duration of the video in seconds","enum":null,"is_list":false,"max":16,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","4:3","3:4","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"720p","description":"Output video resolution","enum":["360p","540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":true,"description":"Whether to use direct audio-video generation. When true, outputs video with sound.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio","required":false,"type":"boolean"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Your request will cost 0.035 $ per video second for 360p and 540 p, cost will be 2.2x for 720p and 1080p resolution.","published_at":"2026-02-06T20:22:55.043000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d6e01/BMufnODRfLxM62qPgxeYS_fe39c8df0dd848f1bfc25a0710be1c1e.jpg","title":"Vidu"},{"category":"image-to-image","description":"Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.","endpoint_id":"fal-ai/vidu/reference-to-image","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of the reference images to use for consistent subject appearance","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Vidu","output_kind":"image","output_props":["image"],"pricing":"Your request will cost $0.1 per image.","published_at":"2025-09-09T11:42:32.318000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/vidu/vidu.webp","title":"Vidu"},{"category":"image-to-video","description":"Vidu Reference to Video creates videos by using a reference images and combining them with a prompt.","endpoint_id":"fal-ai/vidu/reference-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of the reference images to use for consistent subject appearance","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":true,"type":"string"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 4s video your request will cost $0.40.","published_at":"2025-03-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/vidu/vidu.webp","title":"Vidu Reference to Video"},{"category":"image-to-video","description":"Vidu Start-End to Video generates smooth transition videos between specified start and end images.","endpoint_id":"fal-ai/vidu/start-end-to-video","family":"","inputs":[{"default":null,"description":"Text prompt for video generation, max 1500 characters","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the last frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The movement amplitude of objects in the frame","enum":["auto","small","medium","large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"movement_amplitude","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"For 4s video your request will cost $0.20.","published_at":"2025-03-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/vidu/vidu.webp","title":"Vidu Start-End to Video"},{"category":"image-to-video","description":"Vidu Template to Video lets you create different effects by applying motion templates to your images.","endpoint_id":"fal-ai/vidu/template-to-video","family":"","inputs":[{"default":"hug","description":"AI video template to use. Pricing varies by template: Standard templates (hug, kiss, love_pose, etc.) cost 4 credits ($0.20), Premium templates (lunar_newyear, dynasty_dress, dreamy_wedding, etc.) cost 6 credits ($0.30), and Advanced templates (live_photo) cost 10 credits ($0.50).","enum":["dreamy_wedding","romantic_lift","sweet_proposal","couple_arrival","cupid_arrow","pet_lovers","lunar_newyear","hug","kiss","dynasty_dress","wish_sender","love_pose","hair_swap","youth_rewind","morphlab","live_photo","emotionlab","live_memory","interaction","christmas","pet_finger","eat_mushrooms","beast_chase_library","beast_chase_supermarket","petal_scattered","emoji_figure","hair_color_change","multiple_people_kissing","beast_chase_amazon","beast_chase_mountain","balloonman_explodes_pro","get_thinner","jump2pool","bodyshake","jiggle_up","shake_it_dance","subject_3","pubg_winner_hit","shake_it_down","blueprint_supreme","hip_twist","motor_dance","rat_dance","kwok_dance","leg_sweep_dance","heeseung_march","shake_to_max","dame_un_grrr","i_know","lit_bounce","wave_dance","chill_dance","hip_flicking","sakura_season","zongzi_wrap","zongzi_drop","dragonboat_shot","rain_kiss","child_memory","couple_drop","couple_walk","flower_receive","love_drop","cheek_kiss","carry_me","blow_kiss","love_fall","french_kiss_8s","workday_feels","love_story","bloom_magic","ghibli","minecraft","box_me","claw_me","clayshot","manga_meme","quad_meme","pixel_me","clayshot_duo","irasutoya","american_comic","simpsons_comic","yayoi_kusama_style","pop_art","jojo_style","slice_therapy","balloon_flyaway","flying","paperman","pinch","bloom_doorobear","gender_swap","nap_me","sexy_me","spin360","smooth_shift","paper_fall","jump_to_cloud","pilot","sweet_dreams","soul_depart","punch_hit","watermelon_hit","split_stance_pet","make_face","break_glass","split_stance_human","covered_liquid_metal","fluffy_plunge","pet_belly_dance","water_float","relax_cut","head_to_balloon","cloning","across_the_universe_jungle","clothes_spinning_remnant","across_the_universe_jurassic","across_the_universe_moon","fisheye_pet","hitchcock_zoom","cute_bangs","earth_zoom_out","fisheye_human","drive_yacht","virtual_singer","earth_zoom_in","aliens_coming","drive_ferrari","bjd_style","virtual_fitting","orbit","zoom_in","ai_outfit","spin180","orbit_dolly","orbit_dolly_fast","auto_spin","walk_forward","outfit_show","zoom_in_fast","zoom_out_image","zoom_out_startend","muscling","captain_america","hulk","cap_walk","hulk_dive","exotic_princess","beast_companion","cartoon_doll","golden_epoch","oscar_gala","fashion_stride","star_carpet","flame_carpet","frost_carpet","mecha_x","style_me","tap_me","saber_warrior","pet2human","graduation","fishermen","happy_birthday","fairy_me","ladudu_me","ladudu_me_random","squid_game","superman","grow_wings","clevage","fly_with_doraemon","creatice_product_down","pole_dance","hug_from_behind","creatice_product_up_cybercity","creatice_product_up_bluecircuit","creatice_product_up","run_fast","background_explosion"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"template","required":false,"type":"enum"},{"default":null,"description":"URLs of the images to use with the template. Number of images required varies by template: 'dynasty_dress' and 'shop_frame' accept 1-2 images, 'wish_sender' requires exactly 3 images, all other templates accept only 1 image.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"input_image_urls","required":true,"type":"string"},{"default":null,"description":"Random seed for generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"The aspect ratio of the output video","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Vidu","output_kind":"video","output_props":["video"],"pricing":"Standard templates will cost $0.20, Premium templates will cost $0.30, and Advanced templates will cost $0.50.","published_at":"2025-03-12T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/web-examples/vidu/vidu.webp","title":"Vidu Template to Video"},{"category":"video-to-video","description":"VOID removes objects from videos along with all interactions they induce on the scene","endpoint_id":"fal-ai/void-video-inpainting","family":"","inputs":[{"default":null,"description":"URL of the input video containing the object to remove.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"","description":"URL of a mask video for the removal target. For best results this should be a VOID-style quadmask video with 4 grayscale values: 0=object to remove, 63=overlap, 127=affected region, 255=background to keep. A simple binary mask (0=remove, 255=keep) also works. If omitted, the app will generate a temporary mask video from `mask_prompt` using the SAM-3 video endpoint and convert it to a quadmask automatically.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"quad_mask_video_url","required":false,"type":"string"},{"default":null,"description":"Text description of what should be masked in the input video, such as the object or person to remove. Used to generate a temporary mask video with SAM-3 when `quad_mask_video_url` is not provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"mask_prompt","required":false,"type":"string"},{"default":null,"description":"Text description of the desired background after object removal.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":false,"description":"Run VOID Pass 2 warped-noise refinement after Pass 1. This is slower but can improve temporal consistency on longer clips.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_pass2_refinement","required":false,"type":"boolean"},{"default":"The video is not of a high quality, it has a low resolution. Watermark present in each frame. The background is solid. Strange body and strange trajectory. Distortion.","description":"Negative prompt to guide generation away from undesired outputs.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":30,"description":"Number of denoising steps. Higher values improve quality but increase latency.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"Denoising strength. 1.0 means full denoising.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":85,"description":"Temporal window size for inference. The backend snaps this to the nearest CogVideoX-safe value that works with temporal compression and patching. Valid outputs are 69, 77, 85, ..., 197.","enum":null,"is_list":false,"max":197,"media_kind":null,"min":1,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":true,"description":"Enable content safety checking on the output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","seed","timings"],"pricing":"Your request will cost $0.05 per video. With Pass2 enabled it will cost $0.1 per video. Sam3 quad mask generation will cost an additional $0.05.","published_at":"2026-04-16T20:35:57.341000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a959ab1/J4yvJNbWY73Ca0TwDrlhE_e14266cf79374705aabff60c8ee7ac50.jpg","title":"Void Video Inpainting"},{"category":"training","description":"Wan 2.2 text to image LoRA trainer. Fine-tune Wan 2.2 for subjects and styles with unprecedented detail.","endpoint_id":"fal-ai/wan-22-image-trainer","family":"Wan 2.2","inputs":[{"default":null,"description":"URL to the training data.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"training_data_url","required":true,"type":"string"},{"default":null,"description":"Trigger phrase for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":true,"type":"string"},{"default":false,"description":"Whether to include synthetic captions.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"include_synthetic_captions","required":false,"type":"boolean"},{"default":true,"description":"Whether to use face detection for the training data. When enabled, images will use the center of the face as the center of the image when resizing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_face_detection","required":false,"type":"boolean"},{"default":false,"description":"Whether to use face cropping for the training data. When enabled, images will be cropped to the face before resizing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_face_cropping","required":false,"type":"boolean"},{"default":true,"description":"Whether to use masks for the training data.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_masks","required":false,"type":"boolean"},{"default":1000,"description":"Number of training steps.","enum":null,"is_list":false,"max":6000,"media_kind":null,"min":10,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":0.0007,"description":"Learning rate for training.","enum":null,"is_list":false,"max":0.1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":false,"description":"Whether the training data is style data. If true, face specific options like masking and face detection will be disabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"is_style","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"json","output_props":["config_file","diffusers_lora_file","high_noise_lora"],"pricing":"Your request will cost $0.0045 per step (minimum of 100 steps is charged). For $4.5 you can fine-tune a LoRA for 1000 steps.","published_at":"2025-08-11T05:09:18.685000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d6/0TDnFwA9CFqOibLMDhVcf_RNUW4Pgg.png","title":"Wan 2.2 14B Image Trainer"},{"category":"training","description":"Train custom LoRAs for Wan-2.2 T2V/I2V 480P","endpoint_id":"fal-ai/wan-22-trainer/i2v-a14b","family":"Wan Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images and/or videos, although more is better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image/video file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":400,"description":"The number of steps to train for.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"The rate at which the model learns. Higher values can lead to faster training, but over-fitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"","description":"The phrase that will trigger the model to generate an image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, the input will be automatically scale the video to 81 frames at 16fps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"json","output_props":["lora_file","config_file"],"pricing":"Your request will cost $0.005 per step (minimum of 100 steps is charged). For $5 you can fine-tune a LoRA for 1000 steps.","published_at":"2026-02-23T18:10:44.095000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8ff366/NDI3tGs3fj8PgbyK0TThL_88d95271ac3440e7a1901b1298e25711.jpg","title":"Wan-2.2 LoRA Trainer"},{"category":"training","description":"Train custom LoRAs for Wan-2.2 T2V/I2V 480P","endpoint_id":"fal-ai/wan-22-trainer/t2v-a14b","family":"Wan Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images and/or videos, although more is better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image/video file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":400,"description":"The number of steps to train for.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"The rate at which the model learns. Higher values can lead to faster training, but over-fitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"","description":"The phrase that will trigger the model to generate an image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, the input will be automatically scale the video to 81 frames at 16fps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"json","output_props":["lora_file","config_file"],"pricing":"Your request will cost $0.004 per step (minimum of 100 steps is charged). For $4 you can fine-tune a LoRA for 1000 steps.","published_at":"2026-02-23T18:20:05.674000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8ff2f6/Ub5K-T1HayIsPwyGQppfN_4f8ed55de8374b49b79161f8d33554de.jpg","title":"Wan-2.2 LoRA Trainer"},{"category":"video-to-video","description":"VACE Fun for Wan 2.2 A14B from Alibaba-PAI","endpoint_id":"fal-ai/wan-22-vace-fun-a14b/depth","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for depth task.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URLs to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to preprocess the input video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["frames_zip","prompt","video","seed"],"pricing":"Your request will cost $0.10 per video second for 720p, $0.075 per video second for 580p, $0.05 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-09-17T20:52:28.123000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9394/5xuptc139LYPtCtmGCYEH_7s637wVr.png","title":"Wan 2.2 VACE Fun A14B"},{"category":"video-to-video","description":"VACE Fun for Wan 2.2 A14B from Alibaba-PAI","endpoint_id":"fal-ai/wan-22-vace-fun-a14b/inpainting","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL to the source mask file. Required for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":false,"type":"string"},{"default":null,"description":"URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video using salient mask tracking. Will be ignored if mask_video_url is provided.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_image_url","required":false,"type":"string"},{"default":null,"description":"Urls to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to preprocess the input video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["frames_zip","prompt","video","seed"],"pricing":"Your request will cost $0.10 per video second for 720p, $0.075 per video second for 580p, $0.05 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-09-17T21:00:02.580000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a9/7bh4N7oaTXEaYfISZy44E_iPdRe5FM.png","title":"Wan 2.2 VACE Fun A14B"},{"category":"video-to-video","description":"VACE Fun for Wan 2.2 A14B from Alibaba-PAI","endpoint_id":"fal-ai/wan-22-vace-fun-a14b/outpainting","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for outpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URLs to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the left.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_left","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the right.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_right","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the top.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_top","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the bottom.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_bottom","required":false,"type":"boolean"},{"default":0.25,"description":"Amount of expansion. This is a float value between 0 and 1, where 0.25 adds 25% to the original video size on the specified sides.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"expand_ratio","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"video","output_props":["frames_zip","prompt","video","seed"],"pricing":"Your request will cost $0.10 per video second for 720p, $0.075 per video second for 580p, $0.05 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-09-17T21:03:36.437000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9393/M8vfviQUMd2N6iR8qy8L3_gEB1DtEn.png","title":"Wan 2.2 VACE Fun A14B"},{"category":"video-to-video","description":"VACE Fun for Wan 2.2 A14B from Alibaba-PAI","endpoint_id":"fal-ai/wan-22-vace-fun-a14b/reframe","family":"Wan 2.2","inputs":[{"default":"","description":"The text prompt to guide video generation. Optional for reframing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. This video will be used as a reference for the reframe task.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":0,"description":"Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom.","enum":null,"is_list":false,"max":0.9,"media_kind":null,"min":0,"multiline":false,"name":"zoom_factor","required":false,"type":"number"},{"default":true,"description":"Whether to trim borders from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trim_borders","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["frames_zip","prompt","video","seed"],"pricing":"Your request will cost $0.10 per video second for 720p, $0.075 per video second for 580p, $0.05 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-09-17T21:20:15.056000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a0/SAH0GGURqHWnmM-4OzSZi_oejGpBmj.png","title":"Wan 2.2 VACE Fun A14B"},{"category":"image-to-image","description":"Wan 2.5 image-to-image model.","endpoint_id":"fal-ai/wan-25-preview/image-to-image","family":"Wan 2.5","inputs":[{"default":null,"description":"The text prompt describing how to edit the image. Max 2000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of images to edit. For single-image editing, provide 1 URL. For multi-reference generation, provide up to 2 URLs. If more than 2 URLs are provided, only the first 2 will be used.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square","description":"The size of the generated image. Width and height must be between 384 and 1440 pixels.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate. Values from 1 to 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"images","output_props":["actual_prompt","images","seeds"],"pricing":"Your request will cost $0.05 per image.","published_at":"2025-09-25T20:59:52.034000+00:00","thumbnail":"https://v3.fal.media/files/panda/E-LG-LvtKaaYeyx_FPqmu_c75bdd0f332b455e80a7cf14a3a44725.jpg","title":"Wan 2.5 Image to Image"},{"category":"image-to-video","description":"Wan 2.5 image-to-video model.","endpoint_id":"fal-ai/wan-25-preview/image-to-video","family":"Wan 2.5","inputs":[{"default":null,"description":"The text prompt describing the desired video motion. Max 1500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame. Must be publicly accessible or base64 data URI.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the audio to use as the background music. Must be publicly accessible.\nLimit handling: If the audio duration exceeds the duration value (5 or 10 seconds),\nthe audio is truncated to the first 5 or 10 seconds, and the rest is discarded. If\nthe audio is shorter than the video, the remaining part of the video will be silent.\nFor example, if the audio is 3 seconds long and the video duration is 5 seconds, the\nfirst 3 seconds of the output video will have sound, and the last 2 seconds will be s","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"1080p","description":"Video resolution. Valid values: 480p, 720p, 1080p","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. Choose between 5 or 10 seconds.","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed","actual_prompt"],"pricing":"Your request will cost $0.05 per second for 480p, $0.10 per second for 720p, $0.15 per second for 1080p.","published_at":"2025-09-24T01:52:47.880000+00:00","thumbnail":"https://v3.fal.media/files/rabbit/jryVrAZdQNdLdN_4rTlN7_9bebc94cb69a482fb4d948bdd06d6a5e.jpg","title":"Wan 2.5 Image to Video"},{"category":"text-to-image","description":"Wan 2.5 text-to-image model.","endpoint_id":"fal-ai/wan-25-preview/text-to-image","family":"Wan 2.5","inputs":[{"default":null,"description":"The prompt for image generation. Supports Chinese and English, max 2000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":1,"description":"Number of images to generate. Values from 1 to 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"square","description":"The size of the generated image. Can use preset names like 'square', 'landscape_16_9', etc., or specific dimensions. Total pixels must be between 768×768 and 1440×1440, with aspect ratio between [1:4, 4:1].","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":true,"description":"Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"images","output_props":["actual_prompt","images","seeds"],"pricing":"Your request will cost $0.05 per image.","published_at":"2025-09-25T20:57:10.526000+00:00","thumbnail":"https://v3.fal.media/files/penguin/6PlSnB3q28Mu0QjURXyBe_051522e72e02496da12bf011190ca281.jpg","title":"Wan 2.5 Text to Image"},{"category":"text-to-video","description":"Wan 2.5 text-to-video model.","endpoint_id":"fal-ai/wan-25-preview/text-to-video","family":"Wan 2.5","inputs":[{"default":null,"description":"The text prompt for video generation. Supports Chinese and English, max 1500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the audio to use as the background music. Must be publicly accessible.\nLimit handling: If the audio duration exceeds the duration value (5 or 10 seconds),\nthe audio is truncated to the first 5 or 10 seconds, and the rest is discarded. If\nthe audio is shorter than the video, the remaining part of the video will be silent.\nFor example, if the audio is 3 seconds long and the video duration is 5 seconds, the\nfirst 3 seconds of the output video will have sound, and the last 2 seconds will be s","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution tier","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. Choose between 5 or 10 seconds.","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed","actual_prompt"],"pricing":"Your request will cost $0.05 per second for 480p, $0.10 per second for 720p, $0.15 per second for 1080p.","published_at":"2025-09-24T02:07:33.047000+00:00","thumbnail":"https://v3.fal.media/files/koala/yojKCMBipiqJvLr9a3sLC_deec1d2b5b2c4019bc353f6060ec0c09.jpg","title":"Wan 2.5 Text to Video"},{"category":"image-to-video","description":"Wan Effects generates high-quality videos with popular effects from images","endpoint_id":"fal-ai/wan-effects","family":"Wan","inputs":[{"default":null,"description":"The subject to insert into the predefined prompt template for the selected effect.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subject","required":true,"type":"string"},{"default":null,"description":"URL of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"cakeify","description":"The type of effect to apply to the video.","enum":["squish","muscle","inflate","crush","rotate","gun-shooting","deflate","cakeify","hulk","baby","bride","classy","puppy","snow-white","disney-princess","mona-lisa","painting","pirate-captain","princess","jungle","samurai","vip","warrior","zen","assassin","timelapse","tsunami","fire","zoom-call","doom-fps","fus-ro-dah","hug-jesus","robot-face-reveal","super-saiyan","jumpscare","laughing","cartoon-jaw-drop","crying","kissing","angry-face","selfie-younger-self","animeify","blast"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"effect_type","required":false,"type":"enum"},{"default":81,"description":"Number of frames to generate.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":81,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"16:9","description":"Aspect ratio of the output video.","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":1,"description":"The scale of the LoRA weight. Used to adjust effect intensity.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.1,"multiline":false,"name":"lora_scale","required":false,"type":"number"},{"default":false,"description":"Whether to use turbo mode. If True, the video will be generated faster but with lower quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video"],"pricing":"","published_at":"2025-03-13T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_012.jpg","title":"Wan Effects"},{"category":"image-to-video","description":"Wan-2.1 flf2v generates dynamic videos by intelligently bridging a given first frame to a desired end frame through smooth, coherent motion sequences.","endpoint_id":"fal-ai/wan-flf2v","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of the starting image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"start_image_url","required":true,"type":"string"},{"default":null,"description":"URL of the ending image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 100 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":81,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 24.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guide_scale","required":false,"type":"number"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video"],"pricing":"For a video generation, your request will cost $0.2 at 480p resolution and 0.4$ at 720p resolution. For $1 you can run this model with approximately 5 times. More than the default frames will cost 1.25x more.","published_at":"2025-04-17T22:26:51.565000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-2.jpg","title":"Wan-2.1 First-Last-Frame-to-Video"},{"category":"image-to-video","description":"Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images","endpoint_id":"fal-ai/wan-i2v","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 100 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":81,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 24.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guide_scale","required":false,"type":"number"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For a video generation, your request will cost $0.2 at 480p resolution and 0.4$ at 720p resolution. For $1 you can run this model approximately 5 times. More than the default frames will cost 1.25x more.","published_at":"2025-02-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/hunyuan-video-image-to-video.webp","title":"Wan-2.1 Image-to-Video"},{"category":"image-to-video","description":"Add custom LoRAs to Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images","endpoint_id":"fal-ai/wan-i2v-lora","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 100 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":81,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 24.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p or 720p). 480p is 0.5 billing units, and 720p is 1 billing unit.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guide_scale","required":false,"type":"number"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"16:9","description":"Aspect ratio of the output video.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"[]","description":"LoRA weights to be used in the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"If true, the video will be reversed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":true,"description":"If true, the video will be generated faster with no noticeable degradation in the visual quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-03-08T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_02.jpg","title":"Wan-2.1 Image-to-Video with LoRAs"},{"category":"video-to-video","description":"Wan Motion is a streamlined character animation model that transfers motion from a driving video onto a reference character image. Based on Wan-Animate which preserves the original character's proportions, Simple uses pose retargeting to adapt the driving video's skeleton to match the reference character's body shape, producing more natural results when the two have different builds. It outputs at 720p with optimized defaults for fast, high-quality generation — just provide a video, an image, an","endpoint_id":"fal-ai/wan-motion","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the driving video (provides the motion).","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the reference image (provides the character appearance).","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"","description":"Optional text prompt to guide the generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"regular","description":"Acceleration level to use. 'regular' enables caching for faster generation, 'none' disables it.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"Adapts the driving video's motion to match the reference image's body proportions. Recommended when the driving video subject and reference image have different body shapes or sizes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adapt_motion","required":false,"type":"boolean"},{"default":false,"description":"Enhances identity preservation by preprocessing the reference image with Flux Kontext Edit before animation. Produces more faithful face and appearance transfer at the cost of slightly longer processing time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enhance_identity","required":false,"type":"boolean"},{"default":true,"description":"If set to true, input and output will be checked for safety.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.06 per video second for 720p. Video seconds are calculated at 24 frames per second. When enhance_identity is enabled, an additional $0.08 is charged for Flux 2 Edit image preprocessing.","published_at":"2026-02-19T01:00:51.825000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f09a5/VtSJnIbVr0WZ3bOi338JB_a99ce6847ee54a769903f4e17b36a82e.jpg","title":"Wan Motion"},{"category":"image-to-video","description":"Wan-2.1 Pro is a premium image-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from images","endpoint_id":"fal-ai/wan-pro/image-to-video","family":"Wan","inputs":[{"default":null,"description":"The prompt to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":null,"description":"The URL of the image to generate the video from","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Alibaba","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/wan-pro-image-to-video.webp","title":"Wan-2.1 Pro Image-to-Video"},{"category":"text-to-video","description":"Wan-2.1 Pro is a premium text-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from text prompts","endpoint_id":"fal-ai/wan-pro/text-to-video","family":"Wan","inputs":[{"default":null,"description":"The prompt to generate the video","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Whether to enable the safety checker","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-03-11T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_02.jpg","title":"Wan-2.1 Pro Text-to-Video"},{"category":"text-to-video","description":"Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts","endpoint_id":"fal-ai/wan-t2v","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 100 (inclusive).","enum":null,"is_list":false,"max":100,"media_kind":null,"min":81,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 24.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"If true, the video will be generated faster with no noticeable degradation in the visual quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"For a video generation, your request will cost $0.2 at 480p resolution and 0.4$ at 720p resolution. For $1 you can run this model approximately 5 times. More than the default frames will cost 1.25x more.","published_at":"2025-02-25T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_02.jpg","title":"Wan-2.1 Text-to-Video"},{"category":"text-to-video","description":"Add custom LoRAs to Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from images","endpoint_id":"fal-ai/wan-t2v-lora","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 100 (inclusive).","enum":null,"is_list":false,"max":100,"media_kind":null,"min":81,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 24.","enum":null,"is_list":false,"max":24,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["9:16","16:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"If true, the video will be generated faster with no noticeable degradation in the visual quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"turbo_mode","required":false,"type":"boolean"},{"default":"[]","description":"LoRA weights to be used in the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"If true, the video will be reversed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed"],"pricing":"","published_at":"2025-03-25T06:02:53.703000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/wan-i2v-lora.webp","title":"Wan-2.1 Text-to-Video with LoRAs"},{"category":"training","description":"Train custom LoRAs for Wan-2.1 I2V 720P","endpoint_id":"fal-ai/wan-trainer/i2v-720p","family":"Wan Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images and/or videos, although more is better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image/video file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":400,"description":"The number of steps to train for.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"The rate at which the model learns. Higher values can lead to faster training, but over-fitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"","description":"The phrase that will trigger the model to generate an image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, the input will be automatically scale the video to 81 frames at 16fps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"json","output_props":["config_file","lora_file"],"pricing":"","published_at":"2025-06-11T00:33:08.714000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a5c/RjLB7FKIza-PyAnzOMfeB_neXTpyJ5.png","title":"Wan-2.1 LoRA Trainer"},{"category":"training","description":"Train custom LoRAs for Wan-2.1 T2V 1.3B","endpoint_id":"fal-ai/wan-trainer/t2v","family":"Wan Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images and/or videos, although more is better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image/video file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":400,"description":"The number of steps to train for.