nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[docs] Add model-family inference cookbook (#1787)

Browse Source 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
This commit is contained in:
Aryan Kumar
2026-08-30 02:26:10 -07:00
committed by GitHub
co-authored by Aryan Kumar
parent a159b63c67
commit ccc9014430
34 changed files with 4789 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/assets/cookbook-recipes.json
+613 -13
View File
@@ -1,52 +1,652 @@
{
"version": 4,
"recipes": [
{
"id": "fastwan21-t2v",
"family": "wan",
"stage": "inference",
"task": "Text to video",
"label": "FastWan2.1 1.3B (distilled + VSA)",
"summary": "Generate a video in three denoising steps with the distilled FastWan2.1 1.3B checkpoint and video sparse attention.",
"model": "FastVideo/FastWan2.1-T2V-1.3B-Diffusers",
"source": "scripts/inference/inference_wan_VSA_DMD_1_3B.yaml",
"command": "FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN fastvideo generate --config scripts/inference/inference_wan_VSA_DMD_1_3B.yaml"
"command": "FASTVIDEO_ATTENTION_BACKEND=VIDEO_SPARSE_ATTN fastvideo generate --config scripts/inference/inference_wan_VSA_DMD_1_3B.yaml",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under outputs_video_dmd_1.3B/"
},
{
"id": "wan22-t2v",
"family": "wan",
"stage": "inference",
"task": "Text to video",
"label": "Wan2.2 A14B",