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"The rate at which the model learns. Higher values can lead to faster training, but over-fitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"","description":"The phrase that will trigger the model to generate an image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, the input will be automatically scale the video to 81 frames at 16fps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"json","output_props":["config_file","lora_file"],"pricing":"","published_at":"2025-06-11T00:35:31.207000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a58/9x88JS9WeQTWs03-5wAVb_SXqxFAWn.png","title":"Wan-2.1 LoRA Trainer"},{"category":"training","description":"Train custom LoRAs for Wan-2.1 T2V 14B","endpoint_id":"fal-ai/wan-trainer/t2v-14b","family":"Wan Trainer","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images and/or videos, although more is better.\n\n        In addition to images the archive can contain text files with captions. Each text file should have the same name as the image/video file it corresponds to.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"training_data_url","required":true,"type":"string"},{"default":400,"description":"The number of steps to train for.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":100,"multiline":false,"name":"number_of_steps","required":false,"type":"integer"},{"default":0.0002,"description":"The rate at which the model learns. Higher values can lead to faster training, but over-fitting.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"","description":"The phrase that will trigger the model to generate an image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trigger_phrase","required":false,"type":"string"},{"default":false,"description":"If true, the input will be automatically scale the video to 81 frames at 16fps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_scale_input","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"json","output_props":["config_file","lora_file"],"pricing":"","published_at":"2025-06-11T00:34:42.291000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a61/1zhtX52j--Gptv7ljLi92_xzX4kPbT.png","title":"Wan-2.1 LoRA Trainer"},{"category":"video-to-video","description":"VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.","endpoint_id":"fal-ai/wan-vace-14b","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"depth","description":"Task type for the model.","enum":["depth","pose","inpainting","outpainting","reframe"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"task","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. If provided, the model will use this video as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":false,"type":"string"},{"default":null,"description":"URL to the source mask file. If provided, the model will use this mask as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":false,"type":"string"},{"default":null,"description":"URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video. If provided mask video url will be ignored.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_image_url","required":false,"type":"string"},{"default":null,"description":"URLs to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to preprocess the input video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip","seed","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-05-27T07:26:55.366000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan VACE 14B"},{"category":"video-to-video","description":"VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.","endpoint_id":"fal-ai/wan-vace-14b/depth","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for depth task.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URLs to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to preprocess the input video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip","seed","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-06-18T19:17:12.449000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan VACE 14B"},{"category":"video-to-video","description":"VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.","endpoint_id":"fal-ai/wan-vace-14b/inpainting","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL to the source mask file. Required for inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"mask_video_url","required":false,"type":"string"},{"default":null,"description":"URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video using salient mask tracking. Will be ignored if mask_video_url is provided.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_image_url","required":false,"type":"string"},{"default":null,"description":"Urls to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to preprocess the input video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip","seed","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-06-18T19:20:48.150000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan VACE 14B"},{"category":"video-to-video","description":"VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.","endpoint_id":"fal-ai/wan-vace-14b/outpainting","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for outpainting.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URLs to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the left.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_left","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the right.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_right","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the top.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_top","required":false,"type":"boolean"},{"default":false,"description":"Whether to expand the video to the bottom.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expand_bottom","required":false,"type":"boolean"},{"default":0.25,"description":"Amount of expansion. This is a float value between 0 and 1, where 0.25 adds 25% to the original video size on the specified sides.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"expand_ratio","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip","seed","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-06-18T19:21:35.546000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan VACE 14B"},{"category":"video-to-video","description":"VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.","endpoint_id":"fal-ai/wan-vace-14b/pose","family":"Wan","inputs":[{"default":null,"description":"The text prompt to guide video generation. For pose task, the prompt should describe the desired pose and action of the subject in the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":false,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. Required for pose task.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URLs to source reference image. If provided, the model will use this image as reference.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"ref_image_urls","required":false,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Whether to preprocess the input video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip","seed","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-06-18T19:19:07.684000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan VACE 14B"},{"category":"video-to-video","description":"VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.","endpoint_id":"fal-ai/wan-vace-14b/reframe","family":"Wan","inputs":[{"default":"","description":"The text prompt to guide video generation. Optional for reframing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_num_frames","required":false,"type":"boolean"},{"default":81,"description":"Number of frames to generate. Must be between 81 to 241 (inclusive).","enum":null,"is_list":false,"max":241,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"match_input_frames_per_second","required":false,"type":"boolean"},{"default":16,"description":"Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.","enum":null,"is_list":false,"max":30,"media_kind":null,"min":5,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. This video will be used as a reference for the reframe task.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL to the first frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"first_frame_url","required":false,"type":"string"},{"default":null,"description":"URL to the last frame of the video. If provided, the model will use this frame as a reference.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"last_frame_url","required":false,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between the original frames. A value of 0 means no interpolation.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":0,"description":"Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0,"multiline":false,"name":"temporal_downsample_factor","required":false,"type":"integer"},{"default":false,"description":"If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":15,"description":"The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":0,"description":"Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom.","enum":null,"is_list":false,"max":0.9,"media_kind":null,"min":0,"multiline":false,"name":"zoom_factor","required":false,"type":"number"},{"default":true,"description":"Whether to trim borders from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trim_borders","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip","seed","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-06-18T19:22:46.388000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan VACE 14B"},{"category":"video-to-video","description":"Reframe entire videos scene-by-scene using Wan VACE 2.1","endpoint_id":"fal-ai/wan-vace-apps/long-reframe","family":"Wan","inputs":[{"default":"","description":"The text prompt to guide video generation. Optional for reframing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":"letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Resolution of the generated video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","1:1","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":30,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":5,"description":"Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"unipc","description":"Sampler to use for video generation.","enum":["unipc","dpm++","euler"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"sampler","required":false,"type":"enum"},{"default":5,"description":"Shift parameter for video generation.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"URL to the source video file. This video will be used as a reference for the reframe task.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":false,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the generated video.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the generated video.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":true,"description":"Whether to enable auto downsample.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":6,"description":"Minimum FPS for auto downsample.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. Options are 'rife' or 'film'.","enum":["rife","film"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":"content_aware","description":"The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.","enum":["content_aware","white","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"transparency_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP file containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":0,"description":"Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom.","enum":null,"is_list":false,"max":0.9,"media_kind":null,"min":0,"multiline":false,"name":"zoom_factor","required":false,"type":"number"},{"default":true,"description":"Whether to trim borders from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"trim_borders","required":false,"type":"boolean"},{"default":30,"description":"Threshold for scene detection sensitivity (0-100). Lower values detect more scenes.","enum":null,"is_list":false,"max":100,"media_kind":null,"min":0,"multiline":false,"name":"scene_threshold","required":false,"type":"number"},{"default":true,"description":"Whether to paste back the reframed scene to the original video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"paste_back","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.08 per 2 seconds of output video for 720p, $0.06 per 2 seconds of output video for 580p, abd $0.04 per 2 seconds of output video for 480p. Seconds are rounded up to the nearest multiple of 2.","published_at":"2025-10-07T23:30:40.266000+00:00","thumbnail":"https://v3b.fal.media/files/b/monkey/djppEVsT608o2Uk-qVVnF_db844977aa314ad4aed7f765afde7a2a.jpg","title":"Wan 2.1 VACE Long Reframe"},{"category":"video-to-video","description":"Edit videos using plain language and Wan VACE","endpoint_id":"fal-ai/wan-vace-apps/video-edit","family":"Wan","inputs":[{"default":null,"description":"Prompt to edit the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"auto","description":"The type of video you're editing. Use 'general' for most videos, and 'human' for videos emphasizing human subjects and motions. The default value 'auto' means the model will guess based on the first frame of the video.","enum":["auto","general","human"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_type","required":false,"type":"enum"},{"default":[],"description":"URLs of the input images to use as a reference for the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":false,"type":"string"},{"default":"auto","description":"Resolution of the edited video.","enum":["auto","240p","360p","480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"regular","description":"Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.","enum":["none","low","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":true,"description":"Whether to enable automatic downsampling. If your video has a high frame rate or is long, enabling longer sequences to be generated. The video will be interpolated back to the original frame rate after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_auto_downsample","required":false,"type":"boolean"},{"default":"auto","description":"Aspect ratio of the edited video.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":15,"description":"The minimum frames per second to downsample the video to.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"auto_downsample_min_fps","required":false,"type":"number"},{"default":true,"description":"Whether to enable the safety checker.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to include a ZIP archive containing all generated frames.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","frames_zip"],"pricing":"Your request will cost $0.10 per video second for 720p, $0.075 per video second for 580p, $0.05 per video second for 480p. Video seconds are calculated at 16 frames per second after downsampling.","published_at":"2025-09-22T03:14:28.550000+00:00","thumbnail":"https://v3.fal.media/files/elephant/STesgR1tPPvf0dornjZou_377f4dd48d49425198c3396e86328a8b.jpg","title":"Wan VACE Video Edit"},{"category":"video-to-video","description":"Wan-Animate is a video model that generates high-fidelity character videos by replicating the expressions and movements of characters from reference videos.","endpoint_id":"fal-ai/wan/v2.2-14b/animate/move","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"480p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":20,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP archive containing per-frame images generated on GPU (lossless).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":false,"description":"If true, applies quality enhancement for faster generation with improved quality. When enabled, parameters are automatically optimized for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_turbo","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","frames_zip","prompt"],"pricing":"Request is billed based on the number of frames, at a rate of 16 frames per \"video second\":\n\n- 720p: $0.08 per video second\n- 580p: $0.06 per video second\n- 480p: $0.04 per video second\n\nHow to calculate your cost:\n\n1. Total frames = video duration × fps\n2. Video seconds (billed) = total frames ÷ 16\n3. Cost = video seconds × price per second\n\nExample — 5-second video at 60 fps, 720p:\n- Total frames = 5 × 60 = 300 frames\n- Video seconds (billed) = 300 ÷ 16 = 18.75\n- Cost = 18.75 × $0.08 = $1.50","published_at":"2025-09-21T22:31:45.413000+00:00","thumbnail":"https://v3.fal.media/files/lion/uXR8uNNcwPze8WMhqrlWO_f4e668e0be7a4a57bf6b45c93bf75199.jpg","title":"Wan-2.2 Animate Move"},{"category":"video-to-video","description":"Wan-Animate Replace is a model that can integrate animated characters into reference videos, replacing the original character while preserving the scene’s lighting and color tone for seamless environmental integration.","endpoint_id":"fal-ai/wan/v2.2-14b/animate/replace","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":1,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"480p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":20,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":false,"description":"If true, also return a ZIP archive containing per-frame images generated on GPU (lossless).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"return_frames_zip","required":false,"type":"boolean"},{"default":false,"description":"If true, applies quality enhancement for faster generation with improved quality. When enabled, parameters are automatically optimized for best results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"use_turbo","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","frames_zip","prompt"],"pricing":"Request is billed based on the number of frames, at a rate of 16 frames per \"video second\":\n\n- 720p: $0.08 per video second\n- 580p: $0.06 per video second\n- 480p: $0.04 per video second\n\nHow to calculate your cost:\n\n1. Total frames = video duration × fps\n2. Video seconds (billed) = total frames ÷ 16\n3. Cost = video seconds × price per second\n\nExample — 5-second video at 60 fps, 720p:\n- Total frames = 5 × 60 = 300 frames\n- Video seconds (billed) = 300 ÷ 16 = 18.75\n- Cost = 18.75 × $0.08 = $1.50","published_at":"2025-09-21T22:34:12.372000+00:00","thumbnail":"https://v3.fal.media/files/penguin/YKoL7e0b41wIerWU6PA6x_7fcafa06db85466e9864c8f006cb13a7.jpg","title":"Wan-2.2 Animate Replace"},{"category":"audio-to-video","description":"Wan-S2V is a video model that generates high-quality videos from static images and audio, with realistic facial expressions, body movements, and professional camera work for film and television applications","endpoint_id":"fal-ai/wan/v2.2-14b/speech-to-video","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt used for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":80,"description":"Number of frames to generate. Must be between 40 to 120, (must be multiple of 4).","enum":null,"is_list":false,"max":120,"media_kind":null,"min":40,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The URL of the audio file.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Alibaba","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.20 per video second for 720p, $0.15 per video second for 580p, $0.10 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-08-27T03:34:19.544000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92da/lZ3wuzCEnyWGYXU79XYYR_HEKI5ejC.png","title":"Wan-2.2 Speech-to-Video 14B"},{"category":"image-to-video","description":"Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding","endpoint_id":"fal-ai/wan/v2.2-5b/image-to-video","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (580p or 720p).","enum":["580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":40,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"","published_at":"2025-07-30T06:39:13.161000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Wan v2.2 5B"},{"category":"text-to-image","description":"Wan 2.2's 5B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail","endpoint_id":"fal-ai/wan/v2.2-5b/text-to-image","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":40,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":2,"description":"Shift value for the image. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the output image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2025-08-05T21:53:55.050000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9393/PX0OYV5MdhxuuwnGazvKO_UreaOWUg.png","title":"Wan"},{"category":"text-to-video","description":"Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding","endpoint_id":"fal-ai/wan/v2.2-5b/text-to-video","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (580p or 720p).","enum":["580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":40,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"","published_at":"2025-07-28T20:48:02.539000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Wan v2.2 5B"},{"category":"text-to-video","description":"Wan 2.2's 5B distill model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding","endpoint_id":"fal-ai/wan/v2.2-5b/text-to-video/distill","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (580p or 720p).","enum":["580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":40,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":1,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"","published_at":"2025-08-06T17:34:42.197000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a44/U-ajdfZ46XZM-a2guidNK_vSP2SAON.png","title":"Wan"},{"category":"text-to-video","description":"Wan 2.2's 5B FastVideo model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding","endpoint_id":"fal-ai/wan/v2.2-5b/text-to-video/fast-wan","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (580p or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":0,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.025 per video for 720p, $0.01875 per video for 580p, $0.0125 per video for 480p.","published_at":"2025-08-05T23:59:17.192000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92cc/Y-jQHC5zfMnRI6aiLIxIw_ePJVrFgh.png","title":"Wan"},{"category":"image-to-image","description":"Wan 2.2's 14B model edit high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail","endpoint_id":"fal-ai/wan/v2.2-a14b/image-to-image","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.5,"description":"Denoising strength. 1.0 = fully remake; 0.0 = preserve original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"Aspect ratio of the generated image. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":2,"description":"Shift","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":null,"description":"Image Size","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the output image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"image","output_props":["image","seed","prompt"],"pricing":"","published_at":"2025-09-03T07:19:12.410000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Wan"},{"category":"image-to-video","description":"fal-ai/wan/v2.2-A14B/image-to-video","endpoint_id":"fal-ai/wan/v2.2-a14b/image-to-video","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":3.5,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":1,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"URL of the end image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-07-28T15:58:39.979000+00:00","thumbnail":"https://v3.fal.media/files/penguin/xWl1TIQn-uRe7BsctByJk_3e01d1a4f7ff488c9483be0d81f5a3cc.jpg","title":"Wan v2.2 A14B"},{"category":"image-to-video","description":"Wan-2.2 image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and images. This endpoint supports LoRAs made for Wan 2.2","endpoint_id":"fal-ai/wan/v2.2-a14b/image-to-video/lora","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":1,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"[]","description":"LoRA weights to be used in the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"If true, the video will be reversed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":null,"description":"URL of the end image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"","published_at":"2025-08-07T12:44:59.464000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9225/7ePaxzuYYt6ktoZnFABlb_e8tKm9D8.png","title":"Wan v2.2 A14B Image-to-Video A14B with LoRAs"},{"category":"image-to-video","description":"Wan-2.2 Turbo image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.","endpoint_id":"fal-ai/wan/v2.2-a14b/image-to-video/turbo","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":null,"description":"URL of the end image.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.10 per video for 720p, $0.075 per video for 580p, $0.05 per video for 480p.","published_at":"2025-07-31T18:03:47.684000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-1.jpg","title":"Wan"},{"category":"text-to-image","description":"Wan 2.2's 14B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail","endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-image","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":2,"description":"Shift value for the image. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2025-08-05T21:53:20.379000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","title":"Wan"},{"category":"text-to-image","description":"Wan 2.2's 14B model with LoRA support generates high-fidelity images with enhanced prompt alignment, style adaptability.","endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-image/lora","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":2,"description":"Shift value for the image. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"[]","description":"LoRA weights to be used in the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"If true, the video will be reversed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"},{"default":"square_hd","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the output image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"image","output_props":["seed","image"],"pricing":"","published_at":"2025-08-05T23:56:14.535000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d1/Mh651J-EeTKoLefQJk9ZJ_4hQqmZ5G.png","title":"Wan v2.2 A14B Text-to-Image A14B with LoRAs"},{"category":"text-to-video","description":"Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.","endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-video","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":1,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-07-28T16:14:33.355000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","title":"Wan-2.2 Text-to-Video A14B"},{"category":"text-to-video","description":"Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. This endpoint supports LoRAs made for Wan 2.2.","endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-video/lora","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":1,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":"[]","description":"LoRA weights to be used in the inference.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":false,"description":"If true, the video will be reversed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reverse_video","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"","published_at":"2025-08-07T12:45:10.109000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d5/7rPaGC8n8fwRzpR5f1LXG_A7RAUQgT.png","title":"Wan-2.2 Text-to-Video A14B with LoRAs"},{"category":"text-to-video","description":"Wan-2.2 turbo text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.","endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-video/turbo","family":"Wan 2.2","inputs":[{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video (16:9 or 9:16).","enum":["16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.10 per video for 720p, $0.075 per video for 580p, $0.05 per video for 480p.","published_at":"2025-07-31T18:01:55.359000+00:00","thumbnail":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","title":"Wan"},{"category":"video-to-video","description":"Wan-2.2 video-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and source videos.","endpoint_id":"fal-ai/wan/v2.2-a14b/video-to-video","family":"Wan 2.2","inputs":[{"default":null,"description":"URL of the input video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"The text prompt to guide video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.9,"description":"Strength of the video transformation. A value of 1.0 means the output will be completely based on the prompt, while a value of 0.0 means the output will be identical to the input video.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":81,"description":"Number of frames to generate. Must be between 17 to 161 (inclusive).","enum":null,"is_list":false,"max":161,"media_kind":null,"min":17,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":16,"description":"Frames per second of the generated video. Must be between 4 to 60. When using interpolation and `adjust_fps_for_interpolation` is set to true (default true,) the final FPS will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If `adjust_fps_for_interpolation` is set to false, this value will be used as-is.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":"","description":"Negative prompt for video generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the generated video (480p, 580p, or 720p).","enum":["480p","580p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"auto","description":"Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input video.","enum":["auto","16:9","9:16","1:1"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":27,"description":"Number of inference steps for sampling. Higher values give better quality but take longer.","enum":null,"is_list":false,"max":40,"media_kind":null,"min":2,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":false,"description":"If set to true, input data will be checked for safety before processing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"If set to true, output video will be checked for safety after generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_output_safety_checker","required":false,"type":"boolean"},{"default":false,"description":"Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"regular","description":"Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":3.5,"description":"Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":4,"description":"Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale_2","required":false,"type":"number"},{"default":5,"description":"Shift value for the video. Must be between 1.0 and 10.0.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"shift","required":false,"type":"number"},{"default":"film","description":"The model to use for frame interpolation. If None, no interpolation is applied.","enum":["none","film","rife"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"interpolator_model","required":false,"type":"enum"},{"default":1,"description":"Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":0,"multiline":false,"name":"num_interpolated_frames","required":false,"type":"integer"},{"default":true,"description":"If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"adjust_fps_for_interpolation","required":false,"type":"boolean"},{"default":"high","description":"The quality of the output video. Higher quality means better visual quality but larger file size.","enum":["low","medium","high","maximum"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_quality","required":false,"type":"enum"},{"default":"balanced","description":"The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size.","enum":["fast","balanced","small"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"video_write_mode","required":false,"type":"enum"},{"default":false,"description":"If true, the video will be resampled to the passed frames per second. If false, the video will not be resampled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resample_fps","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","prompt"],"pricing":"Your request will cost $0.08 per video second for 720p, $0.06 per video second for 580p, $0.04 per video second for 480p. Video seconds are calculated at 16 frames per second.","published_at":"2025-08-02T02:30:21.079000+00:00","thumbnail":"https://v3.fal.media/files/kangaroo/fRLY4F3IQ1P3DwmVR8WUO_Mmzbg7vdKVmIAsxNycTbw_4a43f046e5be4a97b45a98320ff47bf3.jpg","title":"Wan"},{"category":"image-to-image","description":"Transform and edit existing images with text-guided instructions using the WAN 2.7 model for creative image manipulation.","endpoint_id":"fal-ai/wan/v2.7/edit","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired image edit. Supports Chinese and English.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for editing (1-4 images required). Order matters: reference them as image 1, image 2, image 3, image 4 in the prompt.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"Output image size. Uses fal image size presets or explicit dimensions and is converted to DashScope size format.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-4).","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Enable DashScope prompt expansion. Supported only for image edit mode.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated images.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-04-01T12:21:58.544000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a948161/E43snBsqtEWRB2KGM6723_8b2971637e504a00b4bcf2cec7d544b6.jpg","title":"Wan"},{"category":"video-to-video","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","endpoint_id":"fal-ai/wan/v2.7/edit-video","family":"Wan 2.7","inputs":[{"default":null,"description":"Editing instruction or style transfer description.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input video to edit. Format: MP4, MOV. Duration: 2-10s. Max 100 MB.\n\nMax file size: 100.0MB, Min duration: 2s, Max duration: 10s, Timeout: 30.0s","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Reference image URL for reference-based editing.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Aspect ratio of the generated video. If not provided, uses the aspect ratio of the input video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":0,"description":"Output video duration in seconds. Default 0 means match input video duration. When set (2-10), truncates from the start.","enum":[0,2,3,4,5,6,7,8,9,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"auto","description":"Audio handling. 'auto': model decides whether to regenerate audio. 'origin': preserve original audio from input video.","enum":["auto","origin"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"audio_setting","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","actual_prompt","seed"],"pricing":"","published_at":"2026-03-28T20:00:01.187000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94047a/Ji7eQ_y708vNP0EYe1FoP_076a3220a9c348c29eada5ca7d5946f1.jpg","title":"Wan"},{"category":"image-to-video","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","endpoint_id":"fal-ai/wan/v2.7/image-to-video","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired video. Max 5000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Max 20 MB.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"URL of the last frame image for first-and-last-frame-to-video. Same constraints as image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"end_image_url","required":false,"type":"string"},{"default":null,"description":"URL of a video clip to continue from. Format: MP4, MOV. Duration: 2-10s. Max 100 MB. Cannot be combined with image_url.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":false,"type":"string"},{"default":null,"description":"URL of driving audio. Supports WAV and MP3. Duration: 2-30s. Max 15 MB.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":false,"type":"string"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (2-15).","enum":[2,3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Content to avoid in the video. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Enable intelligent prompt rewriting.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","actual_prompt","seed"],"pricing":"Your request will cost $0.1 per second for 720p resolution. For 1080p your request will cost $0.15 per second.","published_at":"2026-03-28T19:58:40.182000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94048a/7oM_ro6v_fh2pGHvBbpyc_9db05a8e25034dcbb16db5192560d4af.jpg","title":"Wan"},{"category":"image-to-image","description":"Edit and transform images using text instructions with the WAN 2.7 Pro model for precise, professional-grade image modifications.","endpoint_id":"fal-ai/wan/v2.7/pro/edit","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired image edit. Supports Chinese and English.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for editing (1-4 images required). Order matters: reference them as image 1, image 2, image 3, image 4 in the prompt.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"Output image size. Uses fal image size presets or explicit dimensions and is converted to DashScope size format.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-4).","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Enable DashScope prompt expansion. Supported only for image edit mode.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated images.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed"],"pricing":"","published_at":"2026-04-01T12:24:21.597000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94816f/BhHA2kmKyAQ8vJxw_HPQ4_2b4b35f0fbb0449195d84178ba988112.jpg","title":"Wan"},{"category":"text-to-image","description":"Generate premium-quality images from text prompts using the enhanced WAN 2.7 Pro model with superior detail and composition.","endpoint_id":"fal-ai/wan/v2.7/pro/text-to-image","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired output. Supports Chinese and English.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"Output image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-5).","enum":null,"is_list":false,"max":5,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated images.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","generated_text","seed"],"pricing":"","published_at":"2026-04-01T12:18:29.243000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94814a/vKQfFX-pXcXv4MDvgtybu_d79aaa7e8534459281ac0bb474872f4b.jpg","title":"Wan"},{"category":"image-to-video","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","endpoint_id":"fal-ai/wan/v2.7/reference-to-video","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired video. Max 5000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference image URLs for character/object appearance. Pass multiple images for multi-subject generation. Max 20 MB each.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":false,"type":"string"},{"default":null,"description":"Reference video URLs for character/object appearance and motion. Pass multiple videos for multi-subject generation. Max 100 MB each.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"reference_video_urls","required":false,"type":"string"},{"default":null,"description":"Content to avoid in the video. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (2-10).","enum":[2,3,4,5,6,7,8,9,10],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"When true, enables intelligent multi-shot segmentation. When false (default), generates a single continuous shot.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_shots","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","video","actual_prompt"],"pricing":"Your request will cost $0.10 per second. When video inputs are provided, billing duration is calculated as input video duration + output video duration. For example, an 8s input video with a 3s output will be billed for 11 seconds ($1.10).","published_at":"2026-03-28T20:44:41.245000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a940488/7aXOy6uHTo2EHtaZX89Uj_f2a95842752d4ef999d2b00006960480.jpg","title":"Wan 2.7 Reference to Video"},{"category":"text-to-image","description":"Generate high-quality images from text prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.","endpoint_id":"fal-ai/wan/v2.7/text-to-image","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired output. Supports Chinese and English.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"Output image size.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-5).","enum":null,"is_list":false,"max":5,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated images.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","generated_text","seed"],"pricing":"","published_at":"2026-04-01T12:19:40.609000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a948152/0UucVYSOBXiyibwSyN3HT_38400743f04344a5b25b1cd9b551a625.jpg","title":"Wan"},{"category":"text-to-video","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","endpoint_id":"fal-ai/wan/v2.7/text-to-video","family":"Wan 2.7","inputs":[{"default":null,"description":"Text prompt describing the desired video. Max 5000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of driving audio. Supports WAV and MP3. Duration: 3-30s. Max 15 MB. If not provided, the model auto-generates matching background music.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Output video resolution tier.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":5,"description":"Output video duration in seconds (2-15).","enum":[2,3,4,5,6,7,8,9,10,11,12,13,14,15],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"Content to avoid in the video. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Enable intelligent prompt rewriting.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","seed","actual_prompt"],"pricing":"Your request will cost $0.1 per second for 720p resolution. For 1080p your request will cost $0.15 per second.","published_at":"2026-03-28T20:45:33.782000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a94047b/ktfxD5Hs3lGJdXwk7FurU_856b1abaad064b23bb2ae7dee66cf2f3.jpg","title":"Wan Text to Video"},{"category":"speech-to-text","description":"[Experimental] Whisper v3 Large -- but optimized by our inference wizards. Same WER, double the performance!","endpoint_id":"fal-ai/wizper","family":"Wizper","inputs":[{"default":null,"description":"URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"transcribe","description":"Task to perform on the audio file. Either transcribe or translate.","enum":["transcribe","translate"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"task","required":false,"type":"enum"},{"default":"en","description":"Language of the audio file.\n        If translate is selected as the task, the audio will be translated to\n        English, regardless of the language selected. If `None` is passed,\n        the language will be automatically detected. This will also increase\n        the inference time.","enum":["af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":"segment","description":"Level of the chunks to return.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"chunk_level","required":false,"type":"string"},{"default":29,"description":"Maximum speech segment duration in seconds before splitting.","enum":null,"is_list":false,"max":29,"media_kind":null,"min":10,"multiline":false,"name":"max_segment_len","required":false,"type":"integer"},{"default":true,"description":"Whether to merge consecutive chunks. When enabled, chunks are merged if their combined duration does not exceed max_segment_len.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"merge_chunks","required":false,"type":"boolean"},{"default":"3","description":"Version of the model to use. All of the models are the Whisper large variant.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"version","required":false,"type":"string"}],"lab":"","output_kind":"json","output_props":["chunks","text","languages"],"pricing":"","published_at":"2024-04-08T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/wizper.webp","title":"Wizper (Whisper v3 -- fal.ai edition)"},{"category":"audio-to-audio","description":"FFMPEG Utility for Audio Compression","endpoint_id":"fal-ai/workflow-utilities/audio-compressor","family":"","inputs":[{"default":null,"description":"URL of the audio file to compress","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":-18,"description":"Threshold level in dB above which compression is applied (-60 to 0)","enum":null,"is_list":false,"max":0,"media_kind":null,"min":-60,"multiline":false,"name":"threshold","required":false,"type":"number"},{"default":3,"description":"Compression ratio (1 = no compression, higher = more compression)","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"ratio","required":false,"type":"number"},{"default":5,"description":"Attack time in milliseconds (how fast compression starts)","enum":null,"is_list":false,"max":2000,"media_kind":null,"min":0.01,"multiline":false,"name":"attack","required":false,"type":"number"},{"default":50,"description":"Release time in milliseconds (how fast compression stops)","enum":null,"is_list":false,"max":9000,"media_kind":null,"min":0.01,"multiline":false,"name":"release","required":false,"type":"number"},{"default":8,"description":"Makeup gain in dB to compensate for volume reduction","enum":null,"is_list":false,"max":64,"media_kind":null,"min":0,"multiline":false,"name":"makeup","required":false,"type":"number"},{"default":2.83,"description":"Knee width in dB for soft knee compression (0 = hard knee)","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"knee","required":false,"type":"number"},{"default":"192k","description":"Output audio bitrate","enum":["128k","192k","256k","320k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_bitrate","required":false,"type":"enum"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-02-05T16:00:02.325000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d4636/KrltA9CgCSERiJeQDn5YE_eaced6c54cd140deb36a1c2804e1f935.png","title":"Workflow Utilities Audio Compressor"},{"category":"video-to-video","description":"Add automatic subtitles to videos","endpoint_id":"fal-ai/workflow-utilities/auto-subtitle","family":"","inputs":[{"default":null,"description":"URL of the video file to add automatic subtitles to","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"en","description":"Language code for transcription (e.g., 'en', 'es', 'fr', 'de', 'it', 'pt', 'nl', 'ja', 'zh', 'ko') or 3-letter ISO code (e.g., 'eng', 'spa', 'fra')","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"language","required":false,"type":"string"},{"default":"Montserrat","description":"Any Google Font name from fonts.google.com (e.g., 'Montserrat', 'Poppins', 'BBH Sans Hegarty')","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_name","required":false,"type":"string"},{"default":100,"description":"Font size for subtitles (TikTok style uses larger text)","enum":null,"is_list":false,"max":150,"media_kind":null,"min":20,"multiline":false,"name":"font_size","required":false,"type":"integer"},{"default":"bold","description":"Font weight (TikTok style typically uses bold or black)","enum":["normal","bold","black"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_weight","required":false,"type":"enum"},{"default":"white","description":"Subtitle text color for non-active words","enum":["white","black","red","green","blue","yellow","orange","purple","pink","brown","gray","cyan","magenta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"font_color","required":false,"type":"enum"},{"default":"purple","description":"Color for the currently speaking word (karaoke-style highlight)","enum":["white","black","red","green","blue","yellow","orange","purple","pink","brown","gray","cyan","magenta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"highlight_color","required":false,"type":"enum"},{"default":3,"description":"Text stroke/outline width in pixels (0 for no stroke)","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"stroke_width","required":false,"type":"integer"},{"default":"black","description":"Text stroke/outline color","enum":["black","white","red","green","blue","yellow","orange","purple","pink","brown","gray","cyan","magenta"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"stroke_color","required":false,"type":"enum"},{"default":"none","description":"Background color behind text ('none' or 'transparent' for no background)","enum":["black","white","red","green","blue","yellow","orange","purple","pink","brown","gray","cyan","magenta","none","transparent"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"enum"},{"default":0,"description":"Background opacity (0.0 = fully transparent, 1.0 = fully opaque)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"background_opacity","required":false,"type":"number"},{"default":"bottom","description":"Vertical position of subtitles","enum":["top","center","bottom"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"position","required":false,"type":"enum"},{"default":75,"description":"Vertical offset in pixels (positive = move down, negative = move up)","enum":null,"is_list":false,"max":200,"media_kind":null,"min":-200,"multiline":false,"name":"y_offset","required":false,"type":"integer"},{"default":3,"description":"Maximum number of words per subtitle segment. Use 1 for single-word display, 2-3 for short phrases, or 8-12 for full sentences.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"words_per_subtitle","required":false,"type":"integer"},{"default":true,"description":"Enable animation effects for subtitles (bounce style entrance)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_animation","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video","transcription_metadata","subtitle_count","words","transcription"],"pricing":"","published_at":"2025-11-04T14:48:45.210000+00:00","thumbnail":"https://v3b.fal.media/files/b/zebra/-R1ZjOAerDNnOUrhWNeUv_22f1d53a808040bd99ec01459e4f9547.jpg","title":"Workflow Utilities Auto Subtitle"},{"category":"video-to-video","description":"FFMPEG Utility for Blending Videos","endpoint_id":"fal-ai/workflow-utilities/blend-video","family":"","inputs":[{"default":null,"description":"URL of the top layer video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"top_video_url","required":true,"type":"string"},{"default":null,"description":"URL of the bottom layer video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"bottom_video_url","required":true,"type":"string"},{"default":"overlay","description":"Blend mode to use for combining the videos","enum":["addition","average","burn","darken","difference","divide","dodge","exclusion","grainextract","grainmerge","hardlight","lighten","multiply","negation","normal","overlay","phoenix","pinlight","reflect","screen","softlight","subtract","vividlight"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"blend_mode","required":false,"type":"enum"},{"default":1,"description":"Opacity of the top layer (0.0-1.0)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"opacity","required":false,"type":"number"},{"default":true,"description":"End output when the shortest input ends","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"shortest","required":false,"type":"boolean"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-02-05T16:03:39.149000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d4652/nA4J52mF2zpuS-is8vBDo_b537d210dc294adb934ded2b30a61477.png","title":"Workflow Utilities Blend Video"},{"category":"image-to-image","description":"FFMPEG Untility for Extracting nth Frame","endpoint_id":"fal-ai/workflow-utilities/extract-nth-frame","family":"","inputs":[{"default":null,"description":"URL of the video file to extract frames from","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":12,"description":"Extract every Nth frame (e.g., 3 = every 3rd frame, 12 = every 12th frame)","enum":null,"is_list":false,"max":300,"media_kind":null,"min":1,"multiline":false,"name":"frame_interval","required":false,"type":"integer"},{"default":"png","description":"Output format for extracted frames","enum":["png","jpg","jpeg","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":100,"description":"Maximum number of frames to extract","enum":null,"is_list":false,"max":500,"media_kind":null,"min":1,"multiline":false,"name":"max_frames","required":false,"type":"integer"},{"default":95,"description":"Quality for jpg/webp output (1-100)","enum":null,"is_list":false,"max":100,"media_kind":null,"min":1,"multiline":false,"name":"quality","required":false,"type":"integer"}],"lab":"","output_kind":"images","output_props":["images","frame_count"],"pricing":"","published_at":"2026-02-05T16:18:10.236000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d465c/id_c9UTaloHxuWrFq0Z5h_6109c657124c4223b471113b46dcf127.png","title":"Workflow Utilities Extract Nth Frame"},{"category":"audio-to-audio","description":"FFMPEG Utility for Impulse Response","endpoint_id":"fal-ai/workflow-utilities/impulse-response","family":"","inputs":[{"default":null,"description":"URL of the main audio file to process","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"URL of the impulse response WAV file (reverb/effect profile)","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"impulse_response_url","required":true,"type":"string"},{"default":0.7,"description":"Level of the original (dry) signal in the mix (0.0-1.0)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"dry_level","required":false,"type":"number"},{"default":0.3,"description":"Level of the processed (wet) signal in the mix (0.0-1.0)","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"wet_level","required":false,"type":"number"},{"default":-18,"description":"Target integrated loudness in LUFS (typically -24 to -14)","enum":null,"is_list":false,"max":0,"media_kind":null,"min":-70,"multiline":false,"name":"loudness_i","required":false,"type":"number"},{"default":8,"description":"Loudness Range target in LU (typically 5-15)","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"loudness_lra","required":false,"type":"number"},{"default":-1.5,"description":"Maximum true peak in dBTP (typically -2 to -1)","enum":null,"is_list":false,"max":0,"media_kind":null,"min":-10,"multiline":false,"name":"loudness_tp","required":false,"type":"number"},{"default":"192k","description":"Output audio bitrate","enum":["128k","192k","256k","320k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_bitrate","required":false,"type":"enum"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-02-05T16:20:17.271000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d46b5/2lU5oAEfVNGmUFdiop4zR_5b9e09282e294a7d8f2cbdb96ca81b5a.png","title":"Workflow Utilities Impulse Response"},{"category":"unknown","description":"ffmpeg utility to interleave videos","endpoint_id":"fal-ai/workflow-utilities/interleave-video","family":"","inputs":[{"default":null,"description":"List of video URLs to interleave in order","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_urls","required":true,"type":"string"},{"default":null,"description":"Frame rate of the interleaved output video. When set, all interleaved frames are emitted at this rate, so lower values produce a longer output while higher values produce a shorter, faster one. Leave unset to preserve the legacy behavior, which derives the output rate from the input videos (this can yield non-standard rates such as 384.0098).","enum":null,"is_list":false,"max":120,"media_kind":null,"min":1,"multiline":false,"name":"frames_per_second","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-01-27T17:40:26.521000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87987b/4FBs4s-6F9ng4C6B3e-4i_d97b1dd479a045cfa4b0e8d3a1ed39e1.jpg","title":"Workflow Utilities Interleave Video"},{"category":"workflow","description":"Choose the Nth image from an image URL list for workflows.","endpoint_id":"fal-ai/workflow-utilities/pick-image-by-index","family":"","inputs":[{"default":null,"description":"Array of image URLs to select from","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"1-based position of the image to return. Value 1 returns the first image, 2 returns the second, and so on.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"index","required":true,"type":"integer"},{"default":"first-image","description":"Behavior when `index` exceeds the length of `image_urls`. When `first-image`, returns the first image in the array. When `last-image`, returns the last image in the array. This input has no effect when `index` is within range, when `index` is below 1, or when `image_urls` is empty (the latter two cases still return validation errors). Default is `first-image`.","enum":["first-image","last-image"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"fallback_index","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images","image"],"pricing":"","published_at":"2026-04-29T18:49:30.919000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a983b72/2jJcszb7aMncZ6AKlkBM-_8378b055ba694a09a3bc9a2bea5f60e9.jpg","title":"Workflow Utilities Pick Image By Index"},{"category":"video-to-video","description":"FFMPEG Utility to Reverse Videos","endpoint_id":"fal-ai/workflow-utilities/reverse-video","family":"","inputs":[{"default":null,"description":"URL of the video file to reverse","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-02-19T14:16:07.199000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8f1c4d/wJYqiAHfB8xgLi42ui68x_be04f1afc8034fc29b4c1b9cafd413b6.png","title":"Workflow Utilities Reverse Video"},{"category":"video-to-video","description":"FFMPEG Utilities to Scale Videos","endpoint_id":"fal-ai/workflow-utilities/scale-video","family":"","inputs":[{"default":null,"description":"URL of the video file to scale/resize. Height and Width of the video must be even numbers for compatibility with video codecs.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Target width in pixels. If only width is provided, height is auto-calculated to preserve aspect ratio. At least one of width or height must be provided.","enum":null,"is_list":false,"max":7680,"media_kind":null,"min":2,"multiline":false,"name":"width","required":false,"type":"integer"},{"default":null,"description":"Target height in pixels. If only height is provided, width is auto-calculated to preserve aspect ratio. At least one of width or height must be provided.","enum":null,"is_list":false,"max":4320,"media_kind":null,"min":2,"multiline":false,"name":"height","required":false,"type":"integer"},{"default":"stretch","description":"Scaling mode. 'stretch' scales the video to the exact target dimensions (may distort aspect ratio). 'pad' scales to fit within the target dimensions while preserving aspect ratio, then pads with the chosen color to fill the remaining space (letterbox/pillarbox). 'crop' scales to cover the target dimensions while preserving aspect ratio, then center-crops to the exact target size.","enum":["stretch","pad","crop"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"mode","required":false,"type":"enum"},{"default":"black","description":"Padding color when mode is 'pad'. Ignored for other modes.","enum":["black","white","red","green","blue","gray"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pad_color","required":false,"type":"enum"},{"default":"libx264","description":"Video codec to use for encoding. libx264 (H.264) is widely compatible, libx265 (H.265/HEVC) offers better compression.","enum":["libx264","libx265"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"codec","required":false,"type":"enum"},{"default":"fast","description":"Encoding speed preset. Slower presets give better compression but take longer.","enum":["ultrafast","fast","medium","slow"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preset","required":false,"type":"enum"},{"default":18,"description":"Constant Rate Factor for quality (0-51). Lower values mean better quality and larger files. 18 is visually lossless for most content.","enum":null,"is_list":false,"max":51,"media_kind":null,"min":0,"multiline":false,"name":"crf","required":false,"type":"integer"}],"lab":"","output_kind":"video","output_props":["video","original_width","scaled_width","scaled_height","original_height"],"pricing":"","published_at":"2026-02-16T16:05:17.779000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8eb99a/kyzJ7WEk8DJzfmZelPiHR_330f8652ee854c3c8b1323e6d2f6fe86.png","title":"Workflow Utilities Scale Video"},{"category":"video-to-video","description":"FFMPEG Utility for Trim Video","endpoint_id":"fal-ai/workflow-utilities/trim-video","family":"","inputs":[{"default":null,"description":"URL of the video file to trim","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":1,"description":"Start time in seconds","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_time","required":false,"type":"number"},{"default":null,"description":"End time in seconds. If not provided, uses duration instead.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"end_time","required":false,"type":"number"},{"default":2,"description":"Duration in seconds from start_time. Ignored if end_time is provided.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"duration","required":false,"type":"number"}],"lab":"","output_kind":"video","output_props":["video","trimmed_duration","original_duration"],"pricing":"","published_at":"2026-02-11T09:08:18.218000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e11aa/xIakBiV0_r7glqzDfsJ2k_775564bd78674a0fbda370d0faea9e58.jpg","title":"Workflow Utilities Trim Video"},{"category":"vision","description":"Predict whether an image is NSFW or SFW.","endpoint_id":"fal-ai/x-ailab/nsfw","family":"","inputs":[{"default":null,"description":"List of image URLs to check. If more than 10 images are provided, only the first 10 will be checked.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"","output_kind":"json","output_props":["has_nsfw_concepts"],"pricing":"","published_at":"2025-07-28T09:37:20.844000+00:00","thumbnail":"https://v3.fal.media/files/monkey/Tja6xudNPajR7Wiv3CI2z_6fa01860226940cbab39842db772f7da.jpg","title":"NSFW Checker"},{"category":"training","description":"Train LoRAs on Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.","endpoint_id":"fal-ai/z-image-trainer","family":"Z-Image","inputs":[{"default":null,"description":"URL to zip archive with images of a consistent style. Try to use at least 10 images, although more is better.\n\n    The zip can also contain a text file for each image. The text file should be named:\n    ROOT.txt\n    For example:\n    photo.txt\n\n    This text file can be used to specify the edit instructions for the image pair.\n\n    If no text file is provided, the default_caption will be used.\n\n    If no default_caption is provided, the training will fail.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":1000,"description":"Total number of training steps.","enum":null,"is_list":false,"max":10000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":0.0001,"description":"Learning rate applied to trainable parameters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":"balanced","description":"Type of training to perform. Use 'content' to focus on the content of the images, 'style' to focus on the style of the images, and 'balanced' to focus on a combination of both.","enum":["content","style","balanced"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"training_type","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"Your request will cost $2.26 per 1000-step training run. It scales per step, so a 2000-step training run costs $4.52. Note: 100 steps is the minimum step count, which will cost $0.226.","published_at":"2025-12-03T19:09:57.722000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a84daae/ubfu5r0bOZVRBN1_V5AJY_fb0dc5421f4e413ba4a8c94c2e043225.jpg","title":"Z Image Trainer"},{"category":"training","description":"Fast LoRA trainer for Z-Image-Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.","endpoint_id":"fal-ai/z-image-turbo-trainer-v2","family":"Z-Image","inputs":[{"default":null,"description":"URL to the input data zip archive.\n\n        The zip should contain pairs of images and corresponding captions.\n\n        The images should be named: ROOT.EXT. For example: 001.jpg\n\n        The corresponding captions should be named: ROOT.txt. For example: 001.txt\n\n        If no text file is provided for an image, the default_caption will be used.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_data_url","required":true,"type":"string"},{"default":2000,"description":"Number of steps to train for","enum":null,"is_list":false,"max":40000,"media_kind":null,"min":10,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":null,"description":"Default caption to use when caption files are missing. If None, missing captions will cause an error.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"default_caption","required":false,"type":"string"},{"default":0.0005,"description":"Learning rate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"learning_rate","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"Your request will cost $0.85 per 1000-step training run. It scales per step, so a 2000-step training run will cost $1.70.","published_at":"2026-01-24T03:10:13.337000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8b9eef/T4yyPE_lpuMlcnmqlF8Ns_ab635223ffad4b2cb49d48d926eae60f.jpg","title":"Z Image Turbo Trainer V2"},{"category":"text-to-image","description":"Z-Image is the foundation model of the Z- Image family, engineered for good quality, robust generative diversity, broad stylistic coverage, and precise prompt adherence.","endpoint_id":"fal-ai/z-image/base","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2026-01-27T17:24:16.384000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1871/Kxq-m63uqtEhDgll_5W63_c53ec36259f8446495a23b09592f2f09.jpg","title":"Z Image Base"},{"category":"text-to-image","description":"LoRA endpoint for Z-Image, the foundation model of the Z- Image family.","endpoint_id":"fal-ai/z-image/base/lora","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"The guidance scale to use for the image generation.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":"","description":"The negative prompt to use for the image generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2026-01-27T17:26:38.446000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c1883/2G6Kn_ounoUBav_-ayY6k_0f72c0a77d9c4a14a38350dadc12806b.jpg","title":"Z Image Base Lora"},{"category":"text-to-image","description":"Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.","endpoint_id":"fal-ai/z-image/turbo","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-11-26T14:38:10.381000+00:00","thumbnail":"https://v3b.fal.media/files/b/koala/Pvji5sM6n6oNIo-p0Xsn__245f3d4eb5df4952aa80ec74f4afd7f2.jpg","title":"Z Image Turbo"},{"category":"image-to-image","description":"Generate images from text and edge, depth or pose images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.","endpoint_id":"fal-ai/z-image/turbo/controlnet","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for ControlNet generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.75,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_scale","required":false,"type":"number"},{"default":0,"description":"The start of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_start","required":false,"type":"number"},{"default":0.8,"description":"The end of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_end","required":false,"type":"number"},{"default":"none","description":"What kind of preprocessing to apply to the image, if any.","enum":["none","canny","depth","pose"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-07T20:51:56.573000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a85640c/fMxWAimqN7U67KxfCscKM_f4457852189f4fd98e05a47cae2f2baa.jpg","title":"Z Image Turbo Controlnet"},{"category":"image-to-image","description":"Generate images from text and edge, depth or pose images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.","endpoint_id":"fal-ai/z-image/turbo/controlnet/lora","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for ControlNet generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.75,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_scale","required":false,"type":"number"},{"default":0,"description":"The start of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_start","required":false,"type":"number"},{"default":0.8,"description":"The end of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_end","required":false,"type":"number"},{"default":"none","description":"What kind of preprocessing to apply to the image, if any.","enum":["none","canny","depth","pose"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preprocess","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-07T20:55:46.527000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a856427/T39BO4GLnxe-rM537HgrH_23724481e7574950ba6e3f4abb75e1b0.jpg","title":"Z Image Turbo Controlnet Lora"},{"category":"image-to-image","description":"Generate images from text and images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.","endpoint_id":"fal-ai/z-image/turbo/image-to-image","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Image-to-Image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.6,"description":"The strength of the image-to-image conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-07T20:35:23.324000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8563a8/ISfaZAiht16RGXWqoOU4h_13ac5a10d2b34c1db11dc85ee2d57014.jpg","title":"Z Image Turbo Image To Image"},{"category":"image-to-image","description":"Generate images from text and images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.","endpoint_id":"fal-ai/z-image/turbo/image-to-image/lora","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Image-to-Image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.6,"description":"The strength of the image-to-image conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-07T20:39:40.800000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8563c2/33_KzGSlJd9AyR7m8QZYv_bd0753469df54473a018265568b5fc44.jpg","title":"Z Image Turbo Image To Image Lora"},{"category":"image-to-image","description":"Generate images from text, an image and a mask using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.","endpoint_id":"fal-ai/z-image/turbo/inpaint","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Inpaint generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.75,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_scale","required":false,"type":"number"},{"default":0,"description":"The start of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_start","required":false,"type":"number"},{"default":0.8,"description":"The end of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_end","required":false,"type":"number"},{"default":null,"description":"URL of Mask for Inpaint generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":true,"type":"string"},{"default":1,"description":"The strength of the inpaint conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-18T16:14:23.744000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86d0c9/znBEfEDmFTeNP6Fm_dfGw_98585a0351414d37a69e4cf0c7f0305a.jpg","title":"Z Image Turbo Inpaint"},{"category":"image-to-image","description":"Generate images from text, an image, a mask and custom LoRA using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.","endpoint_id":"fal-ai/z-image/turbo/inpaint/lora","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of Image for Inpaint generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.75,"description":"The scale of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_scale","required":false,"type":"number"},{"default":0,"description":"The start of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_start","required":false,"type":"number"},{"default":0.8,"description":"The end of the controlnet conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"control_end","required":false,"type":"number"},{"default":null,"description":"URL of Mask for Inpaint generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":true,"type":"string"},{"default":1,"description":"The strength of the inpaint conditioning.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-18T16:19:58.658000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86d0e7/FSsTeoWO3HUk50Ba1ftXE_8546e152c771482c9b0b7a56fd1a352e.jpg","title":"Z Image Turbo Inpaint Lora"},{"category":"text-to-image","description":"Text-to-Image endpoint with LoRA support for Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.","endpoint_id":"fal-ai/z-image/turbo/lora","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"","published_at":"2025-12-01T21:00:30.834000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8499c8/NoYhi_0XiRWB_GyGXzXdh_c756d700b1a8445a90bcf47126bc8459.jpg","title":"Z Image Turbo Lora"},{"category":"text-to-image","description":"Generate seamlessly tiling photorealistic images from text using Z-Image Turbo","endpoint_id":"fal-ai/z-image/turbo/tiling","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image. Use 'auto' to match the input image size (or 1024x1024 if no image).","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of an image for image-to-image or inpainting. When provided without mask_image_url, performs image-to-image; with mask_image_url, performs inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"URL of a mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"},{"default":0.6,"description":"How much to transform the input image. Only used when image_url is provided.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":128,"description":"Tile size in latent space. Must be even (divisible by 2) for patchification. (64 = 512px, 128 = 1024px, 256 = 2048px).","enum":null,"is_list":false,"max":256,"media_kind":null,"min":32,"multiline":false,"name":"tile_size","required":false,"type":"integer"},{"default":64,"description":"Tile stride in latent space. Must be even (divisible by 2). (32 = 256px, 64 = 512px, 128 = 1024px).","enum":null,"is_list":false,"max":128,"media_kind":null,"min":16,"multiline":false,"name":"tile_stride","required":false,"type":"integer"},{"default":"both","description":"Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), 'vertical' (top-bottom only).","enum":["both","horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tiling_mode","required":false,"type":"enum"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"Your request will cost $0.02 per megapixel.","published_at":"2026-03-17T03:10:40.551000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a927a27/SYJj76y2BxFpBc6ySx7uj_5d9c07ca565e4fe6bdef800c186c176b.jpg","title":"Z-Image Turbo Seamless Tiling"},{"category":"text-to-image","description":"Generate seamlessly tiling photorealistic images from text using Z-Image Turbo and custom LoRA","endpoint_id":"fal-ai/z-image/turbo/tiling/lora","family":"Z-Image","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"square_hd","description":"The size of the generated image. Use 'auto' to match the input image size (or 1024x1024 if no image).","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":8,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":8,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"regular","description":"The acceleration level to use.","enum":["none","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":false,"description":"Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"URL of an image for image-to-image or inpainting. When provided without mask_image_url, performs image-to-image; with mask_image_url, performs inpainting.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"URL of a mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_image_url","required":false,"type":"string"},{"default":0.6,"description":"How much to transform the input image. Only used when image_url is provided.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":128,"description":"Tile size in latent space. Must be even (divisible by 2) for patchification. (64 = 512px, 128 = 1024px, 256 = 2048px).","enum":null,"is_list":false,"max":256,"media_kind":null,"min":32,"multiline":false,"name":"tile_size","required":false,"type":"integer"},{"default":64,"description":"Tile stride in latent space. Must be even (divisible by 2). (32 = 256px, 64 = 512px, 128 = 1024px).","enum":null,"is_list":false,"max":128,"media_kind":null,"min":16,"multiline":false,"name":"tile_stride","required":false,"type":"integer"},{"default":"both","description":"Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), 'vertical' (top-bottom only).","enum":["both","horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tiling_mode","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Alibaba","output_kind":"images","output_props":["images","seed","timings","has_nsfw_concepts","prompt"],"pricing":"Your request will cost $0.025 per megapixel.","published_at":"2026-03-17T03:13:51.642000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a927a46/r4_VKr5hjykY0b3VxLRdx_bdb953058bb14b5581ee39a4763b3697.jpg","title":"Z-Image Turbo Seamless Tiling Lora"},{"category":"text-to-audio","description":"Clone voice of any person and speak anything in their voice using zonos' voice cloning.","endpoint_id":"fal-ai/zonos","family":"","inputs":[{"default":null,"description":"The reference audio.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"reference_audio_url","required":true,"type":"string"},{"default":null,"description":"The content generated using cloned voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"}],"lab":"","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-02-14T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/Ben2/2VVmzf2y5GyRdFoof8BLu.webp","title":"Zonos-Audio-Clone"},{"category":"text-to-speech","description":"Zonos2 is a text-to-speech model that clones a voice from a short sample and speaks naturally across many languages.","endpoint_id":"fal-ai/zonos2","family":"Zonos","inputs":[{"default":null,"description":"Reference audio to clone the voice from.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"reference_audio_url","required":true,"type":"string"},{"default":"\"Fal\" is the fastest solution for your audio generation.","description":"Text to synthesize in the cloned voice.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":false,"type":"string"},{"default":"en_us","description":"Text-normalization language code. Supported: en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn, ko. Unsupported codes skip normalization.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"language","required":false,"type":"string"},{"default":null,"description":"Seed for reproducibility. Random when omitted.","enum":null,"is_list":false,"max":2147483647,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"True = closer voice match; False = more expressive.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"accurate_mode","required":false,"type":"boolean"},{"default":false,"description":"Mark the reference audio as having a clean background.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"clean_speaker_background","required":false,"type":"boolean"},{"default":1.15,"description":"Sampling temperature.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0,"description":"Nucleus sampling probability (0 disables).","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":0.18,"description":"Minimum-probability sampling threshold.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"min_p","required":false,"type":"number"},{"default":106,"description":"Top-k sampling cutoff (0 disables).","enum":null,"is_list":false,"max":2048,"media_kind":null,"min":0,"multiline":false,"name":"top_k","required":false,"type":"integer"},{"default":null,"description":"Maximum number of audio frames to generate. Defaults to the model context limit.","enum":null,"is_list":false,"max":6144,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Zyphra","output_kind":"audio","output_props":["audio","seed"],"pricing":"","published_at":"2026-06-16T19:33:10.497000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9e7f9a/QwGx_S5uNbkzNRXsMZpDw_c64a2dc8166b4688a78bc80bfdb53ed0.jpg","title":"Zonos2 Text to Speech"},{"category":"text-to-video","description":"Creates video with synchronized audio from text input. Grounded in Gemini's real-world knowledge, with improved physics understanding for more coherent motion and interaction.","endpoint_id":"google/gemini-omni-flash","family":"Gemini Omni Flash","inputs":[{"default":null,"description":"The text prompt describing the video you want to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":8,"description":"The duration of the generated video, in seconds.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":3,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"Billing is based on total token consumption. Tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.125 per second of video.","published_at":"2026-06-30T17:26:03.038000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa0649d/TFqtIbw6p_p4rMT-44N8X.jpg","title":"Gemini Omni Flash"},{"category":"video-to-video","description":"Edits generated video across multiple conversational turns while preserving scene coherence. Applies iterative changes through natural-language instructions without regenerating the full sequence from scratch.","endpoint_id":"google/gemini-omni-flash/edit","family":"Gemini Omni Flash","inputs":[{"default":null,"description":"A simple instruction describing the edit. Simple prompts work best; add \"Keep everything else the same.\" to preserve the rest of the scene. Voice editing is not supported.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the video to edit. Note: editing uploaded videos is not available for users in the European Economic Area (EEA), Switzerland, and the United Kingdom.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"Billing is based on total token consumption. Input tokens (text/audio/video) cost $1.875 per 1 million tokens. Output tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.13 per second of video.","published_at":"2026-06-30T17:26:09.799000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa064ab/KaPeBfk0q5Qc2axr3JX-k.jpg","title":"Gemini Omni Flash"},{"category":"image-to-video","description":"Animates a still image into video with audio. Extends a single frame into coherent motion, grounded in Gemini's physical understanding of how scenes and subjects behave.","endpoint_id":"google/gemini-omni-flash/image-to-video","family":"Gemini Omni Flash","inputs":[{"default":null,"description":"The text prompt describing how the image should be animated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input image to animate.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":8,"description":"The duration of the generated video, in seconds.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":3,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"Billing is based on total token consumption. Input tokens (text/audio/video) cost $1.875 per 1 million tokens. Output tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.13 per second of video.","published_at":"2026-06-30T17:26:14.875000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa064c4/0I6OScPBof7TKGPvufHPG.jpg","title":"Gemini Omni Flash"},{"category":"image-to-video","description":"Generates video with audio from combined multimodal references. Accepts text, images, audio, and video together as input to guide subject, motion, style, and sound in the output.","endpoint_id":"google/gemini-omni-flash/reference-to-video","family":"","inputs":[{"default":null,"description":"The text prompt describing the video. You can bind reference images to roles inline using tags like ``<IMAGE_REF_0>`` (see the Omni Flash prompt guide).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URLs of the reference images to incorporate into the video.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":8,"description":"The duration of the generated video, in seconds.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":3,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"Google","output_kind":"video","output_props":["video"],"pricing":"Billing is based on total token consumption. Input tokens (text/audio/video) cost $1.875 per 1 million tokens. Output tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.13 per second of video.","published_at":"2026-06-30T17:26:21.209000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa064be/vTTSwDN_rUlhGecz3iWdY.jpg","title":"Gemini Omni Flash"},{"category":"text-to-image","description":"Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.","endpoint_id":"google/nano-banana-2-lite","family":"Nano Banana Lite","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use \"auto\" to let the model decide based on the prompt.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Text tokens (per 1M): $0.3125 input, $1.875 output. Image tokens (per 1M): $0.3125 input, $37.50 output. Output images are generated at a fixed 1K (1024x1024px)","published_at":"2026-06-30T19:23:11.948000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa065ef/5nRcoeLuJhcbIysKu4EDf.jpg","title":"Nano Banana 2 Lite"},{"category":"text-to-image","description":"Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.","endpoint_id":"google/nano-banana-lite","family":"Nano Banana Lite","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use \"auto\" to let the model decide based on the prompt.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Text tokens (per 1M): $0.3125 input, $1.875 output. Image tokens (per 1M): $0.3125 input, $37.50 output. Output images are generated at a fixed 1K (1024x1024px)","published_at":"2026-06-30T17:49:15.712000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa065ef/5nRcoeLuJhcbIysKu4EDf.jpg","title":"Nano Banana Lite"},{"category":"image-to-image","description":"Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.","endpoint_id":"google/nano-banana-lite/edit","family":"Nano Banana Lite","inputs":[{"default":null,"description":"The prompt for image editing.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed for the random number generator.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8.","enum":["auto","21:9","16:9","3:2","4:3","5:4","1:1","4:5","3:4","2:3","9:16","4:1","1:4","8:1","1:8"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"4","description":"The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.","enum":["1","2","3","4","5","6"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"safety_tolerance","required":false,"type":"enum"},{"default":null,"description":"The URLs of the images to use for image-to-image generation or image editing.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":false,"type":"string"},{"default":"","description":"Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"system_prompt","required":false,"type":"string"},{"default":true,"description":"Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"limit_generations","required":false,"type":"boolean"},{"default":null,"description":"When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.","enum":["minimal","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"thinking_level","required":false,"type":"enum"}],"lab":"Google","output_kind":"images","output_props":["images","description"],"pricing":"Text tokens (per 1M): $0.3125 input, $1.875 output. Image tokens (per 1M): $0.3125 input, $37.50 output. Output images are generated at a fixed 1K (1024x1024px)","published_at":"2026-06-30T17:49:04.027000+00:00","thumbnail":"https://v3b.fal.media/files/b/0aa065ff/LYSxe7cVmkxjqJto2r6Qv.jpg","title":"Nano Banana Lite Edit"},{"category":"text-to-image","description":"Generate high-quality images, posters, and logos with Ideogram's latest V4.0q — producing crisp visuals with accurate text rendering, fine detail, and full creative control for polished, ready-to-use designs.","endpoint_id":"ideogram/v4","family":"Ideogram 4","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Medium","description":"Which model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.","enum":["None","Medium","Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expansion_model","required":false,"type":"enum"},{"default":"square_hd","description":"The resolution of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use. Faster speeds use fewer denoising steps.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","low","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"Your request will cost $0.0075 per megapixel in TURBO mode, $0.015 per megapixel in BALANCED mode, or $0.025 per megapixel in QUALITY mode. For example, a 2048 x 2048 image will cost $0.03, $0.06 or $0.10 based on the mode.","published_at":"2026-06-03T16:00:06.003000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9cb567/UOWMMlOcuBA-NRLAWnP2G_8e662a91cf494675a0f6a83852cdb6e1.jpg","title":"Ideogram V4.0 Text to Image"},{"category":"image-to-image","description":"Ideogram V4.0q Image-to-Image transforms an input image with a text prompt, restyling and reworking the composition while preserving its core structure for prompt-faithful, high-fidelity edits.","endpoint_id":"ideogram/v4/image-to-image","family":"Ideogram 4","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Medium","description":"Which model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.","enum":["None","Medium","Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expansion_model","required":false,"type":"enum"},{"default":"auto","description":"The output image size. Use 'auto' to match the input image size (capped at ~25MP, up to 8192px per side).","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use. Faster speeds use fewer denoising steps.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","low","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"URL of the input image for image-to-image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.8,"description":"How much to transform the input image. 1.0 ignores the input image entirely; lower values stay closer to it.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"}],"lab":"Ideogram","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"Your request will cost $0.0075 per megapixel in TURBO mode, $0.015 per megapixel in BALANCED mode, or $0.025 per megapixel in QUALITY mode. For example, a 2048 x 2048 image will cost $0.03, $0.06 or $0.10 based on the mode.","published_at":"2026-06-11T08:19:33.351000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dc0d8/Sk7dDmlNxtuNqrIC5PGqo_cb68a0ee29c44a729d67bd251546ba63.jpg","title":"Ideogram V4.0q Image to Image"},{"category":"image-to-image","description":"Ideogram V4.0q Image-to-Image LoRA applies a custom-trained LoRA on top of an input image, steering edits toward a specific style, subject, or brand identity while keeping the source composition intact.","endpoint_id":"ideogram/v4/image-to-image/lora","family":"Ideogram 4","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Medium","description":"Which model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.","enum":["None","Medium","Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expansion_model","required":false,"type":"enum"},{"default":"auto","description":"The output image size. Use 'auto' to match the input image size (capped at ~25MP, up to 8192px per side).","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use. Faster speeds use fewer denoising steps.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","low","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"URL of the input image for image-to-image generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.8,"description":"How much to transform the input image. 1.0 ignores the input image entirely; lower values stay closer to it.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Ideogram","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"Your request will cost $0.01125 per megapixel in TURBO mode, $0.0225 per megapixel in BALANCED mode, or $0.0375 per megapixel in QUALITY mode. For example, a 2048 x 2048 image will cost $0.045, $0.09 or $0.15 based on the mode.","published_at":"2026-06-11T08:40:12.382000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dc125/R5xvoF_mCJPgGY0qolsZN_b74e1684e9b14cd0b3fe2221fb4b3fe8.jpg","title":"Ideogram V4.0q Image to Image LoRA"},{"category":"text-to-image","description":"Generate high-quality images, posters, and logos with Ideogram's latest V4.0q using LoRA — producing crisp visuals with accurate text rendering, fine detail, and full creative control for polished, ready-to-use designs.","endpoint_id":"ideogram/v4/lora","family":"Ideogram 4","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Medium","description":"Which model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.","enum":["None","Medium","Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expansion_model","required":false,"type":"enum"},{"default":"square_hd","description":"The resolution of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use. Faster speeds use fewer denoising steps.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","low","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Ideogram","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"Your request will cost $0.01125 per megapixel in TURBO mode, $0.0225 per megapixel in BALANCED mode, or $0.0375 per megapixel in QUALITY mode. For example, a 2048 x 2048 image will cost $0.045, $0.09 or $0.15 based on the mode.","published_at":"2026-06-08T21:52:57.532000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d8504/vZt4MS5ALRjG0SPhvD7iC_36e62ea6ddaa4fb79692b0cd37fb9204.jpg","title":"Ideogram V4.0q Text to Image (LoRA)"},{"category":"image-to-image","description":"Ideogram V4.0q Tiling generates seamless, edge-matching textures and patterns that repeat infinitely in any direction, ideal for backgrounds, surfaces, and wallpapers.","endpoint_id":"ideogram/v4/tiling","family":"Ideogram 4","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Medium","description":"Which model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.","enum":["None","Medium","Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expansion_model","required":false,"type":"enum"},{"default":"square_hd","description":"The resolution of the generated seamlessly tileable image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use. Faster speeds use fewer denoising steps.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","low","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Optional URL of an image. When provided without `mask_url`, performs image-to-image tiling; with `mask_url`, performs inpainting tiling.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Optional URL of a mask image for inpainting tiling. White regions are regenerated, black regions are preserved. Requires `image_url`.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_url","required":false,"type":"string"},{"default":0.8,"description":"How much to transform the input image. Only used when `image_url` is provided.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"both","description":"Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), or 'vertical' (top-bottom only).","enum":["both","horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tiling_mode","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"Your request will cost $0.03 per megapixel in TURBO mode, $0.06 per megapixel in BALANCED mode, or $0.10 per megapixel in QUALITY mode.","published_at":"2026-06-11T08:39:43.049000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dc187/wgqbs05r1GarIV7-_tmEh_aa72f164e692496a9cbc07285ac20409.jpg","title":"Ideogram V4.0q Tiling"},{"category":"image-to-image","description":"Ideogram V4.0q Tiling LoRA produces seamless repeatable patterns guided by a custom-trained LoRA, locking a specific aesthetic or motif into tileable textures for cohesive, large-scale surface design.","endpoint_id":"ideogram/v4/tiling/lora","family":"Ideogram 4","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"Medium","description":"Which model expands the prompt. 'None' disables prompt expansion and skips its fee; 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.","enum":["None","Medium","Large"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"expansion_model","required":false,"type":"enum"},{"default":"square_hd","description":"The resolution of the generated seamlessly tileable image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"BALANCED","description":"The rendering speed to use. Faster speeds use fewer denoising steps.","enum":["TURBO","BALANCED","QUALITY"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"rendering_speed","required":false,"type":"enum"},{"default":"none","description":"The acceleration level to use for the image generation.","enum":["none","low","regular","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The seed to use for generation. If not provided, a random seed will be used.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Optional URL of an image. When provided without `mask_url`, performs image-to-image tiling; with `mask_url`, performs inpainting tiling.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Optional URL of a mask image for inpainting tiling. White regions are regenerated, black regions are preserved. Requires `image_url`.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"mask_url","required":false,"type":"string"},{"default":0.8,"description":"How much to transform the input image. Only used when `image_url` is provided.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":"both","description":"Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), or 'vertical' (top-bottom only).","enum":["both","horizontal","vertical"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"tiling_mode","required":false,"type":"enum"},{"default":"[]","description":"List of LoRA weights to apply (maximum 3).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"}],"lab":"Ideogram","output_kind":"images","output_props":["has_nsfw_concepts","timings","prompt","seed","images"],"pricing":"Your request will cost $0.03375 per megapixel in TURBO mode, $0.0675 per megapixel in BALANCED mode, or $0.1125 per megapixel in QUALITY mode.","published_at":"2026-06-11T08:40:27.862000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dc197/BnySTC6s06Ny468TjI2oi_801b238832aa4df5a2e777afff0286af.jpg","title":"Ideogram V4.0q Tiling LoRA"},{"category":"training","description":"Train custom LoRAs for personalization, styles or other use cases on top of Ideogram V4.","endpoint_id":"ideogram/v4/trainer","family":"Ideogram 4","inputs":[{"default":null,"description":"URL to a zip archive with training images and captions. The trainer uses the target-only dataset prepared by prepare_dataset_dir. Captions are read from same-stem .txt files.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"images_data_url","required":true,"type":"string"},{"default":1000,"description":"Number of LoRA training steps.","enum":null,"is_list":false,"max":40000,"media_kind":null,"min":100,"multiline":false,"name":"steps","required":false,"type":"integer"},{"default":null,"description":"Caption to use when an image has no caption file. If force_default_caption is true, this caption replaces all caption files.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"default_caption","required":false,"type":"string"},{"default":"auto","description":"Training image size. Use auto to pick the largest common no-upscale crop from the dataset. Images are center-cropped without upscaling. Available presets: square 1024x1024, landscape 1536x1024, portrait 1024x1536, widescreen 1920x1088, ultrawide 2048x768, phone_wallpaper 1024x1792, social_banner 1584x400. You can also pass a custom WIDTHxHEIGHT string when both values are divisible by 16.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"resolution","required":false,"type":"string"},{"default":0.0001,"description":"Learning Rate","enum":null,"is_list":false,"max":0.01,"media_kind":null,"min":1e-06,"multiline":false,"name":"learning_rate","required":false,"type":"number"},{"default":"fal","description":"Dictates the naming scheme for the output weights","enum":["fal","comfy"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_lora_format","required":false,"type":"enum"}],"lab":"Ideogram","output_kind":"json","output_props":["diffusers_lora_file","config_file"],"pricing":"The cost of training depends on the number of steps. The formula is: 0.00675 * steps. With 1000 steps, your request will cost $6.75.","published_at":"2026-06-10T00:28:19.073000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9daa87/0v2Rl8_IMMR1ZeMf0Klcb_89069342d0f04b92a3a24cb4b801af0f.jpg","title":"Ideogram V4.0q LoRA Trainer"},{"category":"text-to-image","description":"ImagineArt 1.5 text-to-image model generates high-fidelity professional-grade visuals with lifelike realism, strong aesthetics, and text that actually reads correctly.","endpoint_id":"imagineart/imagineart-1.5-preview/text-to-image","family":"","inputs":[{"default":null,"description":"Text prompt describing the desired image. Accepts either a raw string or a JSON string/fenced JSON with positive_prompt and optional negative_prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Image aspect ratio: 1:1, 3:1, 1:3, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3","enum":["1:1","3:1","1:3","16:9","9:16","4:3","3:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Seed for generation. 0 and -1 are treated as random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"ImagineArt","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2025-11-20T07:54:03.048000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/dzrNfvK_MHMcQvZSBju-R_9731ad76917e41e4bd48796e82fa9bc3.jpg","title":"Imagineart 1.5 Preview"},{"category":"text-to-image","description":"ImagineArt 1.5 Pro is an advanced text-to-image model that creates ultra-high-fidelity 4K visuals with lifelike realism, refined aesthetics, and powerful creative output suited for professional use.","endpoint_id":"imagineart/imagineart-1.5-pro-preview/text-to-image","family":"","inputs":[{"default":null,"description":"Text prompt describing the desired image. Accepts either a raw string or a JSON string/fenced JSON with positive_prompt and optional negative_prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Image aspect ratio: 1:1, 3:1, 1:3, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3","enum":["1:1","3:1","1:3","16:9","9:16","4:3","3:4","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":null,"description":"Seed for generation. 0 and -1 are treated as random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"ImagineArt","output_kind":"images","output_props":["images"],"pricing":"","published_at":"2026-01-15T08:52:36.780000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a775c/_DQSwdUUQgTD1E8ZjcsSf_15104de7104540b38840ceb135a0f673.jpg","title":"ImagineArt 1.5 Pro Preview"},{"category":"image-to-image","description":"ImagineArt 2.0 Edit delivers precise prompt-guided image editing at 2K resolution, preserving fine detail and realism while accurately applying targeted changes across one or more reference images.","endpoint_id":"imagineart/imagineart-2.0-edit-preview/image-to-image","family":"","inputs":[{"default":null,"description":"Reference image URL(s). Up to 4 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Editing instruction (e.g. 'replace the background with a sunset beach').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"auto","description":"Output aspect ratio. 'auto' = match the first input image's aspect ratio, sized to fill","enum":["auto","1:1","9:16","16:9","3:2","2:3","4:3","3:4","4:5","5:4","3:1","1:3","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"","output_kind":"images","output_props":["images"],"pricing":"Output Resolution: 2K. Pricing: $0.05 (1 image) then $0.007 for any additional input image other than 1st image.","published_at":"2026-05-19T14:38:38.088000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9ad814/PsE01Pyi5i4PgVaJ7qytu_4e417585f9e74974afdf1362d3ec7443.jpg","title":"Imagineart 2.0 Edit Preview"},{"category":"text-to-image","description":"ImagineArt 2.0 is ImagineArt's latest state-of-the-art visual reasoning text-to-image model, generating high-fidelity, professional-grade visuals with lifelike realism, cinematic effects, and strong aesthetic quality.","endpoint_id":"imagineart/imagineart-2.0-preview/text-to-image","family":"ImagineArt 2.0","inputs":[{"default":null,"description":"Text prompt describing the desired image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Image aspect ratio: 1:1, 3:1, 1:3, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 4:5, 5:4, 4:1, 1:4","enum":["1:1","16:9","9:16","4:3","3:4","3:1","1:3","3:2","2:3","21:9","4:5","5:4","4:1","1:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"2K","description":"Output resolution: '1K' targets ~1024px and will be faster. '2K' targets ~2048px image size and will be slower but with higher quality.","enum":["1K","2K"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Default is random (0 and -1 are treated as random)","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"low","description":"Visual Understanding Level: low (default) or high. High reasoning takes more time but generates better images.","enum":["high","low"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"enum"}],"lab":"ImagineArt","output_kind":"images","output_props":["images"],"pricing":"Your request will cost 1K at $0.03 and 2K at $0.05 per image generation.","published_at":"2026-04-16T19:53:53.912000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9619d4/8isHEzPc3fcKe_uRplQCZ_0270eeb6dceb461c97fe89581ef257f7.jpg","title":"Imagineart 2.0 Preview"},{"category":"text-to-image","description":"Generate high-fidelity images from text with Krea 2 Large, supporting aspect ratio, creativity, seed controls, and optional style references.","endpoint_id":"krea/v2/large/text-to-image","family":"Krea 2","inputs":[{"default":null,"description":"Text description of the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Aspect ratio of the generated image.","enum":["1:1","4:3","3:2","16:9","2.35:1","4:5","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"medium","description":"Controls how loosely the model interprets the prompt. Higher values produce more creative results that may drift from the prompt; lower values stay closer to the prompt.","enum":["raw","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"creativity","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"Optional list of reference images that guide the style of the generated image. At most 10 entries.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_style_references","required":false,"type":"json"},{"default":"[]","description":"Optional list of Krea preset styles (LoRA-based) to apply. Each entry references a style by `id` from the Krea styles catalog. At most 10 entries.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"json"},{"default":"[]","description":"Optional moodboard to apply to the generation. Krea currently accepts at most one moodboard per request. Each entry references a moodboard by `id` (UUID).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"moodboards","required":false,"type":"json"}],"lab":"Krea","output_kind":"images","output_props":["images","seed"],"pricing":"For every image you generate, you will be charged $0.060 (text-to-image) or $0.065 (using image_style_references).","published_at":"2026-05-27T15:00:13.274000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fb3/ATU9JDQwjBy0xRtTwPbft_7338811c31e94f11b04ef25761fe530f.jpg","title":"Krea 2 Large"},{"category":"text-to-image","description":"Generate high-quality images from text with Krea 2 Medium, supporting aspect ratio, creativity controls, seeds, and optional style references.","endpoint_id":"krea/v2/medium/text-to-image","family":"Krea 2","inputs":[{"default":null,"description":"Text description of the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Aspect ratio of the generated image.","enum":["1:1","4:3","3:2","16:9","2.35:1","4:5","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"medium","description":"Controls how loosely the model interprets the prompt. Higher values produce more creative results that may drift from the prompt; lower values stay closer to the prompt.","enum":["raw","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"creativity","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"Optional list of reference images that guide the style of the generated image. At most 10 entries.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_style_references","required":false,"type":"json"},{"default":"[]","description":"Optional list of Krea preset styles (LoRA-based) to apply. Each entry references a style by `id` from the Krea styles catalog. At most 10 entries.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"json"},{"default":"[]","description":"Optional moodboard to apply to the generation. Krea currently accepts at most one moodboard per request. Each entry references a moodboard by `id` (UUID).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"moodboards","required":false,"type":"json"}],"lab":"Krea","output_kind":"images","output_props":["images","seed"],"pricing":"For every image you generate, you will be charged $0.030 (text-to-image) or $0.035 (using image_style_references).","published_at":"2026-05-27T15:00:06.399000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9b9b04/L9ZlfONfHVw2xbk7h6Lu2_c9565826f8af4827851a7b8e73fc8cf8.jpg","title":"Krea 2 Medium"},{"category":"text-to-image","description":"Generate high-fidelity images extremely fast from text with Krea 2 Medium Turbo, supporting aspect ratio, creativity, seed controls, and optional style references.","endpoint_id":"krea/v2/medium/turbo/text-to-image","family":"Krea 2","inputs":[{"default":null,"description":"Text description of the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1:1","description":"Aspect ratio of the generated image.","enum":["1:1","4:3","3:2","16:9","2.35:1","4:5","2:3","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"medium","description":"Controls how loosely the model interprets the prompt. Higher values produce more creative results that may drift from the prompt; lower values stay closer to the prompt.","enum":["raw","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"creativity","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducible generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"Optional list of reference images that guide the style of the generated image. At most 10 entries.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_style_references","required":false,"type":"json"},{"default":"[]","description":"Optional list of Krea preset styles (LoRA-based) to apply. Each entry references a style by `id` from the Krea styles catalog. At most 10 entries.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"styles","required":false,"type":"json"},{"default":"[]","description":"Optional moodboard to apply to the generation. Krea currently accepts at most one moodboard per request. Each entry references a moodboard by `id` (UUID).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"moodboards","required":false,"type":"json"}],"lab":"Krea","output_kind":"images","output_props":["images","seed"],"pricing":"For every image you generate, you will be charged $0.015 (text-to-image) or $0.0175 (using image_style_references).","published_at":"2026-06-04T14:58:43.586000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f1c/JJWaVP5VEiyeEiqaEXWli_321bd6ab4d3f4ee8bf0003a332814416.jpg","title":"Krea 2 Medium Text to Image Turbo"},{"category":"image-to-video","description":"Luma Ray 3.2 animates a source image into cinematic motion guided by a text prompt, preserving the starting frame's look while controlling resolution, duration, and seamless looping.","endpoint_id":"luma/agent/ray/v3.2/image-to-video","family":"Ray 3.2","inputs":[{"default":null,"description":"Text prompt describing the motion/scene to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image used as the first frame of the video. Provide either image_url (optionally with end_image_url) or keyframes — the two anchoring modes are mutually exclusive.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":null,"description":"Optional URL of an image used as the last frame. When set, the model interpolates between image_url and end_image_url. Cannot be combined with keyframes.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"end_image_url","required":false,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["3:4","4:3","1:1","9:16","16:9","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"540p","description":"Resolution of the generated video. Higher resolutions cost more.","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"Duration of the generated video. 10s requires multi-keyframe input (keyframes / keyframe_indexes); it is not supported with a single image_url / end_image_url anchor.","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Generate a seamless loop. Only valid for standard-dynamic-range generations without an end frame or keyframes.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":false,"description":"Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with loop.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hdr","required":false,"type":"boolean"},{"default":false,"description":"Also export an EXR file alongside the MP4. Requires hdr=true and HDR access.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"exr_export","required":false,"type":"boolean"},{"default":null,"description":"Multi-keyframe image-to-video guide frames: 1-64 image URLs pinned at the positions given by keyframe_indexes. Mutually exclusive with image_url, end_image_url, and loop; unlocks 10s and HDR. Provide keyframes and keyframe_indexes together (same length).","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"keyframes","required":false,"type":"string"},{"default":null,"description":"Output-frame positions (duration x 24fps: 5s -> 0-120, 10s -> 0-240) where each keyframes[i] is anchored. Non-negative, unique, and the same length as keyframes.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keyframe_indexes","required":false,"type":"integer"}],"lab":"Luma AI","output_kind":"video","output_props":["exr_file","video"],"pricing":"For 5s video your request will cost $0.15 for 540p, $0.30 for 720p and $1.20 for 1080p. 10s is not available for image-to-video (start-frame requirement). HDR (5s) costs $0.60 at 720p and $2.40 at 1080p; HDR + EXR (5s) costs $0.90 at 720p and $3.60 at 1080p (540p not available in HDR). For $1 you can run this model approximately 6 times (540p/5s).","published_at":"2026-06-09T15:14:38.545000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d98c5/bGUKcElNU84zDuONbJcfm_72859703947a48629cc1b9773d784260.jpg","title":"Luma Ray 3.2 Image to Video"},{"category":"video-to-video","description":"Luma Ray 3.2 reframes an existing video into a new aspect ratio guided by a text prompt, preserving the original footage frame-for-frame while controlling resolution and outpainting the surrounding canvas.","endpoint_id":"luma/agent/ray/v3.2/reframe","family":"Ray 3.2","inputs":[{"default":null,"description":"Text prompt describing the content to paint into the newly exposed canvas area when reframing to the target aspect ratio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the source video to reframe (must be 30 seconds or less).","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Target aspect ratio for the reframed video.","enum":["3:4","4:3","1:1","9:16","16:9","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":true,"type":"enum"},{"default":"540p","description":"Resolution of the reframed video. Higher resolutions cost more.","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"Optional normalized source rectangle controlling where the source video sits in the output canvas.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"source_position","required":false,"type":"json"}],"lab":"Luma AI","output_kind":"video","output_props":["exr_file","video"],"pricing":"Reframe is billed per started source second: $0.06/s at 540p, $0.12/s at 720p and $0.36/s at 1080p. A 5s source will cost $0.30 for 540p, $0.60 for 720p and $1.80 for 1080p. A 10s source costs $0.60 at 540p, $1.20 at 720p and $3.60 at 1080p. For $1 you can reframe approximately 3 five-second clips (540p).","published_at":"2026-06-11T08:25:00.838000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dd7b5/EYZitiCzNxOgXBBIwJFBQ_b17d775dd8f64f82b17fbcbf06e2ba9f.jpg","title":"Luma Ray 3.2 Reframe"},{"category":"text-to-video","description":"Luma Ray 3.2 generates cinematic video from a text prompt, with control over resolution, duration, and seamless looping, plus reference images to lock in subject and style.","endpoint_id":"luma/agent/ray/v3.2/text-to-video","family":"Ray 3.2","inputs":[{"default":null,"description":"Text prompt describing the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["3:4","4:3","1:1","9:16","16:9","21:9"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"540p","description":"Resolution of the generated video. Higher resolutions cost more.","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"Duration of the generated video.","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":false,"description":"Generate a seamless loop. Only valid for 5s, standard-dynamic-range generations without an end frame.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loop","required":false,"type":"boolean"},{"default":false,"description":"Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with 10s or loop.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hdr","required":false,"type":"boolean"},{"default":false,"description":"Also export an EXR file alongside the MP4. Requires hdr=true and HDR access.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"exr_export","required":false,"type":"boolean"}],"lab":"Luma AI","output_kind":"video","output_props":["exr_file","video"],"pricing":"For 5s video your request will cost $0.50 for 540p, $1 for 720p and $2 for 1080p. For 10s, $1 at 540p, $2 at 720p and $4 at 1080p. For $1 you can run this model approximately 2 times (540p/5s).","published_at":"2026-06-09T15:14:43.926000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d98a0/DwsmVaf6M6SVp2KIN3bId_321b3394d9f243de98b9f6295b4c48b5.jpg","title":"Luma Ray 3.2 Text to Video"},{"category":"video-to-video","description":"Luma Ray 3.2 re-renders an existing video into new cinematic motion guided by a text prompt, preserving the source's look and movement while controlling resolution, duration, and HDR.","endpoint_id":"luma/agent/ray/v3.2/video-to-video","family":"Ray 3.2","inputs":[{"default":null,"description":"Text prompt describing how to edit the source video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the source video to edit.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional URL of an image to use as the edited video's first frame — e.g. a restyled version of the source's opening frame to steer the look of the edit. Leave unset to let the model derive the first frame from the source video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"start_image_url","required":false,"type":"string"},{"default":"540p","description":"Resolution of the edited video. Higher resolutions cost more.","enum":["540p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5s","description":"Duration of the edited video.","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":null,"description":"How closely the edit preserves the source video. 'adhere_*' stays closest to the source, 'flex_*' is balanced, and 'reimagine_*' diverges most. Leave unset to use Luma's default. Cannot be combined with auto_controls.","enum":["adhere_1","adhere_2","adhere_3","flex_1","flex_2","flex_3","reimagine_1","reimagine_2","reimagine_3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"edit_strength","required":false,"type":"enum"},{"default":false,"description":"Let the model derive the edit conditioning schedule from the source video. Cannot be combined with edit_strength.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_controls","required":false,"type":"boolean"},{"default":false,"description":"Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"hdr","required":false,"type":"boolean"},{"default":false,"description":"Also export an EXR file alongside the MP4. Requires hdr=true and HDR access.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"exr_export","required":false,"type":"boolean"},{"default":null,"description":"Per-signal conditioning controls (pose, depth, normals, trajectory, face) for finer control than edit_strength. Cannot be combined with auto_controls.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"controls","required":false,"type":"json"},{"default":null,"description":"Multi-keyframe edit guide frames: up to 64 image URLs pinned at the source-frame positions given by keyframe_indexes. Mutually exclusive with start_image_url. Provide keyframes and keyframe_indexes together (same length).","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"keyframes","required":false,"type":"string"},{"default":null,"description":"Source-video frame positions where each keyframes[i] is anchored. Non-negative, unique, and the same length as keyframes.","enum":null,"is_list":true,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"keyframe_indexes","required":false,"type":"integer"}],"lab":"Luma AI","output_kind":"video","output_props":["exr_file","video"],"pricing":"For 5s video your request will cost $0.72 for 540p, $1.08 for 720p and $2.16 for 1080p. For 10s, $1.44 at 540p, $2.16 at 720p and $4.32 at 1080p. HDR (720p/1080p only) costs $2.16/$4.32 at 5s and $4.32/$8.64 at 10s; HDR + EXR costs $3.24/$6.48 at 5s and $6.48/$12.96 at 10s (540p not available in HDR). For $1 you can run this model approximately 1 time (540p/5s).","published_at":"2026-06-11T08:36:00.570000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9dd626/fDtx2FCaRxBnEQmyYu2DY_d03821f138c94cf3a2cf165a9aa389bf.jpg","title":"Luma Ray 3.2 Video to Video"},{"category":"image-to-image","description":"Luma Uni-1 Edit reworks a source image from a text instruction, preserving the original composition while applying style changes and following optional reference images to steer the result.","endpoint_id":"luma/agent/uni-1/v1/edit","family":"Uni-1","inputs":[{"default":null,"description":"Text prompt describing the edit to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the source image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"auto","description":"Visual style of the edited image.","enum":["auto","manga"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"Encoding format of the edited image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Optional list of reference image URLs used to guide the edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":false,"type":"string"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"Each edit costs $0.042 plus $0.003 per reference/source image. A single-image edit runs $0.045. For $1 you can run this model approximately 22 times.","published_at":"2026-06-09T15:16:33.097000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d98d3/t8rhVKRw9Rj_5adYTDK6m_b393038bbf464975b8d573f94f2fadc0.jpg","title":"Luma Uni-1 Edit"},{"category":"text-to-image","description":"Luma Uni-1 Max generates a single image at the model's highest fidelity, delivering richer detail and stronger prompt adherence than the base tier for hero-quality stills.","endpoint_id":"luma/agent/uni-1/v1/max","family":"Uni-1","inputs":[{"default":null,"description":"Text prompt describing the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Aspect ratio of the generated image.","enum":["3:1","2:1","16:9","3:2","1:1","2:3","9:16","1:2","1:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"auto","description":"Visual style of the generated image.","enum":["auto","manga"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"Encoding format of the generated image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"When true, the model may consult the web for references.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"},{"default":null,"description":"Optional list of reference image URLs used to guide the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":false,"type":"string"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"Each image costs $0.102. For $1 you can run this model approximately 9 times.","published_at":"2026-06-09T15:16:24.712000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d98ea/3z1sASr8I0QtWyvc6bhIP_808c1c2b4b11452388ce903d4cd3d243.jpg","title":"Luma Uni-1 Text to Image Max"},{"category":"image-to-image","description":"Luma Uni-1 Max Edit applies text-guided edits to a source image at maximum fidelity, holding the original structure while honoring reference images for precise, high-detail revisions.","endpoint_id":"luma/agent/uni-1/v1/max/edit","family":"Uni-1","inputs":[{"default":null,"description":"Text prompt describing the edit to apply.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the source image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"auto","description":"Visual style of the edited image.","enum":["auto","manga"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"Encoding format of the edited image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Optional list of reference image URLs used to guide the edit.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":false,"type":"string"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"Each edit costs $0.102 plus $0.003 per reference/source image. A single-image edit runs $0.105. For $1 you can run this model approximately 9 times.","published_at":"2026-06-09T15:16:14.108000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d98fd/-vUZCkQbk_HxqDUKgcvo6_6b69ed5b53c74a6ba900168b8ad17e71.jpg","title":"Luma Uni-1 Edit Max"},{"category":"text-to-image","description":"Luma Uni-1 turns a text prompt into a single high-fidelity image, with control over aspect ratio and visual style, plus optional web-sourced and reference-image guidance for sharper grounding.","endpoint_id":"luma/agent/uni-1/v1/text-to-image","family":"Uni-1","inputs":[{"default":null,"description":"Text prompt describing the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Aspect ratio of the generated image.","enum":["3:1","2:1","16:9","3:2","1:1","2:3","9:16","1:2","1:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"auto","description":"Visual style of the generated image.","enum":["auto","manga"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":null,"description":"Encoding format of the generated image.","enum":["png","jpeg"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":false,"description":"When true, the model may consult the web for references.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_web_search","required":false,"type":"boolean"},{"default":null,"description":"Optional list of reference image URLs used to guide the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_urls","required":false,"type":"string"}],"lab":"Luma AI","output_kind":"images","output_props":["images"],"pricing":"Each image costs $0.042. For $1 you can run this model approximately 23 times.","published_at":"2026-06-09T15:15:56.994000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9d990b/4ef8FCP-VEq-mXDufTE1f_ad73fb1124324bdc8d747094ad401a8a.jpg","title":"Luma Uni-1 Text to Image"},{"category":"text-to-image","description":"MAI-Image-2.5 is Microsoft's photorealistic image generation and editing model that turns text prompts or uploaded images into high-quality, design-ready visuals with fine-grained, pixel-level control.","endpoint_id":"microsoft/mai-image-2.5","family":"Mai Image 2.5","inputs":[{"default":null,"description":"The text prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Use \"auto\" to let the model decide based on the prompt.","enum":["auto","1:1","4:3","3:4","16:9","9:16","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Microsoft","output_kind":"images","output_props":["images","description"],"pricing":"Text tokens (per 1M): $5.00 input. Image output: ~$0.05 per generated image (billed as 1024 output tokens). Each requested image is billed separately. Token cost is rounded up to the nearest $0.0001. Note: Pricing is subject to change.","published_at":"2026-06-02T21:15:26.791000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9cb935/HbS9rehPTKxqOgAogjHKc_05794f384f4f4631b439ecc867b97b08.jpg","title":"Mai Image 2.5 Text to Image"},{"category":"image-to-image","description":"MAI-Image-2.5 is Microsoft's photorealistic image generation and editing model that turns text prompts or uploaded images into high-quality, design-ready visuals with fine-grained, pixel-level control.","endpoint_id":"microsoft/mai-image-2.5/edit","family":"Mai Image 2.5","inputs":[{"default":null,"description":"The instruction describing how to edit the input image(s).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"auto","description":"The aspect ratio of the generated image. Use \"auto\" to match the input or let the model decide.","enum":["auto","1:1","4:3","3:4","16:9","9:16","3:2","2:3"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the image to edit. Provide one http(s) or data: URL.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"}],"lab":"Microsoft","output_kind":"images","output_props":["images","description"],"pricing":"Image output: ~$0.05 per generated image, billed as ~1024 output image tokens. Each requested image is billed separately. Total token cost is rounded up to the nearest $0.0001. Text tokens: $5.00 per 1M input tokens. Image input tokens: $8.00 per 1M input tokens. Note: Pricing is subject to change.","published_at":"2026-06-03T23:46:30.286000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9cd5ea/45Nk09Ywc5xp2308fS4Wa_b2473bfde0a2498e9840eac9cbe8028e.jpg","title":"Mai Image 2.5"},{"category":"video-to-audio","description":"Generate synced sounds for any video, and return the new sound track (like MMAudio)","endpoint_id":"mirelo-ai/sfx-v1.5/video-to-audio","family":"","inputs":[{"default":null,"description":"A video url that can accessed from the API to process and add sound effects","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Additional description to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":2,"description":"The number of samples to generate from the model","enum":null,"is_list":false,"max":8,"media_kind":null,"min":2,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":8069,"description":"The seed to use for the generation. If not provided, a random seed will be used","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":10,"description":"The duration of the generated audio in seconds","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":0,"description":"The start offset in seconds to start the audio generation from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_offset","required":false,"type":"number"}],"lab":"Mirelo AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-10-15T11:13:45.451000+00:00","thumbnail":"https://v3b.fal.media/files/b/lion/wwhXRNDWSVEdS9jIG6BAA_b1d337ecdccb441aa80caab321487fb7.jpg","title":"Mirelo SFX V1.5"},{"category":"video-to-video","description":"Generate synced sounds for any video, and return it with its new sound track (like MMAudio)","endpoint_id":"mirelo-ai/sfx-v1.5/video-to-video","family":"","inputs":[{"default":null,"description":"A video url that can accessed from the API to process and add sound effects","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Additional description to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":2,"description":"The number of samples to generate from the model","enum":null,"is_list":false,"max":8,"media_kind":null,"min":2,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":8069,"description":"The seed to use for the generation. If not provided, a random seed will be used","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":10,"description":"The duration of the generated audio in seconds","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":0,"description":"The start offset in seconds to start the audio generation from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"start_offset","required":false,"type":"number"}],"lab":"Mirelo AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-10-15T11:11:27.394000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/ySuE0GYF98p7-856X4mvc_9371de55f14448e08b76871b7d77c059.jpg","title":"Mirelo SFX V1.5"},{"category":"video-to-audio","description":"Generate synced sounds for any video, and return the new sound track (like MMAudio)","endpoint_id":"mirelo-ai/sfx-v1/video-to-audio","family":"","inputs":[{"default":null,"description":"A video url that can accessed from the API to process and add sound effects","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Additional description to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":2,"description":"The number of samples to generate from the model","enum":null,"is_list":false,"max":8,"media_kind":null,"min":2,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":2105,"description":"The seed to use for the generation. If not provided, a random seed will be used","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":10,"description":"The duration of the generated audio in seconds","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"}],"lab":"Mirelo AI","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.007 per second of output and per sample.","published_at":"2025-08-15T12:24:51.311000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f92d6/5GisulG5ECXXgAO6-czKP_7uRr34ZG.png","title":"Mirelo SFX"},{"category":"video-to-video","description":"Generate synced sounds for any video, and return it with its new sound track (like MMAudio)","endpoint_id":"mirelo-ai/sfx-v1/video-to-video","family":"","inputs":[{"default":null,"description":"A video url that can accessed from the API to process and add sound effects","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Additional description to guide the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":2,"description":"The number of samples to generate from the model","enum":null,"is_list":false,"max":8,"media_kind":null,"min":2,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":2105,"description":"The seed to use for the generation. If not provided, a random seed will be used","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":10,"description":"The duration of the generated audio in seconds","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"}],"lab":"Mirelo AI","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.007 per second of output and per sample.","published_at":"2025-08-14T15:28:42.130000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9398/n7-A2Zl0tPWjWAfZxXTGj_SwtWmr31.png","title":"Mirelo SFX"},{"category":"audio-to-audio","description":"Extend any sound effect with seamless, natural tails.","endpoint_id":"mirelo-ai/sfx1.6/extend-audio","family":"","inputs":[{"default":null,"description":"URL of the audio prefix to extend. The prefix duration must be 3–59 seconds; the total output (prefix + append_duration) is capped at 60 seconds.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Optional text prompt guiding the extension.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":10,"description":"How many seconds to add after the prefix. Total output = prefix duration + append_duration, capped at 60s. Minimum 1s, maximum 57s (60s cap minus the 3s prefix minimum).","enum":null,"is_list":false,"max":57,"media_kind":null,"min":1,"multiline":false,"name":"append_duration","required":false,"type":"number"},{"default":false,"description":"When true, run the extend+loop path: extend the prefix and stitch the end back to the prefix start so the tile loops seamlessly. When false, run a one-shot extension.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ambience","required":false,"type":"boolean"},{"default":false,"description":"Only used when ambience=true: concatenate the loop with itself for a 2x-length output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"double_output","required":false,"type":"boolean"},{"default":1,"description":"Number of variations to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":null,"description":"Seed for generation. -1 or None for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":-1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"wav","description":"Audio format for the returned files.","enum":["wav","mp3","aac","flac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upload_audio_format","required":false,"type":"enum"}],"lab":"Mirelo AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-05-18T18:43:44.785000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9abc5b/IzyebtglRHhrTN4R332lK_3ce3e48026f845a4b657e7a85e4ea921.jpg","title":"Mirelo SFX1.6"},{"category":"audio-to-audio","description":"Erase and replace any moment in your audio with AI-driven precision.","endpoint_id":"mirelo-ai/sfx1.6/inpaint-audio","family":"","inputs":[{"default":null,"description":"URL of the source audio. Maximum 10 seconds — longer clips are rejected. The model regenerates only the region defined by `segment`; everything outside it is preserved.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Region [start_s, end_s] (in seconds, 1s ≤ start < end ≤ 10s, 1–8s span) to regenerate. The audio outside this region is preserved.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"segment","required":true,"type":"json"},{"default":null,"description":"Optional text prompt guiding the regenerated segment.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":1,"description":"Number of variations to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":null,"description":"Seed for generation. -1 or None for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":-1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"wav","description":"Audio format for the returned files.","enum":["wav","mp3","aac","flac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upload_audio_format","required":false,"type":"enum"}],"lab":"Mirelo AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-05-18T18:43:48.448000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9abc6b/yrs1WKYDwD72zvCfre8HT_3682862f016942178f0100e9cd27f1fd.jpg","title":"Mirelo SFX1.6"},{"category":"text-to-audio","description":"Generate ambient sounds for any text prompt. Now you can turn any SFX into a natural loop for ambient soundscapes.","endpoint_id":"mirelo-ai/sfx1.6/text-to-audio","family":"","inputs":[{"default":null,"description":"Text prompt for the generated audio.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":true,"type":"string"},{"default":10,"description":"Duration of the generated audio in seconds.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":0.1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":false,"description":"When true, generate a seamlessly loopable ambience tile (room tone, rain, drones, etc.). When false, generate a generic text-conditioned SFX of `duration` seconds.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"ambience","required":false,"type":"boolean"},{"default":false,"description":"Only used when ambience=true: concatenate the loop with itself for a 2x-length output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"double_output","required":false,"type":"boolean"},{"default":1,"description":"Number of variations to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":null,"description":"Seed for generation. -1 or None for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":-1,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"wav","description":"Audio format for the returned files.","enum":["wav","mp3","aac","flac"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"upload_audio_format","required":false,"type":"enum"}],"lab":"Mirelo AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2026-05-18T18:43:51.572000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9a49f4/j_CsUhacSWsqc9KyZ6X5G_6e551c71998c4f9697cee6bc6f22554d.jpg","title":"Mirelo SFX1.6"},{"category":"video-to-video","description":"Generate synced sounds for any video, and return it with its new sound track (like MMAudio). Now up to 60 seconds!","endpoint_id":"mirelo-ai/sfx1.6/video-to-video","family":"","inputs":[{"default":null,"description":"Video URL to add SFX to.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional text prompt guiding generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"text_prompt","required":false,"type":"string"},{"default":10,"description":"Duration of the generated SFX in seconds. Values >10 use sliding-window extended generation.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"},{"default":1,"description":"Number of variations to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":null,"description":"Seed for generation. -1 or None for random.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":-1,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Mirelo AI","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2026-05-18T18:43:54.282000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9abc49/Hx1n7Mr61RIVuZ9Ia8rEU_38997284ae234545a12528f31e3b592c.jpg","title":"Mirelo SFX1.6"},{"category":"image-to-video","description":"Generate a video starting from an image as the first frame with Marey, a generative video model trained exclusively on fully licensed data.","endpoint_id":"moonvalley/marey/i2v","family":"Marey","inputs":[{"default":null,"description":"The prompt to generate a video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1920x1080","description":"The dimensions of the generated video in width x height format.","enum":["1920x1080","1080x1920","1152x1152","1536x1152","1152x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dimensions","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video.","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"<synthetic> <scene cut> low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts","description":"Negative prompt used to guide the model away from undesirable features.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":-1,"description":"Seed for random number generation. Use -1 for random seed each run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Controls how strongly the generation is guided by the prompt (0-20). Higher values follow the prompt more closely.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The URL of the image to use as the first frame of the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Moonvalley","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $1.50 for a 5s video or $3.00 for a 10s video.","published_at":"2025-08-14T01:27:37.851000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9394/ZLHbUTHZhNxJ56W9NaaeK_iLOqZpyY.png","title":"Marey Realism V1.5"},{"category":"video-to-video","description":"Pull motion from a reference video and apply it to new subjects or scenes.","endpoint_id":"moonvalley/marey/motion-transfer","family":"Marey","inputs":[{"default":null,"description":"The prompt to generate a video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to use as the control video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"https://video-editor-files-prod.s3.us-east-2.amazonaws.com/users/1e4d46df-0702-4491-95ce-763592f33f34/uploaded-images/9b9dce1c-abd0-46c0-bac9-9454f8893b06/original","description":"Optional first frame image URL to use as the first frame of the generated video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_frame_image_url","required":false,"type":"string"},{"default":null,"description":"Optional reference image URL to use for pose control or as a starting frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":"<synthetic> <scene cut> low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts","description":"Negative prompt used to guide the model away from undesirable features.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":-1,"description":"Seed for random number generation. Use -1 for random seed each run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Moonvalley","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $2.00 per video.","published_at":"2025-08-14T01:30:37.686000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f93a5/vjMxBOfrRCK4jN0P79ETX_qvnjaHVQ.png","title":"Marey Realism V1.5"},{"category":"video-to-video","description":"Ideal for matching human movement. Your input video determines human poses, gestures, and body movements that will appear in the generated video.","endpoint_id":"moonvalley/marey/pose-transfer","family":"Marey","inputs":[{"default":null,"description":"The prompt to generate a video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URL of the video to use as the control video.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Optional first frame image URL to use as the first frame of the generated video","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"first_frame_image_url","required":false,"type":"string"},{"default":null,"description":"Optional reference image URL to use for pose control or as a starting frame","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"reference_image_url","required":false,"type":"string"},{"default":"<synthetic> <scene cut> low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts","description":"Negative prompt used to guide the model away from undesirable features.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":-1,"description":"Seed for random number generation. Use -1 for random seed each run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"}],"lab":"Moonvalley","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $2.00 per video.","published_at":"2025-08-14T01:35:00.575000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9a4c/EPt_AnjU8dkXIo-fjuhMl_cj1U1nbj.png","title":"Marey Realism V1.5"},{"category":"text-to-video","description":"Generate a video from a text prompt with Marey, a generative video model trained exclusively on fully licensed data.","endpoint_id":"moonvalley/marey/t2v","family":"Marey","inputs":[{"default":null,"description":"The prompt to generate a video from","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"1920x1080","description":"The dimensions of the generated video in width x height format.","enum":["1920x1080","1152x1152","1536x1152","1152x1536"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"dimensions","required":false,"type":"enum"},{"default":"5s","description":"The duration of the generated video.","enum":["5s","10s"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"<synthetic> <scene cut> low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts","description":"Negative prompt used to guide the model away from undesirable features.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":-1,"description":"Seed for random number generation. Use -1 for random seed each run.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Controls how strongly the generation is guided by the prompt (0-20). Higher values follow the prompt more closely.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"guidance_scale","required":false,"type":"number"}],"lab":"Moonvalley","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $1.50 for a 5s video or $3.00 for a 10s video.","published_at":"2025-08-14T01:01:05.296000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f9394/PrU8g8NJYdKOP6NaL5j2K_LCCKVkOr.png","title":"Marey Realism V1.5"},{"category":"image-to-video","description":"Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.","endpoint_id":"nvidia/cosmos-3-super/image-to-video","family":"Cosmos","inputs":[{"default":null,"description":"Text prompt describing the motion and scene of the video to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the conditioning first-frame image for the video.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"The video captures a series of frames showing macroblocking artifacts, chromatic aberration, high-frequency noise, and rolling shutter distortion. It includes static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, bit-depth compression artifacts, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, hard cut, visual noise, and flickering. It features moiré patterns, edge halos, and temporal aliasing. Furthermore, the content defies common sense, generating illogical scenarios, nonsensical entities, absurd character behaviors, and conceptual paradoxes that violate basic human reasoning and everyday reality. The video looks like a surreal or glitchy hallucination. Overall, the video is of poor quality.","description":"Content to steer the generation away from (artifacts, unwanted motion). Defaults to NVIDIA's recommended i2v negative prompt; pass an empty string to disable.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"If true, the Cosmos3-Nano Reasoner (a VLM that sees the first frame) rewrites the prompt into the dense caption Cosmos3 was trained on. The app starts a local Reasoner by default, or uses COSMOS_PROMPT_UPSAMPLER_BASE_URL when configured. Falls back to the raw prompt if expansion fails.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Enable the iterative Cosmos agentic loop: prompt upsampling, candidate video generation, VLM critique of sampled frames, and prompt rewrite. Each candidate is a full render, so this is substantially slower and costlier than a single generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_agentic_generation","required":false,"type":"boolean"},{"default":2,"description":"Maximum agentic prompt stages when agentic generation is enabled.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"agentic_max_iterations","required":false,"type":"integer"},{"default":2,"description":"Candidate videos to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"agentic_samples_per_iteration","required":false,"type":"integer"},{"default":true,"description":"Stop the agentic loop early when the critic score clears the strict quality threshold.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"agentic_early_stop","required":false,"type":"boolean"},{"default":{"height":480,"width":832},"description":"The size of the generated video. The request is clamped and snapped to the nearest supported NVIDIA tier (256p/480p/720p) and aspect ratio.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":189,"description":"Number of frames to generate. More frames yield a longer video.","enum":null,"is_list":false,"max":189,"media_kind":null,"min":5,"multiline":false,"name":"num_frames","required":false,"type":"integer"},{"default":24,"description":"Frames per second of the output video.","enum":null,"is_list":false,"max":60,"media_kind":null,"min":4,"multiline":false,"name":"frames_per_second","required":false,"type":"integer"},{"default":28,"description":"Number of denoising steps. More steps yield higher quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":6,"description":"Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":null,"description":"The same seed and prompt given to the same model version will produce the same video every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for the input prompt and image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"NVIDIA","output_kind":"video","output_props":["seed","video"],"pricing":"Your request will cost $0.05 per second of generated video, rounded up. Agentic generation is billed for each candidate video generated","published_at":"2026-06-02T00:21:20.063000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fbe/hXW1eVvHgtPqSxYZP4CqC_8cd37164dacf41aaad63b1aa2afb0b5c.jpg","title":"Cosmos 3 Super Image to Video"},{"category":"text-to-image","description":"Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.","endpoint_id":"nvidia/cosmos-3-super/text-to-image","family":"Cosmos","inputs":[{"default":null,"description":"Text prompt describing the image to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"","description":"Content to steer the generation away from (colors, objects, artifacts).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":false,"description":"Expand the prompt with OpenRouter before image generation. When enabled, the prompt is rewritten into the dense structured-JSON format Cosmos3 was trained on; generation falls back to the raw prompt if expansion fails.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"Automatically generate and compare multiple candidate images, then refine the prompt between rounds to better match the original request. This can improve prompt adherence but increases latency and billable image generations.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_agentic_generation","required":false,"type":"boolean"},{"default":2,"description":"Maximum number of refinement rounds when agentic generation is enabled.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"agentic_max_iterations","required":false,"type":"integer"},{"default":2,"description":"Candidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"agentic_samples_per_iteration","required":false,"type":"integer"},{"default":true,"description":"Stop early when a candidate image is already a strong match for the prompt.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"agentic_early_stop","required":false,"type":"boolean"},{"default":"square_hd","description":"The size of the generated image. Each edge is clamped to 512-1280px (multiples of 16).","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"Number of denoising steps. More steps yield higher quality but take longer.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":4,"description":"Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":null,"description":"The same seed and prompt given to the same model version will produce the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for the input prompt and generated images.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"NVIDIA","output_kind":"images","output_props":["seed","has_nsfw_concepts","images"],"pricing":"Your request will cost $0.04 per generated image. Prompt expansion adds $0.02 per request when enabled. Agentic generation bills for every candidate image generated during selection, not just the final returned image.","published_at":"2026-06-01T22:04:50.504000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fbf/8oMkNXbqWEcxXACy_vm-Z_21bfbdc01687466b9206e49cc70423e4.jpg","title":"Cosmos 3 Super"},{"category":"llm","description":"Open, efficient reasoning model from NVIDIA. 30B A3B hybrid Transformer-Mamba MoE, built for enterprise agentic workflows.","endpoint_id":"nvidia/nemotron-3-nano-omni","family":"Nemotron","inputs":[{"default":null,"description":"Text prompt to send to the model. English only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":"no_think","description":"Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.","enum":["think","no_think"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning_mode","required":false,"type":"enum"},{"default":1024,"description":"Maximum number of tokens to generate.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.7,"description":"Sampling temperature. Lower is more deterministic.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.95,"description":"Nucleus sampling probability mass.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"}],"lab":"NVIDIA","output_kind":"json","output_props":["finish_reason","usage","output"],"pricing":"","published_at":"2026-04-28T15:50:58.353000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97fbd9/If5ov--ixg3WLwZO41VX7_adc5fcfe153c4ff5b57fd501934b4a99.jpg","title":"Nemotron 3 Nano Omni"},{"category":"audio-to-text","description":"Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts audio plus a prompt and returns text.","endpoint_id":"nvidia/nemotron-3-nano-omni/audio","family":"Nemotron","inputs":[{"default":null,"description":"Text prompt to send to the model. English only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":"no_think","description":"Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.","enum":["think","no_think"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning_mode","required":false,"type":"enum"},{"default":1024,"description":"Maximum number of tokens to generate.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.7,"description":"Sampling temperature. Lower is more deterministic.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.95,"description":"Nucleus sampling probability mass.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":null,"description":"URL of the audio clip to reason about. wav or mp3, max 50 minutes.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"NVIDIA","output_kind":"json","output_props":["finish_reason","usage","output"],"pricing":"","published_at":"2026-04-28T15:51:13.512000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97fbf3/g_W4YFr0ezicmk-_sAhsr_58513a223d514f269d222988f86de3ce.jpg","title":"Nemotron 3 Nano Omni"},{"category":"video-to-text","description":"Video reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts video plus a prompt and returns text.","endpoint_id":"nvidia/nemotron-3-nano-omni/video","family":"Nemotron","inputs":[{"default":null,"description":"Text prompt to send to the model. English only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":"no_think","description":"Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.","enum":["think","no_think"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning_mode","required":false,"type":"enum"},{"default":1024,"description":"Maximum number of tokens to generate.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.7,"description":"Sampling temperature. Lower is more deterministic.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.95,"description":"Nucleus sampling probability mass.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":null,"description":"URL of the video to reason about. mp4, up to 1080p, max 2 minutes.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"}],"lab":"NVIDIA","output_kind":"json","output_props":["finish_reason","usage","output"],"pricing":"","published_at":"2026-04-28T15:51:20.073000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97fc0c/IvpJSkmN4FKa3qtjq1cwG_c50977be73724e55afe22e21c722e382.jpg","title":"Nemotron 3 Nano Omni"},{"category":"image-to-text","description":"Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts an image plus a prompt and returns text.","endpoint_id":"nvidia/nemotron-3-nano-omni/vision","family":"Nemotron","inputs":[{"default":null,"description":"Text prompt to send to the model. English only.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":"no_think","description":"Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.","enum":["think","no_think"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning_mode","required":false,"type":"enum"},{"default":1024,"description":"Maximum number of tokens to generate.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"},{"default":0.7,"description":"Sampling temperature. Lower is more deterministic.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":0.95,"description":"Nucleus sampling probability mass.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"top_p","required":false,"type":"number"},{"default":null,"description":"URL of the image to reason about. RGB JPEG or PNG.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"NVIDIA","output_kind":"json","output_props":["finish_reason","usage","output"],"pricing":"","published_at":"2026-04-28T15:51:27.028000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a97fc1a/44YyOoFOCrsAmXpvExbhN_bf489eed741849bf89170edd15436191.jpg","title":"Nemotron 3 Nano Omni"},{"category":"speech-to-text","description":"Nemotron-ASR-Streaming is a multi lingual, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality multi lingual transcription across both low-latency streaming and high-throughput batch workloads.","endpoint_id":"nvidia/nemotron-asr-multilingual/asr","family":"Nemotron","inputs":[{"default":null,"description":"URL of the audio file to transcribe.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":"auto","description":"Target language for transcription (language-ID prompt). 'auto' lets the model detect the language.","enum":["auto","en-US","en-GB","es-US","es-ES","de-DE","fr-FR","fr-CA","it-IT","ar-AR","ja-JP","ko-KR","pt-BR","pt-PT","ru-RU","hi-IN","zh-CN","vi-VN","he-IL","nl-NL","cs-CZ","da-DK","pl-PL","nn-NO","nb-NO","sv-SE","th-TH","tr-TR","bg-BG","el-GR","et-EE","fi-FI","hr-HR","hu-HU","lt-LT","lv-LV","ro-RO","sk-SK","uk-UA","mt-MT","sl-SI"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":"regular","description":"Controls the speed/accuracy trade-off. 'none' = best accuracy (1.12s chunks), 'regular' = balanced (0.56s chunks), 'high' = faster (0.32s chunks), 'full' = fastest (0.08s chunks).","enum":["none","regular","high","full"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"NVIDIA","output_kind":"json","output_props":["partial","output"],"pricing":"","published_at":"2026-06-10T17:20:08.711000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fbf/6-zNQDwpy54LnxDQx2dEO_a053aeaf6ad14a4fb4bce191086d95f1.jpg","title":"Nemotron Asr Multilingual"},{"category":"text-to-image","description":"GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.","endpoint_id":"openai/gpt-image-2","family":"GPT Image 2","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image. Supports preset names, explicit {width, height}, or 'auto' to let the model pick the best size. Concrete sizes must have both dimensions as multiples of 16, max edge 3840px, aspect ratio <= 3:1, total pixels between 655,360 and 8,294,400.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"high","description":"Quality for the generated image. Use 'auto' to let the model pick the best quality for the prompt.","enum":["auto","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output.\nImage tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference.\nSee the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a cent ($0.0001.)","published_at":"2026-04-21T19:15:20.183000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a970c4a/BkrYELYOiaZMXCw-pgRcB_QlgOenEx.png","title":"GPT Image 2 API"},{"category":"image-to-image","description":"GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.","endpoint_id":"openai/gpt-image-2/edit","family":"GPT Image 2","inputs":[{"default":null,"description":"The prompt for image generation","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The URLs of the images to use as a reference for the generation.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":"auto","description":"The size of the generated image. Use 'auto' to infer from input images.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","auto","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":"high","description":"Quality for the generated image. Use 'auto' to let the model pick the best quality for the prompt.","enum":["auto","low","medium","high"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quality","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"png","description":"Output format for the images","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"The URL of the mask image to use for the generation. This indicates what part of the image to edit.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":false,"type":"string"}],"lab":"OpenAI","output_kind":"images","output_props":["images"],"pricing":"Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output.\nImage tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference.\nSee the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a cent ($0.0001).","published_at":"2026-04-21T19:15:07.070000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2f0d/G7gs81xziNgfaucyi7NO7_cfb3919cd2914dfba679e44ce8bbecdc.jpg","title":"GPT Image 2 API"},{"category":"llm","description":"Run any LLM with fal. Access Claude (Anthropic), ChatGPT / GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), DeepSeek, Llama (Meta), Qwen (Alibaba), Mistral, and 200+ more models through a single API. Supports reasoning, structured output, and streaming. Powered by OpenRouter.","endpoint_id":"openrouter/router","family":"Openrouter","inputs":[{"default":null,"description":"Prompt to be used for the chat completion","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"System prompt to provide context or instructions to the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Name of the model to use. Charged based on actual token usage.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":true,"type":"string"},{"default":false,"description":"Should reasoning be the part of the final answer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":1,"description":"This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Openrouter","output_kind":"json","output_props":["partial","error","usage","output","reasoning"],"pricing":"You will be charged based on the number of input and output tokens.","published_at":"2025-11-12T20:17:58.937000+00:00","thumbnail":"https://v3b.fal.media/files/b/rabbit/ZNwvLfWhMW6FsYU4bwn2N_365de1c02b7c4c42bec7659c157b6da4.jpg","title":"OpenRouter"},{"category":"unknown","description":"Run any audio capable LLM with fal. Process audio files — transcription, analysis, understanding, understand— using Gemini (Google) models. Supports wav, mp3, aiff, aac, ogg, flac, m4a. Powered by OpenRouter.","endpoint_id":"openrouter/router/audio","family":"Openrouter","inputs":[{"default":null,"description":"URL or data URI of the audio file to process. Supported formats: wav, mp3, aiff, aac, ogg, flac, m4a.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Prompt to be used for the audio processing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"System prompt to provide context or instructions to the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Name of the model to use. Charged based on actual token usage.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":true,"type":"string"},{"default":false,"description":"Should reasoning be the part of the final answer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":1,"description":"This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Openrouter","output_kind":"json","output_props":["usage","output"],"pricing":"You will be charged based on the number of input and output tokens.","published_at":"2025-12-22T17:15:42.947000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87593d/pDGPXXb694Rjgst08FkUa_60fe8689185944889b162dc64de6cffc.jpg","title":"OpenRouter [Audio]"},{"category":"llm","description":"Run any LLM (Large Language Model) with fal, powered by OpenRouter.","endpoint_id":"openrouter/router/enterprise","family":"","inputs":[{"default":null,"description":"Prompt to be used for the chat completion","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"System prompt to provide context or instructions to the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Name of the model to use. Charged based on actual token usage.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":true,"type":"string"},{"default":false,"description":"Should reasoning be the part of the final answer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":1,"description":"This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Openrouter","output_kind":"json","output_props":["partial","error","usage","output","reasoning"],"pricing":"You will be charged based on the number of input and output tokens.","published_at":"2026-06-23T22:00:07.809000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a876188/HOgaJbkaD8eI0aOITjbwz_511c32d7a4c14f4686fd7e88cd21e259.jpg","title":"OpenRouter [Enterprise]"},{"category":"video-to-text","description":"Run any video-capable LLM with fal. Analyze, summarize, and understand video files using Gemini (Google) models. Supports mp4, mpeg, mov, webm, and YouTube links. Powered by OpenRouter.","endpoint_id":"openrouter/router/video","family":"Openrouter","inputs":[{"default":null,"description":"List of URLs or data URIs of video files to process. Supported formats: mp4, mpeg, mov, webm. For Google Gemini on AI Studio, YouTube links are also supported. Mutually exclusive with video_url.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Prompt to be used for the video processing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"System prompt to provide context or instructions to the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Name of the model to use. Charged based on actual token usage.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":true,"type":"string"},{"default":false,"description":"Should reasoning be the part of the final answer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":1,"description":"This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Openrouter","output_kind":"json","output_props":["usage","output"],"pricing":"You will be charged based on the number of input and output tokens.","published_at":"2026-01-13T23:31:16.485000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a4887/4urYAt4UGIT4KfbwEdL6R_f0b95609b9e241468dbaf34bf3229f91.jpg","title":"OpenRouter [Video]"},{"category":"video-to-text","description":"Run any VLM (Video Language Model) with fal, powered by OpenRouter.","endpoint_id":"openrouter/router/video/enterprise","family":"Openrouter","inputs":[{"default":null,"description":"List of URLs or data URIs of video files to process. Supported formats: mp4, mpeg, mov, webm. For Google Gemini on AI Studio, YouTube links are also supported. Mutually exclusive with video_url.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Prompt to be used for the video processing","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"System prompt to provide context or instructions to the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Name of the model to use. Charged based on actual token usage.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":true,"type":"string"},{"default":false,"description":"Should reasoning be the part of the final answer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":1,"description":"This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Openrouter","output_kind":"json","output_props":["usage","output"],"pricing":"You will be charged based on the number of input and output tokens.","published_at":"2026-01-13T23:57:11.907000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a491c/S5EO4nTWCnQl8LBj3j-pb_d972f9018895443e8d8f7a4bb0f08050.jpg","title":"OpenRouter [Video][Enterprise]"},{"category":"vision","description":"Run any Vision Language Model with fal. Analyze and understand images using Claude (Anthropic), GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), Llama (Meta), Qwen, Pixtral (Mistral), and more. Send one or multiple images for captioning, analysis, OCR, or visual Q&A. Powered by OpenRouter.","endpoint_id":"openrouter/router/vision","family":"Openrouter","inputs":[{"default":null,"description":"List of image URLs to be processed","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Prompt to be used for the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"System prompt to provide context or instructions to the model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"system_prompt","required":false,"type":"string"},{"default":null,"description":"Name of the model to use. Charged based on actual token usage.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model","required":true,"type":"string"},{"default":false,"description":"Should reasoning be the part of the final answer.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"reasoning","required":false,"type":"boolean"},{"default":1,"description":"This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0,"multiline":false,"name":"temperature","required":false,"type":"number"},{"default":null,"description":"This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":1,"multiline":false,"name":"max_tokens","required":false,"type":"integer"}],"lab":"Openrouter","output_kind":"json","output_props":["usage","output"],"pricing":"You will be charged based on the number of input and output tokens.","published_at":"2025-11-12T20:20:52.668000+00:00","thumbnail":"https://v3b.fal.media/files/b/penguin/v-wl5CGbHxNVatcGXntIY_e14c7922d88348769a90469d1c206501.jpg","title":"OpenRouter [Vision]"},{"category":"vision","description":"Isaac-01 is a multimodal vision-language model from Perceptron for various vision language tasks.","endpoint_id":"perceptron/isaac-01","family":"Isaac 1","inputs":[{"default":null,"description":"Image URL to be processed","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Prompt to be used for the image","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"text","description":"Response style to be used for the image.\n\n- text: Model will output text. Good for descriptions and captioning.\n- box: Model will output a combination of text and bounding boxes. Good for\nlocalization.\n- point: Model will output a combination of text and points. Good for counting many\nobjects.\n- polygon: Model will output a combination of text and polygons. Good for granular\nsegmentation.","enum":["text","box","point","polygon"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"response_style","required":false,"type":"enum"}],"lab":"Perceptron","output_kind":"json","output_props":["usage","error","partial","output"],"pricing":"$0.26 per 1M input tokens, $2.17 per 1M output tokens","published_at":"2025-09-17T15:12:22.823000+00:00","thumbnail":"https://v3.fal.media/files/panda/nuuSn6Wf3q72FHqD8uppE_86098dbea31a439bb14ee16b29277afe.jpg","title":"Isaac 0.1"},{"category":"image-to-image","description":"Pixelcut’s Background Remover enables fast, ultra high-quality removal of backgrounds from images. Perfect for e-commerce and image editing workflows. Powered by advanced AI for clean, perfect cutouts every time.","endpoint_id":"pixelcut/background-removal","family":"","inputs":[{"default":null,"description":"Input image (JPEG or PNG)","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"rgba","description":"Output format","enum":["rgba","alpha","zip"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Pixelcut","output_kind":"image","output_props":["image","file"],"pricing":"","published_at":"2026-03-04T08:51:07.655000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8e11aa/gFKCEDWIuxTOpt8Yn8Igr_5b5e714fe11d4742b2cb3abaa13b589c.jpg","title":"Pixelcut Background Remover"},{"category":"video-to-video","description":"Pixelcut's Video Background Remover is an AI segmentation model that erases backgrounds frame by frame, with seamless temporal consistency.","endpoint_id":"pixelcut/video-background-removal","family":"","inputs":[{"default":null,"description":"URL of the input video","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"transparent","description":"Output background: transparent, a named preset color, or 'custom' to use the background_color color picker.","enum":["transparent","black","white","green","blue","magenta","custom"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background","required":false,"type":"enum"},{"default":null,"description":"Custom solid background color (only used when background='custom').","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"background_color","required":false,"type":"json"},{"default":null,"description":"Output video format. Auto-detected if not set (defaults to webm_vp9 for transparent).","enum":["webm_vp9","mp4_h264","mp4_h265","mov_proresks","mov_h265","mkv_h264","mkv_h265","mkv_vp9","gif"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Pixelcut","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.022 per 30 frames.","published_at":"2026-06-11T17:35:22.832000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9de071/4KSnVL4HHDmFy5Ty4paA7_83e32f5de65c4f8bbc5611c87c1defa4.jpg","title":"Pixelcut Video Background Removal"},{"category":"speech-to-speech","description":"Transform voices using Resemble AI's Chatterbox. Convert audio to new voices or your own samples, with expressive results and built-in perceptual watermarking.","endpoint_id":"resemble-ai/chatterboxhd/speech-to-speech","family":"Chatterbox","inputs":[{"default":null,"description":"URL to the source audio file to be voice-converted.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"source_audio_url","required":true,"type":"string"},{"default":null,"description":"The voice to use for the speech-to-speech request. If neither target_voice nor target_voice_audio_url are provided, a random target voice will be used.","enum":["Aurora","Blade","Britney","Carl","Cliff","Richard","Rico","Siobhan","Vicky"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"target_voice","required":false,"type":"enum"},{"default":null,"description":"URL to the audio file which represents the voice of the output audio. If provided, this will override the target_voice setting. If neither target_voice nor target_voice_audio_url are provided, the default target voice will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"target_voice_audio_url","required":false,"type":"string"},{"default":false,"description":"If True, the generated audio will be upscaled to 48kHz. The generation of the audio will take longer, but the quality will be higher. If False, the generated audio will be 24kHz.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"high_quality_audio","required":false,"type":"boolean"}],"lab":"Resemble AI","output_kind":"audio","output_props":["audio"],"pricing":"","published_at":"2025-06-02T19:21:41.438000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/chatterbox.webp","title":"Chatterboxhd"},{"category":"text-to-speech","description":"Generate expressive, natural speech with Resemble AI's Chatterbox. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.","endpoint_id":"resemble-ai/chatterboxhd/text-to-speech","family":"Chatterbox","inputs":[{"default":"My name is Maximus Decimus Meridius, commander of the Armies of the North, General of the Felix Legions and loyal servant to the true emperor, Marcus Aurelius. Father to a murdered son, husband to a murdered wife. And I will have my vengeance, in this life or the next.","description":"Text to synthesize into speech.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":false,"type":"string"},{"default":null,"description":"The voice to use for the TTS request. If neither voice nor audio are provided, a random voice will be used.","enum":["Aurora","Blade","Britney","Carl","Cliff","Richard","Rico","Siobhan","Vicky"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":null,"description":"URL to the audio sample to use as a voice prompt for zero-shot TTS voice cloning. Providing a audio sample will override the voice setting. If neither voice nor audio_url are provided, a random voice will be used.","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":0.5,"description":"Controls emotion exaggeration. Range typically 0.25 to 2.0.","enum":null,"is_list":false,"max":2,"media_kind":null,"min":0.25,"multiline":false,"name":"exaggeration","required":false,"type":"number"},{"default":0.5,"description":"Classifier-free guidance scale (CFG) controls the conditioning factor. Range typically 0.2 to 1.0. For expressive or dramatic speech, try lower cfg values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher. If the reference speaker has a fast speaking style, lowering cfg to around 0.3 can improve pacing.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"cfg","required":false,"type":"number"},{"default":false,"description":"If True, the generated audio will be upscaled to 48kHz. The generation of the audio will take longer, but the quality will be higher. If False, the generated audio will be 24kHz.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"high_quality_audio","required":false,"type":"boolean"},{"default":0,"description":"Useful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":0,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":0.8,"description":"Controls the randomness of generation. Range typically 0.05 to 5.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":0.05,"multiline":false,"name":"temperature","required":false,"type":"number"}],"lab":"Resemble AI","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.04 per 1000 characters.","published_at":"2025-06-02T19:16:12.548000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/chatterbox.webp","title":"Chatterboxhd"},{"category":"text-to-image","description":"Juggernaut Base Flux LoRA by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.","endpoint_id":"rundiffusion-fal/juggernaut-flux-lora","family":"Juggernaut","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","prompt","seed"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-lora.webp","title":"Juggernaut Flux Base LoRA"},{"category":"image-to-image","description":"Juggernaut Base Flux LoRA Inpainting by RunDiffusion is a drop-in replacement for Flux [Dev] inpainting that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.","endpoint_id":"rundiffusion-fal/juggernaut-flux-lora/inpainting","family":"Juggernaut","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate. This is always set to 1 for streaming output.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":"none","description":"Acceleration level for image generation. 'regular' balances speed and quality.","enum":["none","regular"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"acceleration","required":false,"type":"enum"},{"default":null,"description":"URL of image to use for inpainting. or img2img","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":0.85,"description":"The strength to use for inpainting/image-to-image. Only used if the image_url is provided. 1.0 is completely remakes the image while 0.0 preserves the original.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":null,"description":"The mask to area to Inpaint in.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"mask_url","required":true,"type":"string"}],"lab":"Rundiffusion","output_kind":"images","output_props":["images","has_nsfw_concepts","timings","prompt","seed"],"pricing":"","published_at":"2025-04-21T21:29:32.480000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-lora.webp","title":"Juggernaut Flux Lora"},{"category":"text-to-image","description":"Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.","endpoint_id":"rundiffusion-fal/juggernaut-flux/base","family":"Juggernaut","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-base.webp","title":"Juggernaut Flux Base"},{"category":"image-to-image","description":"Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.","endpoint_id":"rundiffusion-fal/juggernaut-flux/base/image-to-image","family":"Juggernaut","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-base.webp","title":"Juggernaut Flux Base"},{"category":"text-to-image","description":"Juggernaut Lightning Flux by RunDiffusion provides blazing-fast, high-quality images rendered at five times the speed of Flux. Perfect for mood boards and mass ideation, this model excels in both realism and prompt adherence.","endpoint_id":"rundiffusion-fal/juggernaut-flux/lightning","family":"Juggernaut","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":4,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":12,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-lightning.webp","title":"Juggernaut Flux Lightning"},{"category":"text-to-image","description":"Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.","endpoint_id":"rundiffusion-fal/juggernaut-flux/pro","family":"Juggernaut","inputs":[{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-pro.webp","title":"Juggernaut Flux Pro"},{"category":"image-to-image","description":"Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.","endpoint_id":"rundiffusion-fal/juggernaut-flux/pro/image-to-image","family":"Juggernaut","inputs":[{"default":null,"description":"The URL of the image to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":0.95,"description":"The strength of the initial image. Higher strength values are better for this model.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0.01,"multiline":false,"name":"strength","required":false,"type":"number"},{"default":40,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":10,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":20,"media_kind":null,"min":1,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"png","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["prompt","timings","seed","has_nsfw_concepts","images"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/juggernaut-flux-pro.webp","title":"Juggernaut Flux Pro"},{"category":"text-to-image","description":"RunDiffusion Photo Flux provides insane realism. With this enhancer, textures and skin details burst to life, turning your favorite prompts into vivid, lifelike creations. Recommended to keep it at 0.65 to 0.80 weight. Supports resolutions up to 1536x1536.","endpoint_id":"rundiffusion-fal/rundiffusion-photo-flux","family":"Juggernaut","inputs":[{"default":0.75,"description":"LoRA Scale of the photo lora model","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"photo_lora_scale","required":false,"type":"number"},{"default":null,"description":"The prompt to generate an image from.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":"landscape_4_3","description":"The size of the generated image.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":28,"description":"The number of inference steps to perform.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":null,"description":"The same seed and the same prompt given to the same version of the model\n            will output the same image every time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":"[]","description":"The LoRAs to use for the image generation. You can use any number of LoRAs\n            and they will be merged together to generate the final image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"loras","required":false,"type":"json"},{"default":3.5,"description":"The CFG (Classifier Free Guidance) scale is a measure of how close you want\n            the model to stick to your prompt when looking for a related image to show you.","enum":null,"is_list":false,"max":35,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":1,"description":"The number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"Rundiffusion","output_kind":"images","output_props":["prompt","images","timings","has_nsfw_concepts","seed"],"pricing":"","published_at":"2025-03-05T00:00:00+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/rundiffusion-photo-flux.webp","title":"Rundiffusion Photo Flux"},{"category":"image-to-image","description":"Rembg-enhance is optimized for 2D vector images, 3D graphics, and photos by leveraging matting technology.","endpoint_id":"smoretalk-ai/rembg-enhance","family":"","inputs":[{"default":null,"description":"URL of the input image","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Smoretalk AI","output_kind":"image","output_props":["image"],"pricing":"","published_at":"2025-05-09T03:29:12.011000+00:00","thumbnail":"https://v3.fal.media/files/tiger/k7u2IikPi0ubraTdzzOYz_smoretalk-ai-rembg-enhance-thumbnail.png","title":"Rembg Enhance (Remove Background Enhance)"},{"category":"text-to-audio","description":"Generates production-ready music from a single text prompt, with full control over style, mood, instrumentation, and exact duration.","endpoint_id":"sonilo/v1.1/text-to-music","family":"Sonilo v1.1","inputs":[{"default":null,"description":"Text prompt describing the music to generate.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":90,"description":"Requested output duration in seconds (max 600). Also used for billing (one billable unit per second per sample, rounded up).","enum":null,"is_list":false,"max":600,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":1,"description":"How many distinct music tracks to generate.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"}],"lab":"Sonilo","output_kind":"audio","output_props":["audio","audios"],"pricing":"Your request will cost $0.0025 per second of output and per sample.","published_at":"2026-06-03T18:40:52.042000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9cce58/2fkn-QJvDeqArMhlb66vr_9e400a7a1fd841f38bed933eeb6aa3fe.jpg","title":"Sonilo V1.1 Text to Music"},{"category":"video-to-audio","description":"Analyzes your video's pacing, mood, and timing to generate a frame-synced, commercial-ready soundtrack in seconds","endpoint_id":"sonilo/v1.1/video-to-music","family":"Sonilo v1.1","inputs":[{"default":null,"description":"Public http(s) URL of the source video to score.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":1,"description":"How many distinct music tracks to generate for the video.","enum":null,"is_list":false,"max":3,"media_kind":null,"min":1,"multiline":false,"name":"num_samples","required":false,"type":"integer"},{"default":null,"description":"Optional text prompt steering the musical style. If omitted, a prompt is generated automatically from the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":false,"type":"string"},{"default":null,"description":"Optional. Start scoring from this offset (seconds) into the video. Requires Start Offset + Duration <= Video Duration.","enum":null,"is_list":false,"max":600,"media_kind":null,"min":0,"multiline":false,"name":"start_offset","required":false,"type":"number"},{"default":null,"description":"Optional. Length (seconds) of the video segment to score. When set, scores a segment of this length starting at Start Offset (or from the beginning if Start Offset is unset). Defaults (None) to the rest of the video: the whole video when Start Offset is unset, or from Start Offset to the end when it is set.","enum":null,"is_list":false,"max":600,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"number"}],"lab":"Sonilo","output_kind":"audio","output_props":["audio","audios"],"pricing":"Your request will cost $0.009 per second of output and per sample.","published_at":"2026-06-03T18:40:46.335000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fa5/jHE-xiu94lGuFQ6TRzyJ0_42eae911d4d0441e91d0e870274c4898.jpg","title":"V1.1"},{"category":"image-to-3d","description":"Generate high-quality 3D models from a single image using Tripo H3.1.","endpoint_id":"tripo3d/h3.1/image-to-3d","family":"Tripo H3.1","inputs":[{"default":null,"description":"URL of the input image for 3D model creation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Target number of faces for the generated mesh. If not set, the model adaptively determines the count.","enum":null,"is_list":false,"max":2000000,"media_kind":null,"min":1000,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":true,"description":"Whether to generate textures for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate PBR (Physically Based Rendering) materials. If true, texture is also enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pbr","required":false,"type":"boolean"},{"default":null,"description":"Seed for geometry generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_seed","required":false,"type":"integer"},{"default":null,"description":"Seed for texture generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_seed","required":false,"type":"integer"},{"default":"standard","description":"Quality level for textures. 'detailed' produces higher-resolution textures.","enum":["standard","detailed"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_quality","required":false,"type":"enum"},{"default":"standard","description":"Quality level for geometry.","enum":["standard","detailed"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_quality","required":false,"type":"enum"},{"default":"original_image","description":"How textures are aligned. 'original_image' aligns to input image, 'geometry' aligns to generated geometry.","enum":["original_image","geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_alignment","required":false,"type":"enum"},{"default":false,"description":"Auto-scale the model to real-world dimensions (meters).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_size","required":false,"type":"boolean"},{"default":"default","description":"Model orientation. 'align_image' auto-rotates to match the input image.","enum":["default","align_image"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"orientation","required":false,"type":"enum"},{"default":false,"description":"Generate quad (4-sided) mesh topology instead of triangles. When Tripo emits FBX bytes for quad output, the returned model file is FBX.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quad","required":false,"type":"boolean"}],"lab":"Tripo3D","output_kind":"file","output_props":["model_urls","rendered_image","model_mesh"],"pricing":"Your request will cost $0.20 (without textures), $0.30 (with standard textures), or $0.40 (with HD textures), plus an additional $0.20 for detailed geometry and $0.05 for quad mesh if selected.","published_at":"2026-04-15T18:24:28.326000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a95559a/DXp1uAfHvZsXt-GJ9-Bp-_47060336be0749d5bd751ca6359cd2f9.jpg","title":"Tripo H3.1 Image to 3D"},{"category":"image-to-3d","description":"Generate 3D models from multiple view images using Tripo H3.1.","endpoint_id":"tripo3d/h3.1/multiview-to-3d","family":"Tripo H3.1","inputs":[{"default":null,"description":"2 to 4 image URLs of the same object from different angles. Order: [front, left, back, right]. Front view is required.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":true,"type":"string"},{"default":null,"description":"Target number of faces for the generated mesh. If not set, the model adaptively determines the count.","enum":null,"is_list":false,"max":2000000,"media_kind":null,"min":1000,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":true,"description":"Whether to generate textures for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate PBR (Physically Based Rendering) materials. If true, texture is also enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pbr","required":false,"type":"boolean"},{"default":null,"description":"Seed for geometry generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_seed","required":false,"type":"integer"},{"default":null,"description":"Seed for texture generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_seed","required":false,"type":"integer"},{"default":"standard","description":"Quality level for textures.","enum":["standard","detailed"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_quality","required":false,"type":"enum"},{"default":"standard","description":"Quality level for geometry.","enum":["standard","detailed"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_quality","required":false,"type":"enum"},{"default":"original_image","description":"How textures are aligned.","enum":["original_image","geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_alignment","required":false,"type":"enum"},{"default":false,"description":"Auto-scale the model to real-world dimensions (meters).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_size","required":false,"type":"boolean"},{"default":"default","description":"Model orientation.","enum":["default","align_image"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"orientation","required":false,"type":"enum"},{"default":false,"description":"Generate quad (4-sided) mesh topology instead of triangles. When Tripo emits FBX bytes for quad output, the returned model file is FBX.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quad","required":false,"type":"boolean"}],"lab":"Tripo3D","output_kind":"file","output_props":["model_urls","rendered_image","model_mesh"],"pricing":"Your request will cost $0.10 (without textures), $0.20 (with standard textures), or $0.30 (with HD textures), plus an additional $0.20 for detailed geometry and $0.05 for quad mesh if selected.","published_at":"2026-04-15T18:24:49.403000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a95559a/U1mXxU33GmFb4hpddFBT9_ebaf264db7864aa38096b36738fd4c8c.jpg","title":"Tripo H3.1 Multiview to 3D"},{"category":"text-to-3d","description":"Generate 3D models from text descriptions using Tripo H3.1.","endpoint_id":"tripo3d/h3.1/text-to-3d","family":"Tripo H3.1","inputs":[{"default":null,"description":"Text description of the 3D object to generate. Maximum 1024 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Text describing features to avoid in the generated model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Target number of faces for the generated mesh. If not set, the model adaptively determines the count.","enum":null,"is_list":false,"max":2000000,"media_kind":null,"min":1000,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":true,"description":"Whether to generate textures for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate PBR (Physically Based Rendering) materials. If true, texture is also enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pbr","required":false,"type":"boolean"},{"default":null,"description":"Seed for geometry generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_seed","required":false,"type":"integer"},{"default":null,"description":"Seed for the text-to-image step.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_seed","required":false,"type":"integer"},{"default":null,"description":"Seed for texture generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_seed","required":false,"type":"integer"},{"default":"standard","description":"Quality level for textures. 'detailed' produces higher-resolution textures.","enum":["standard","detailed"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_quality","required":false,"type":"enum"},{"default":"standard","description":"Quality level for geometry.","enum":["standard","detailed"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"geometry_quality","required":false,"type":"enum"},{"default":false,"description":"Auto-scale the model to real-world dimensions (meters).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_size","required":false,"type":"boolean"},{"default":false,"description":"Generate quad (4-sided) mesh topology instead of triangles. When Tripo emits FBX bytes for quad output, the returned model file is FBX.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quad","required":false,"type":"boolean"}],"lab":"Tripo3D","output_kind":"file","output_props":["model_urls","rendered_image","model_mesh"],"pricing":"Your request will cost $0.10 (without textures), $0.20 (with standard textures), or $0.30 (with HD textures), plus an additional $0.20 for detailed geometry and $0.05 for quad mesh if selected.","published_at":"2026-04-15T18:24:37.074000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a95559a/M9VA3cYkl8K_pUsuQYiQz_992bf220fed24835892f1abe3027c871.jpg","title":"Tripo H3.1 Text to 3D"},{"category":"image-to-3d","description":"Generate 3D models from a single image using Tripo P1.","endpoint_id":"tripo3d/p1/image-to-3d","family":"Tripo P1","inputs":[{"default":null,"description":"URL of the input image for 3D model creation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Target number of faces for the generated mesh. If not set, the model adaptively determines the count.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":48,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":true,"description":"Whether to generate textures for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"boolean"},{"default":null,"description":"Seed for geometry generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_seed","required":false,"type":"integer"}],"lab":"Tripo3D","output_kind":"file","output_props":["model_urls","rendered_image","model_mesh"],"pricing":"Your request will cost $0.40 (without textures) or $0.50 (with textures).","published_at":"2026-04-15T18:23:58.905000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9555d8/5Ofas7tl8rqFeF9Ql9N_7_8c7b86b5319b4c9daab2d1743920a7fa.jpg","title":"Tripo P1 Image to 3D"},{"category":"text-to-3d","description":"Generate 3D models from text descriptions using Tripo P1.","endpoint_id":"tripo3d/p1/text-to-3d","family":"Tripo P1","inputs":[{"default":null,"description":"Text description of the 3D object to generate. Maximum 1024 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Target number of faces for the generated mesh. If not set, the model adaptively determines the count.","enum":null,"is_list":false,"max":20000,"media_kind":null,"min":48,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":true,"description":"Whether to generate textures for the model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"boolean"},{"default":null,"description":"Seed for geometry generation reproducibility.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"model_seed","required":false,"type":"integer"}],"lab":"Tripo3D","output_kind":"file","output_props":["model_urls","rendered_image","model_mesh"],"pricing":"","published_at":"2026-04-15T18:24:09.919000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9555d9/Iy0IDz5o0s5iyWHXMdnPQ_90e6f4ac24554af68acf654d79f36db3.jpg","title":"Tripo P1 Text to 3D"},{"category":"image-to-3d","description":"State of the art Image to 3D Object generation. Generate 3D model from a single image!","endpoint_id":"tripo3d/tripo/v2.5/image-to-3d","family":"Tripo 2.5","inputs":[{"default":null,"description":"This is the random seed for model generation. The seed controls the geometry generation process, ensuring identical models when the same seed is used. This parameter is an integer and is randomly chosen if not set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Limits the number of faces on the output model. If this option is not set, the face limit will be adaptively determined.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":false,"description":"A boolean option to enable pbr. The default value is True, set False to get a model without pbr. If this option is set to True, texture will be ignored and used as True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pbr","required":false,"type":"boolean"},{"default":"standard","description":"An option to enable texturing. Default is 'standard', set 'no' to get a model without any textures, and set 'HD' to get a model with hd quality textures.","enum":["no","standard","HD"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"enum"},{"default":null,"description":"This is the random seed for texture generation. Using the same seed will produce identical textures. This parameter is an integer and is randomly chosen if not set. If you want a model with different textures, please use same seed and different texture_seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_seed","required":false,"type":"integer"},{"default":false,"description":"Automatically scale the model to real-world dimensions, with the unit in meters. The default value is False.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_size","required":false,"type":"boolean"},{"default":null,"description":"[DEPRECATED] Defines the artistic style or transformation to be applied to the 3D model, altering its appearance according to preset options (extra $0.05 per generation). Omit this option to keep the original style and apperance.","enum":["person:person2cartoon","object:clay","object:steampunk","animal:venom","object:barbie","object:christmas","gold","ancient_bronze"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":false,"description":"Set True to enable quad mesh output (extra $0.05 per generation). If quad=True and face_limit is not set, the default face_limit will be 10000. Note: Enabling this option will force the output to be an FBX model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quad","required":false,"type":"boolean"},{"default":"original_image","description":"Determines the prioritization of texture alignment in the 3D model. The default value is original_image.","enum":["original_image","geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_alignment","required":false,"type":"enum"},{"default":"default","description":"Set orientation=align_image to automatically rotate the model to align the original image. The default value is default.","enum":["default","align_image"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"orientation","required":false,"type":"enum"},{"default":null,"description":"URL of the image to use for model generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"Tripo3D","output_kind":"file","output_props":["rendered_image","base_model","pbr_model","task_id","model_mesh"],"pricing":"Your request will cost $0.2 (without textures), $0.3 (with standard textures), or $0.4 (with HD textures), plus an additional $0.05 each for Style and quad options if selected.","published_at":"2025-04-25T18:54:01.400000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/tripo-image-to-3d.webp","title":"Tripo3D"},{"category":"image-to-3d","description":"State of the art Multiview to 3D Object generation. Generate 3D models from multiple images!","endpoint_id":"tripo3d/tripo/v2.5/multiview-to-3d","family":"Tripo 2.5","inputs":[{"default":null,"description":"This is the random seed for model generation. The seed controls the geometry generation process, ensuring identical models when the same seed is used. This parameter is an integer and is randomly chosen if not set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":null,"description":"Limits the number of faces on the output model. If this option is not set, the face limit will be adaptively determined.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"face_limit","required":false,"type":"integer"},{"default":false,"description":"A boolean option to enable pbr. The default value is True, set False to get a model without pbr. If this option is set to True, texture will be ignored and used as True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"pbr","required":false,"type":"boolean"},{"default":"standard","description":"An option to enable texturing. Default is 'standard', set 'no' to get a model without any textures, and set 'HD' to get a model with hd quality textures.","enum":["no","standard","HD"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture","required":false,"type":"enum"},{"default":null,"description":"This is the random seed for texture generation. Using the same seed will produce identical textures. This parameter is an integer and is randomly chosen if not set. If you want a model with different textures, please use same seed and different texture_seed.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_seed","required":false,"type":"integer"},{"default":false,"description":"Automatically scale the model to real-world dimensions, with the unit in meters. The default value is False.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"auto_size","required":false,"type":"boolean"},{"default":null,"description":"[DEPRECATED] Defines the artistic style or transformation to be applied to the 3D model, altering its appearance according to preset options (extra $0.05 per generation). Omit this option to keep the original style and apperance.","enum":["person:person2cartoon","object:clay","object:steampunk","animal:venom","object:barbie","object:christmas","gold","ancient_bronze"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"style","required":false,"type":"enum"},{"default":false,"description":"Set True to enable quad mesh output (extra $0.05 per generation). If quad=True and face_limit is not set, the default face_limit will be 10000. Note: Enabling this option will force the output to be an FBX model.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"quad","required":false,"type":"boolean"},{"default":"original_image","description":"Determines the prioritization of texture alignment in the 3D model. The default value is original_image.","enum":["original_image","geometry"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"texture_alignment","required":false,"type":"enum"},{"default":"default","description":"Set orientation=align_image to automatically rotate the model to align the original image. The default value is default.","enum":["default","align_image"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"orientation","required":false,"type":"enum"},{"default":null,"description":"Front view image of the object.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"front_image_url","required":true,"type":"string"},{"default":null,"description":"Left view image of the object.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"left_image_url","required":false,"type":"string"},{"default":null,"description":"Back view image of the object.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"back_image_url","required":false,"type":"string"},{"default":null,"description":"Right view image of the object.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"right_image_url","required":false,"type":"string"}],"lab":"Tripo3D","output_kind":"file","output_props":["rendered_image","base_model","pbr_model","task_id","model_mesh"],"pricing":"Your request will cost $0.2 (without textures), $0.3 (with standard textures), or $0.4 (with HD textures), plus an additional $0.05 each for Style and quad options if selected.","published_at":"2025-06-18T08:56:32.461000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9f922c/RX98se6CNyskvVJVV4yMj_oFMwwAhM.png","title":"Tripo3D"},{"category":"image-to-3d","description":"TripoSplat is an open-source model from TripoAI / VAST AI Research that converts a single 2D image into high-quality 3D Gaussians using a novel learned density-control approach","endpoint_id":"tripo3d/triposplat","family":"","inputs":[{"default":null,"description":"URL of the input image to convert into a 3D Gaussian splat.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":262144,"description":"Target number of Gaussians in the output splat. Higher means more detail but larger files and slower rendering. Rounded to the nearest multiple of 32 internally.","enum":null,"is_list":false,"max":262144,"media_kind":null,"min":32768,"multiline":false,"name":"num_gaussians","required":false,"type":"integer"},{"default":20,"description":"Number of flow-matching sampler steps. More steps improve fidelity with a roughly linear runtime cost.","enum":null,"is_list":false,"max":50,"media_kind":null,"min":1,"multiline":false,"name":"num_inference_steps","required":false,"type":"integer"},{"default":3,"description":"Classifier-free guidance strength. Values at or below 1.0 disable guidance; higher values increase detail and adherence to the input image, but too high can oversaturate colors.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":0,"multiline":false,"name":"guidance_scale","required":false,"type":"number"},{"default":"ply","description":"File format for the generated Gaussian splat.","enum":["ply","splat"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is generated.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable safety checking of the input image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Tripo3D","output_kind":"file","output_props":["num_gaussians","timings","preprocessed_image","model_mesh","seed"],"pricing":"","published_at":"2026-06-03T21:25:03.135000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9cd62a/5MiqHVAziRLKtEWtbx28J_957c1708b50a4caea905d4842f3bfd30.jpg","title":"Triposplat"},{"category":"audio-to-video","description":"Generate high-quality videos with UGC-like avatars from audio","endpoint_id":"veed/avatars/audio-to-video","family":"Avatars","inputs":[{"default":null,"description":"The avatar to use for the video","enum":["emily_vertical_primary","emily_vertical_secondary","marcus_vertical_primary","marcus_vertical_secondary","mira_vertical_primary","mira_vertical_secondary","jasmine_vertical_primary","jasmine_vertical_secondary","jasmine_vertical_walking","aisha_vertical_walking","elena_vertical_primary","elena_vertical_secondary","any_male_vertical_primary","any_female_vertical_primary","any_male_vertical_secondary","any_female_vertical_secondary","any_female_vertical_walking","emily_primary","emily_side","marcus_primary","marcus_side","aisha_walking","elena_primary","elena_side","any_male_primary","any_female_primary","any_male_side","any_female_side"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"avatar_id","required":true,"type":"enum"},{"default":null,"description":"Audio Url","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-05-28T14:17:50.831000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/veed_logo.webp","title":"Avatars"},{"category":"text-to-video","description":"Generate high-quality videos with UGC-like avatars from text","endpoint_id":"veed/avatars/text-to-video","family":"Avatars","inputs":[{"default":null,"description":"The avatar to use for the video","enum":["emily_vertical_primary","emily_vertical_secondary","marcus_vertical_primary","marcus_vertical_secondary","mira_vertical_primary","mira_vertical_secondary","jasmine_vertical_primary","jasmine_vertical_secondary","jasmine_vertical_walking","aisha_vertical_walking","elena_vertical_primary","elena_vertical_secondary","any_male_vertical_primary","any_female_vertical_primary","any_male_vertical_secondary","any_female_vertical_secondary","any_female_vertical_walking","emily_primary","emily_side","marcus_primary","marcus_side","aisha_walking","elena_primary","elena_side","any_male_primary","any_female_primary","any_male_side","any_female_side"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"avatar_id","required":true,"type":"enum"},{"default":null,"description":"Text","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-05-28T14:20:10.759000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/veed_logo.webp","title":"Avatars"},{"category":"image-to-video","description":"VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video","endpoint_id":"veed/fabric-1.0","family":"Fabric 1","inputs":[{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Audio Url","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Resolution","enum":["720p","480p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":true,"type":"enum"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"480p - $0.08 per second, 720p - $0.15 per second","published_at":"2025-09-19T22:01:20.442000+00:00","thumbnail":"https://v3.fal.media/files/zebra/t3xqW_dkjrcRc2vmUS0EN_10a217d1a5ba4488be7bb1967189ef65.jpg","title":"Fabric 1.0"},{"category":"image-to-video","description":"VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video","endpoint_id":"veed/fabric-1.0/fast","family":"Fabric 1","inputs":[{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Audio Url","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"},{"default":null,"description":"Resolution","enum":["720p","480p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":true,"type":"enum"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"480p - $0.10 per second, 720p - $0.20 per second","published_at":"2025-10-01T14:00:46.685000+00:00","thumbnail":"https://v3.fal.media/files/zebra/AGRvOvMtrM0o02wz8-hRF_cb5739a5199b49a7971c5319881c6765.jpg","title":"Fabric 1.0 Fast"},{"category":"text-to-video","description":"VEED Fabric 1.0 text-to-video API","endpoint_id":"veed/fabric-1.0/text","family":"Fabric 1","inputs":[{"default":null,"description":"Image Url","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"Text","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":null,"description":"Optional additional voice description. The primary voice description is auto-generated from the image. You can use simple descriptors like 'British accent' or 'Confident' or provide a detailed description like 'Confident male voice, mid-20s, with notes of...'","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"voice_description","required":false,"type":"string"},{"default":null,"description":"Resolution","enum":["720p","480p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":true,"type":"enum"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"480p - $0.08 per second, 720p - $0.15 per second","published_at":"2025-12-12T15:22:12.764000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a860513/IhQfhGTiM994lkg1kPlOX_4836a8df5844488399dc1205ef3cc083.jpg","title":"Fabric 1.0"},{"category":"video-to-video","description":"Generate realistic lipsync from any audio using VEED's latest model","endpoint_id":"veed/lipsync","family":"Lipsync","inputs":[{"default":null,"description":"Video Url","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Audio Url","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":false,"name":"audio_url","required":true,"type":"string"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"","published_at":"2025-05-28T16:17:01.408000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/gallery/veed_logo.webp","title":"Lipsync"},{"category":"video-to-video","description":"VEED’s Subtitles API transforms raw footage into polished, publish-ready content with professional burned-in subtitles starting at a base rate of $0.10 per minute.","endpoint_id":"veed/subtitles","family":"Subtitles","inputs":[{"default":null,"description":"Upload or paste a URL to the video you want to subtitle.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":null,"description":"Each style defines fonts, colors, layout, and animation. Two tiers with different pricing:\n\n- Dynamic presets (2x multiplier): glass, whisper, glide2, fusion, glide, terminal, handwritten, backdrop, backdrop2. Richer, context-aware rendering that adapts to the input.\n- Basic presets (1x multiplier): simple, plain, beans, corpo, boo, shadeplay, casper, capri, lowkey, vinta, diego, ali, slay, kitty, hustle, karl, sprout, flex, mint, rizz, vegas. Fixed, lightweight styling with predictable output.","enum":["glass","whisper","glide2","fusion","glide","terminal","handwritten","backdrop","backdrop2","simple","plain","beans","corpo","boo","shadeplay","casper","capri","lowkey","vinta","diego","ali","slay","kitty","hustle","karl","sprout","flex","mint","rizz","vegas"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"preset","required":true,"type":"enum"},{"default":null,"description":"Improves transcription accuracy, and should match the source audio (not output subtitles).","enum":["af-ZA","am-ET","ar-AE","ar-BH","ar-DZ","ar-EG","ar-IL","ar-IQ","ar-JO","ar-KW","ar-LB","ar-MA","ar-OM","ar-PS","ar-QA","ar-SA","ar-TN","ast-ES","az-AZ","ba","bas","be-BY","bg-BG","br","bs-BA","ca-ES","ceb-PH","ckb-IQ","cs-CZ","cy-GB","da-DK","de-DE","dyu","el-GR","en-AU","en-GB","en-IN","en-NZ","en-US","eo","es-AR","es-BO","es-CL","es-CO","es-CR","es-DO","es-EC","es-ES","es-GT","es-HN","es-MX","es-NI","es-PA","es-PE","es-PR","es-PY","es-SV","es-US","es-UY","es-VE","et-EE","eu-ES","fa-IR","ff","fi-FI","fil-PH","fo","fr-CA","fr-FR","fy","ga","gd","gl-ES","ha-NG","haw","he-IL","hr-HR","hsb","ht","hu-HU","hy-AM","id-ID","ig","is-IS","it-IT","ja-JP","ja-Latn-JP","jv-ID","ka-GE","kab","kam-KE","kea-CV","kk-KZ","ko-KR","ku","ky-KG","la","lb-LU","lg","lij","ln-CD","lo-LA","lt-LT","luo-KE","lv-LV","mg","mi-NZ","mk-MK","mn-MN","ms-MY","mt-MT","nb-NO","nl-NL","nn","nso-ZA","ny-MW","oc-FR","pl-PL","ps-AF","pt-BR","pt-PT","ro-RO","roh","ru-RU","rw-RW","sah","sk-SK","sl-SI","sm","sn-ZW","so-SO","sq-AL","sr-Latn-RS","sr-RS","srd","ss","su-ID","sv-SE","sw-KE","sw-TZ","tg-TJ","th-TH","tk","tn","tok","ton","tr-TR","ts-ZA","tt","uk-UA","umb-AO","ur-IN","ur-PK","uz-UZ","vi-VN","vro","wo-SN","xh-ZA","yi","yo-NG","yue-Hant-HK","zh","zh-HK","zh-TW","zu-ZA"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":null,"description":"Translate the subtitles into this language. Omit to keep the original spoken language. If you also pass srt_content or srt_file_url, set `language` to its source language for the most reliable translation.","enum":["ab","ace","ach","af-ZA","ak","alz","am-ET","ar-AE","ar-BH","ar-DZ","ar-EG","ar-IL","ar-IQ","ar-JO","ar-KW","ar-LB","ar-MA","ar-OM","ar-PS","ar-QA","ar-SA","ar-TN","awa","ay","az-AZ","ban","bbc","be-BY","bem","bew","bg-BG","bho","bik","bm","bs-BA","bts","btx","bua","ca-ES","ceb-PH","cgg","chm","ckb-IQ","cnh","co","crh","crs","cs-CZ","cv","cy-GB","da-DK","de-DE","din","doi","dov","dv","dz","ee","el-GR","en-AU","en-GB","en-IN","en-NZ","en-US","eo","es-AR","es-BO","es-CL","es-CO","es-CR","es-DO","es-EC","es-ES","es-GT","es-HN","es-MX","es-NI","es-PA","es-PE","es-PR","es-PY","es-SV","es-US","es-UY","es-VE","et-EE","eu-ES","fa-IR","ff","fi-FI","fil-PH","fj","fr-CA","fr-FR","fy","ga","gaa","gd","gl-ES","gn","gom","ha-NG","haw","he-IL","hil","hmn","hr-HR","hrx","ht","hu-HU","hy-AM","id-ID","ig","ilo","is-IS","it-IT","ja-JP","ja-Latn-JP","jv-ID","ka-GE","kk-KZ","ko-KR","kri","ktu","ku","ky-KG","la","lb-LU","lg","li","lij","lmo","ln-CD","lo-LA","lt-LT","ltg","luo-KE","lus","lv-LV","mai","mak","mg","mi-NZ","min","mk-MK","mn-MN","mni-Mtei","ms-Arab","ms-MY","mt-MT","nb-NO","new","nl-NL","nr","nso-ZA","nus","ny-MW","oc-FR","om","pag","pam","pap","pl-PL","ps-AF","pt-BR","pt-PT","qu","rn","ro-RO","rom","ru-RU","rw-RW","scn","sg","shn","sk-SK","sl-SI","sm","sn-ZW","so-SO","sq-AL","sr-Latn-RS","sr-RS","ss","st","su-ID","sv-SE","sw-KE","sw-TZ","szl","tet","tg-TJ","th-TH","ti","tk","tn","tr-TR","ts-ZA","tt","ug","uk-UA","ur-IN","ur-PK","uz-UZ","vi-VN","xh-ZA","yi","yo-NG","yua","yue-Hant-HK","zh","zh-HK","zh-TW","zu-ZA"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"translation_language","required":false,"type":"enum"},{"default":null,"description":"Upload or paste a URL to your .srt subtitles file. When provided, transcription is skipped.","enum":null,"is_list":false,"max":null,"media_kind":"file","min":null,"multiline":false,"name":"srt_file_url","required":false,"type":"string"},{"default":null,"description":"Paste raw SRT subtitle text. Alternative to srt_file_url. When provided, transcription is skipped.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"srt_content","required":false,"type":"string"},{"default":null,"description":"Optional list of terms to help auto-transcription correctly recognise brand names and domain jargon that providers commonly mis-spell (e.g. \"VEED\" → \"vid\"). Ignored when srt_content / srt_file_url is set.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"vocabulary","required":false,"type":"json"},{"default":null,"description":"Optional preset overrides: vertical position, shadow intensity, and per-tier text styling (font, weight, hex colour) for each word-importance tier. Any omitted field keeps the preset's default.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"customization","required":false,"type":"json"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.10 per minute of input video, with a 2x multiplier for resolutions above 1080p and a 2x multiplier for dynamic styling. Setting a translation_language adds a flat +$0.20 / minute surcharge on top. Minimum charge: 1 minute.","published_at":"2026-05-18T09:03:09.763000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9abb98/lM8WGbJkKyFl5iABMR-3q_3192a25aba5c4ec7895cc8f2ac48f841.jpg","title":"Subtitles"},{"category":"video-to-video","description":"Remove background from any video with people and objects. No green screen needed.","endpoint_id":"veed/video-background-removal","family":"","inputs":[{"default":null,"description":"Video Url","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"vp9","description":"Single VP9 video with alpha channel or two videos (rgb and alpha) in H264 format. H264 is recommended for better RGB quality.","enum":["vp9","h264"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_codec","required":false,"type":"enum"},{"default":true,"description":"Improves the quality of the extracted object's edges.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refine_foreground_edges","required":false,"type":"boolean"},{"default":true,"description":"Set to False if the subject is not a person.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subject_is_person","required":false,"type":"boolean"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.0225 per 30 frames (Refine Foreground Edges: ON) / $0.015 (Refine: OFF).","published_at":"2025-11-28T16:15:50.575000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8493a9/Oi0ou1tpONWDl5MQg1Ior_04bb265985a24a558bc3adae79407610.jpg","title":"Video Background Removal"},{"category":"video-to-video","description":"Remove background from any video with people and objects. No green screen needed.","endpoint_id":"veed/video-background-removal/fast","family":"","inputs":[{"default":null,"description":"Video Url","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"vp9","description":"Single VP9 video with alpha channel or two videos (rgb and alpha) in H264 format. H264 is recommended for better RGB quality.","enum":["vp9","h264"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_codec","required":false,"type":"enum"},{"default":true,"description":"Improves the quality of the extracted object's edges.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"refine_foreground_edges","required":false,"type":"boolean"},{"default":true,"description":"Set to False if the subject is not a person.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"subject_is_person","required":false,"type":"boolean"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.012 per 30 frames (Refine Foreground Edges: ON) / $0.008 cents (Refine: OFF).","published_at":"2025-12-01T13:33:43.631000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a848f46/fPWWIeh4BRaiUufOGPa1i_2e9706df51e1437d867dfe9eb5b4f854.jpg","title":"Video Background Removal"},{"category":"video-to-video","description":"Remove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges.","endpoint_id":"veed/video-background-removal/green-screen","family":"","inputs":[{"default":null,"description":"Video Url","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":"vp9","description":"Single VP9 video with alpha channel or two videos (rgb and alpha) in H264 format. H264 is recommended for better RGB quality.","enum":["vp9","h264"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_codec","required":false,"type":"enum"},{"default":0.8,"description":"Increase the value if green spots remain in the video, decrease if color changes are noticed on the extracted subject.","enum":null,"is_list":false,"max":1,"media_kind":null,"min":0,"multiline":false,"name":"spill_suppression_strength","required":false,"type":"number"}],"lab":"Veed","output_kind":"video","output_props":["video"],"pricing":"Your request will cost $0.025 per 30 frames.","published_at":"2025-11-28T16:14:11.401000+00:00","thumbnail":"https://v3b.fal.media/files/b/kangaroo/2dnJmbIsYHIB4aBpIgI0L_0044788dd750470589b08c44e7dc1087.jpg","title":"Video Background Removal"},{"category":"image-to-image","description":"Wan 2.6 image-to-image model.","endpoint_id":"wan/v2.6/image-to-image","family":"Wan 2.6","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters. Example: 'Generate an image using the style of image 1 and background of image 2'.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-5000px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":true,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":"square_hd","description":"Output image size. Use presets like 'square_hd', 'landscape_16_9', 'portrait_9_16', or specify exact dimensions with ImageSize(width=1280, height=720). Total pixels must be between 768*768 and 1280*1280.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Number of images to generate (1-4). Directly affects billing cost.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":true,"description":"Enable LLM prompt optimization. Significantly improves results for simple prompts but adds 3-4 seconds processing time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility (0-2147483647). Same seed produces more consistent results.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"images","output_props":["seed","images"],"pricing":"","published_at":"2025-12-23T21:00:06.432000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a87803a/zQUa6Yt1AHEqQjqgXBNNe.png","title":"Wan v2.6 Image to Image"},{"category":"image-to-video","description":"Wan 2.6 image-to-video model.","endpoint_id":"wan/v2.6/image-to-video","family":"Wan 2.6","inputs":[{"default":null,"description":"The text prompt describing the desired video motion. Max 1500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame. Must be publicly accessible or base64 data URI. Image dimensions must be between 240 and 7680.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the audio to use as the background music. Must be publicly accessible.\nLimit handling: If the audio duration exceeds the duration value (5, 10, or 15 seconds),\nthe audio is truncated to the first N seconds, and the rest is discarded. If\nthe audio is shorter than the video, the remaining part of the video will be silent.\nFor example, if the audio is 3 seconds long and the video duration is 5 seconds, the\nfirst 3 seconds of the output video will have sound, and the last 2 seconds will be si","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"1080p","description":"Video resolution. Valid values: 720p, 1080p","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. Choose between 5, 10 or 15 seconds.","enum":["5","10","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"When true, enables intelligent multi-shot segmentation. Only active when enable_prompt_expansion is True. Set to false for single-shot generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_shots","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","actual_prompt","video"],"pricing":"Your request will cost  $0.10 per second for 720p, $0.15 per second for 1080p.","published_at":"2025-12-15T17:25:59.831000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86d2e1/KF3SBRRkzqdothbEr6ANe.png","title":"Wan v2.6 Image to Video"},{"category":"image-to-video","description":"Wan 2.6 image-to-video flash model.","endpoint_id":"wan/v2.6/image-to-video/flash","family":"Wan 2.6","inputs":[{"default":null,"description":"The text prompt describing the desired video motion. Max 1500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the image to use as the first frame. Must be publicly accessible or base64 data URI. Image dimensions must be between 240 and 7680.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":true,"type":"string"},{"default":null,"description":"URL of the audio to use as the background music. Must be publicly accessible.\nLimit handling: If the audio duration exceeds the duration value (5, 10, or 15 seconds),\nthe audio is truncated to the first N seconds, and the rest is discarded. If\nthe audio is shorter than the video, the remaining part of the video will be silent.\nFor example, if the audio is 3 seconds long and the video duration is 5 seconds, the\nfirst 3 seconds of the output video will have sound, and the last 2 seconds will be si","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"1080p","description":"Video resolution. Valid values: 720p, 1080p","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. Choose between 5, 10 or 15 seconds.","enum":["5","10","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":false,"description":"When true, enables intelligent multi-shot segmentation. Only active when enable_prompt_expansion is True. Set to false for single-shot generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_shots","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"},{"default":true,"description":"Whether the model generates native audio for the video. Set to false for silent video generation, which is cheaper (half as much as a flash generation with audio)Independent of audio_url, which only provides a track to sync the video against.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["seed","actual_prompt","video"],"pricing":"Your request will cost  $0.05 per second for 720p, $0.075 per second for 1080p.","published_at":"2026-01-18T08:06:36.211000+00:00","thumbnail":"https://storage.googleapis.com/falserverless/model_tests/video_models/Gemini_Generated_Image_k9ohc1k9ohc1k9oh.png","title":"V2.6"},{"category":"video-to-video","description":"Wan 2.6 reference-to-video model.","endpoint_id":"wan/v2.6/reference-to-video","family":"Wan 2.6","inputs":[{"default":null,"description":"Use @Video1, @Video2, @Video3 to reference subjects from your videos. Works for people, animals, or objects. For multi-shot prompts: '[0-3s] Shot 1. [3-6s] Shot 2.' Max 1500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference videos for subject consistency (1-3 videos). Videos' FPS must be at least 16 FPS.Reference in prompt as @Video1, @Video2, @Video3. Works for people, animals, or objects.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":true,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution tier. R2V only supports 720p and 1080p (no 480p).","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. R2V supports only 5 or 10 seconds (no 15s).","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"When true (default), enables intelligent multi-shot segmentation for coherent narrative videos with multiple shots. When false, generates single continuous shot. Only active when enable_prompt_expansion is True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_shots","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","actual_prompt","seed"],"pricing":"Your request will cost  $0.10 per second for 720p, $0.15 per second for 1080p.","published_at":"2025-12-16T05:08:01.945000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86d2c4/3COND31RbAVcBEj0c7P-b.png","title":"Wan v2.6 Reference to Video"},{"category":"video-to-video","description":"Wan 2.6 reference-to-video flash model.","endpoint_id":"wan/v2.6/reference-to-video/flash","family":"Wan 2.6","inputs":[{"default":null,"description":"Use Character1, Character2, etc. to reference subjects from your reference files. Works for people, animals, or objects. For multi-shot prompts: '[0-3s] Shot 1. [3-6s] Shot 2.' Max 1500 characters. Reference order: video_urls first, then image_urls.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Reference videos for subject consistency (0-3 videos). Videos' FPS must be at least 16 FPS. Combined with image_urls, total references cannot exceed 5. Reference order: video_urls are numbered first (Character1, Character2...), then image_urls continue the sequence.","enum":null,"is_list":true,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_urls","required":false,"type":"string"},{"default":null,"description":"Reference images for subject consistency (0-5 images). Combined with video_urls, total references cannot exceed 5. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP. Resolution: 240-5000px. Max 10MB each. Reference order: image_urls continue numbering after video_urls.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_urls","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution tier. R2V Flash only supports 720p and 1080p.","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. R2V Flash supports only 5 or 10 seconds.","enum":["5","10"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"When true (default), enables intelligent multi-shot segmentation for coherent narrative videos with multiple shots. When false, generates single continuous shot. Only active when enable_prompt_expansion is True.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_shots","required":false,"type":"boolean"},{"default":true,"description":"Whether to generate a video with audio. Set to false for silent video generation. Silent videos are faster and cost 25% of the audio version price.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"generate_audio","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["video","actual_prompt","seed"],"pricing":"Your request will cost  $0.10 per second for 720p, $0.15 per second for 1080p.","published_at":"2026-02-06T18:01:37.773000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8d6ad5/i7hPcbtP9HLfjs9-HQ9sJ_c5cd47efdacf4c0cb431698708aed327.jpg","title":"V2.6"},{"category":"text-to-image","description":"Wan 2.6 text-to-image model.","endpoint_id":"wan/v2.6/text-to-image","family":"Wan 2.6","inputs":[{"default":null,"description":"Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"Optional reference image (0 or 1). When provided, can be used for style guidance. Resolution: 384-5000px each dimension. Max size: 10MB. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"image_url","required":false,"type":"string"},{"default":"","description":"Content to avoid in the generated image. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":null,"description":"Output image size. If not set: matches input image size (up to 1280*1280). Use presets like 'square_hd', 'landscape_16_9', or specify exact dimensions.","enum":["square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9","custom_size"],"has_custom_size":true,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"image_size","required":false,"type":"enum"},{"default":1,"description":"Maximum number of images to generate (1-5). Actual count may be less depending on model inference.","enum":null,"is_list":false,"max":5,"media_kind":null,"min":1,"multiline":false,"name":"max_images","required":false,"type":"integer"},{"default":null,"description":"Random seed for reproducibility (0-2147483647).","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"Enable content moderation for input and output.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"images","output_props":["seed","images","generated_text"],"pricing":"","published_at":"2025-12-23T21:00:10.736000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a878040/GSP3n-IjMgY2GlxiwOu3V.png","title":"Wan v2.6 Text to Image"},{"category":"text-to-video","description":"Wan 2.6 text-to-video model.","endpoint_id":"wan/v2.6/text-to-video","family":"Wan 2.6","inputs":[{"default":null,"description":"The text prompt for video generation. Supports Chinese and English, max 1500 characters. For multi-shot videos, use format: 'Overall description. First shot [0-3s] content. Second shot [3-5s] content.'","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the audio to use as the background music. Must be publicly accessible.\nLimit handling: If the audio duration exceeds the duration value (5, 10, or 15 seconds),\nthe audio is truncated to the first N seconds, and the rest is discarded. If\nthe audio is shorter than the video, the remaining part of the video will be silent.\nFor example, if the audio is 3 seconds long and the video duration is 5 seconds, the\nfirst 3 seconds of the output video will have sound, and the last 2 seconds will be si","enum":null,"is_list":false,"max":null,"media_kind":"audio","min":null,"multiline":true,"name":"audio_url","required":false,"type":"string"},{"default":"16:9","description":"The aspect ratio of the generated video. Wan 2.6 supports additional ratios.","enum":["16:9","9:16","1:1","4:3","3:4"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1080p","description":"Video resolution tier. Wan 2.6 T2V only supports 720p and 1080p (no 480p).","enum":["720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"5","description":"Duration of the generated video in seconds. Choose between 5, 10, or 15 seconds.","enum":["5","10","15"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"duration","required":false,"type":"enum"},{"default":"","description":"Negative prompt to describe content to avoid. Max 500 characters.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"negative_prompt","required":false,"type":"string"},{"default":true,"description":"Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_prompt_expansion","required":false,"type":"boolean"},{"default":true,"description":"When true, enables intelligent multi-shot segmentation for coherent narrative videos. Only active when enable_prompt_expansion is True. Set to false for single-shot generation.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"multi_shots","required":false,"type":"boolean"},{"default":null,"description":"Random seed for reproducibility. If None, a random seed is chosen.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"seed","required":false,"type":"integer"},{"default":true,"description":"If set to true, the safety checker will be enabled.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"enable_safety_checker","required":false,"type":"boolean"}],"lab":"Alibaba","output_kind":"video","output_props":["actual_prompt","video","seed"],"pricing":"Your request will cost  $0.10 per second for 720p, $0.15 per second for 1080p.","published_at":"2025-12-16T05:12:22.693000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a86d2d7/3WTDnIgc5z_RVh24RgF-D.png","title":"Wan v2.6 Text to Video"},{"category":"text-to-image","description":"Generate highly aesthetic images with xAI's Grok Imagine Image generation model.","endpoint_id":"xai/grok-imagine-image","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of the desired image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"1:1","description":"Aspect ratio of the generated image.","enum":["2:1","20:9","19.5:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:19.5","9:20","1:2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1k","description":"Resolution of the generated image. `1k` for standard resolution, `2k` for high resolution.","enum":["1k","2k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"xAI","output_kind":"images","output_props":["images","revised_prompt"],"pricing":"","published_at":"2026-01-29T00:28:58.441000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8c4b97/vZlFRoT1SBs5XMoVqN_P5_f4b2e3f42dcc4f06a18953fda2b5c942.jpg","title":"Grok Imagine Image"},{"category":"image-to-image","description":"Edit images precisely with xAI's Grok Imagine model","endpoint_id":"xai/grok-imagine-image/edit","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of the desired image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"auto","description":"Aspect ratio of the edited image. When set to `auto` (the default), the output preserves the aspect ratio of the first input image.","enum":["auto","2:1","20:9","19.5:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:19.5","9:20","1:2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1k","description":"Resolution of the generated image. `1k` for standard resolution, `2k` for high resolution.","enum":["1k","2k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"List of URLs of the images to edit. A maximum of 3 images are supported.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":false,"type":"string"}],"lab":"xAI","output_kind":"images","output_props":["images","revised_prompt"],"pricing":"Your request will cost $0.022 per image ($0.02 for image output + $0.002 for image input).","published_at":"2026-01-29T00:29:41.002000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a0dc7/kv2XmZ5em8Kb2-7oXZndp_b897f79cbc564e1d8f4e5d5c71710c2b.jpg","title":"Grok Imagine Image"},{"category":"image-to-image","description":"Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.","endpoint_id":"xai/grok-imagine-image/quality/edit","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of the desired image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"auto","description":"Aspect ratio of the edited image. When set to `auto` (the default), the output preserves the aspect ratio of the first input image.","enum":["auto","2:1","20:9","19.5:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:19.5","9:20","1:2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1k","description":"Resolution of the generated image. `1k` for standard resolution, `2k` for high resolution.","enum":["1k","2k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"},{"default":null,"description":"List of URLs of the images to edit. A maximum of 3 images are supported.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_urls","required":false,"type":"string"}],"lab":"xAI","output_kind":"images","output_props":["images","revised_prompt"],"pricing":"Your request with cost $0.05 per output image for 1K and $0.07 per output image for 2K in addition to $0.01 per input image.","published_at":"2026-05-07T00:48:30.326000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a959abd/vUggNVIfKJsfVCUQhcI7s_ea5f9f2ac49147d49270324989db60e4.jpg","title":"Grok Imagine Image Editing Quality"},{"category":"text-to-image","description":"Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.","endpoint_id":"xai/grok-imagine-image/quality/text-to-image","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of the desired image.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":1,"description":"Number of images to generate.","enum":null,"is_list":false,"max":4,"media_kind":null,"min":1,"multiline":false,"name":"num_images","required":false,"type":"integer"},{"default":"1:1","description":"Aspect ratio of the generated image.","enum":["2:1","20:9","19.5:9","16:9","4:3","3:2","1:1","2:3","3:4","9:16","9:19.5","9:20","1:2"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"},{"default":"1k","description":"Resolution of the generated image. `1k` for standard resolution, `2k` for high resolution.","enum":["1k","2k"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"jpeg","description":"The format of the generated image.","enum":["jpeg","png","webp"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"enum"}],"lab":"xAI","output_kind":"images","output_props":["images","revised_prompt"],"pricing":"Your request with cost $0.05 per image for 1K and $0.07 per image for 2K.","published_at":"2026-05-07T00:49:05.554000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a959ac2/BbRJ1XroSH1gwHzPYc_t8_8ba16f7ab525499aaa149fba1039b4a4.jpg","title":"Grok Imagine Image"},{"category":"video-to-video","description":"Edit videos using xAI's Grok Imagine","endpoint_id":"xai/grok-imagine-video/edit-video","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of the desired edit.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the input video to edit. The video will be resized to a maximum area of 854x480 pixels and truncated to 8 seconds.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":true,"name":"video_url","required":true,"type":"string"},{"default":"auto","description":"Resolution of the output video.","enum":["auto","480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"}],"lab":"xAI","output_kind":"video","output_props":["video"],"pricing":"For a 6s 480p video your request will cost $0.36 ($0.05 per second of video output + $0.01 per second of video input). At an output resolution of 480p, every second costs $0.06 ($0.05 for output and $0.01 for input), and at 720p, every second costs $0.08 ($0.07 for output and $0.01 for input)","published_at":"2026-01-29T00:27:49.985000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a29af/LdzkePZifdyhKkL-fzyZm_f823bcaae85c4342ad20c800c9a2cef1.jpg","title":"Grok Imagine Video"},{"category":"video-to-video","description":"Extend videos with xAI's Grok Imagine video model","endpoint_id":"xai/grok-imagine-video/extend-video","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of what should happen next in the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"URL of the source video to extend. Must be MP4 format (H.264, H.265, or AV1 codec), 2-15 seconds long.","enum":null,"is_list":false,"max":null,"media_kind":"video","min":null,"multiline":false,"name":"video_url","required":true,"type":"string"},{"default":6,"description":"Length of the extension in seconds.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":2,"multiline":false,"name":"duration","required":false,"type":"integer"}],"lab":"xAI","output_kind":"video","output_props":["video"],"pricing":"For a 6s 480p video your request will cost $0.36 ($0.05 per second of video output + $0.01 per second of video input). At an output resolution of 480p, every second costs $0.06 ($0.05 for output and $0.01 for input), and at 720p, every second costs $0.08 ($0.07 for output and $0.01 for input)","published_at":"2026-03-24T17:54:09.171000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a937b17/7vgMNPVP3FZ6BEZzv5mII_2605d58f4fd84b0ba950203d58c0e445.jpg","title":"Grok Imagine Extend Video"},{"category":"image-to-video","description":"Generate videos from images with audio using xAI's Grok Imagine Video model.","endpoint_id":"xai/grok-imagine-video/image-to-video","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of desired changes or motion in the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"Video duration in seconds.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the output video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"URL of the input image for video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"},{"default":"auto","description":"Aspect ratio of the generated video.","enum":["auto","16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"xAI","output_kind":"video","output_props":["video"],"pricing":"A 6s 480p video will cost $0.302 ($0.05 per second of 480p video + $0.002 for image input). At an output resolution of 480p, every second costs $0.05, and at 720p, every second costs $0.07.","published_at":"2026-01-29T00:27:07.613000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a0dd0/3wXg362MQ0pczC2ZQFBfW_c153dd469fd14b75bbd9fa6d27f1b63e.jpg","title":"Grok Imagine Video"},{"category":"image-to-video","description":"Generate videos using multiple reference images with xAI's Grok Imagine video model","endpoint_id":"xai/grok-imagine-video/reference-to-video","family":"Grok Imagine","inputs":[{"default":null,"description":"Text prompt describing the video to generate. Use @Image1, @Image2, etc. to reference specific images from reference_image_urls in order.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":null,"description":"One or more reference image URLs to guide the video generation as style and content references. Reference in prompt as @Image1, @Image2, etc. Maximum 7 images.","enum":null,"is_list":true,"max":null,"media_kind":"image","min":null,"multiline":true,"name":"reference_image_urls","required":true,"type":"string"},{"default":8,"description":"Video duration in seconds.","enum":null,"is_list":false,"max":10,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"480p","description":"Resolution of the output video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"xAI","output_kind":"video","output_props":["video"],"pricing":"A 6s 480p video will cost $0.302 ($0.05 per second of 480p video + $0.002 for image input). At an output resolution of 480p, every second costs $0.05, and at 720p, every second costs $0.07.","published_at":"2026-03-24T17:55:41.616000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a937ab6/vW4pJVZGWgLX9tSTMZPiz_314f49c562014442a5a64eed32ab69ae.jpg","title":"Grok Imagine Reference to Video"},{"category":"text-to-video","description":"Generate videos with audio from text using Grok Imagine Video.","endpoint_id":"xai/grok-imagine-video/text-to-video","family":"Grok Imagine","inputs":[{"default":null,"description":"Text description of the desired video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"Video duration in seconds.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the output video.","enum":["480p","720p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":"16:9","description":"Aspect ratio of the generated video.","enum":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"aspect_ratio","required":false,"type":"enum"}],"lab":"xAI","output_kind":"video","output_props":["video"],"pricing":"For 6s 480p video your request will cost $0.3. At an output resolution of 480p, every second costs $0.05, and at 720p, every second costs $0.07.","published_at":"2026-01-29T00:26:17.072000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a8a0dd6/EDbXLIstjumsrgtGfV4NA_b75e853d42ea45f695d07e434331bdfb.jpg","title":"Grok Imagine Video"},{"category":"image-to-video","description":"Generate videos from images with audio using xAI's Grok Imagine 1.5 Video model.","endpoint_id":"xai/grok-imagine-video/v1.5/image-to-video","family":"Grok Imagine 1.5","inputs":[{"default":null,"description":"Text description of desired changes or motion in the video.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"prompt","required":true,"type":"string"},{"default":6,"description":"Video duration in seconds.","enum":null,"is_list":false,"max":15,"media_kind":null,"min":1,"multiline":false,"name":"duration","required":false,"type":"integer"},{"default":"720p","description":"Resolution of the output video.","enum":["480p","720p","1080p"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"resolution","required":false,"type":"enum"},{"default":null,"description":"URL of the input image for video generation.","enum":null,"is_list":false,"max":null,"media_kind":"image","min":null,"multiline":false,"name":"image_url","required":true,"type":"string"}],"lab":"xAI","output_kind":"video","output_props":["video"],"pricing":"Priced per second of output video, by resolution: 480p at $0.08/sec, 720p at $0.14/sec. A 5-second 480p clip costs $0.40; 720p costs $0.70. Cost scales linearly with duration. Each input image adds $0.01. Audio, if generated, is included.","published_at":"2026-05-31T09:49:36.797000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a9c2fbd/9sTsrztjz1KsxHWj1ONNM_b6a22e5d6ce2424aadbf4c3a7cf5f73a.jpg","title":"Grok Imagine Video 1.5"},{"category":"text-to-speech","description":"Generate speech with expressive and realistic voices from xAI","endpoint_id":"xai/tts/v1","family":"Grok TTS v1","inputs":[{"default":null,"description":"The text to convert to speech. Maximum 15,000 characters. Supports speech tags for expressive delivery: inline tags like [laugh], [pause], [sigh] and wrapping tags like <whisper>text</whisper>, <slow>text</slow>.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":true,"name":"text","required":true,"type":"string"},{"default":"eve","description":"Voice to use for synthesis. eve: energetic, upbeat. ara: warm, friendly. rex: confident, clear. sal: smooth, balanced. leo: authoritative, strong.","enum":["eve","ara","rex","sal","leo"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"voice","required":false,"type":"enum"},{"default":"auto","description":"BCP-47 language code or 'auto' for automatic detection. Supported: en, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi, bn, ar-EG, ar-SA, ar-AE.","enum":["auto","en","ar-EG","ar-SA","ar-AE","bn","zh","fr","de","hi","id","it","ja","ko","pt-BR","pt-PT","ru","es-MX","es-ES","tr","vi"],"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"language","required":false,"type":"enum"},{"default":null,"description":"Output format configuration. Defaults to MP3 at 24 kHz / 128 kbps.","enum":null,"is_list":false,"max":null,"media_kind":null,"min":null,"multiline":false,"name":"output_format","required":false,"type":"json"}],"lab":"xAI","output_kind":"audio","output_props":["audio"],"pricing":"Your request will cost $0.015 per 1000 characters.","published_at":"2026-03-17T00:21:43.728000+00:00","thumbnail":"https://v3b.fal.media/files/b/0a92763c/4toOv_gM9xUL_Zwmt4Gc8_67e9f077fc4c48e78dfa428f7d50b190.jpg","title":"xAI Text to Speech"}],"version":1,"window_days":0}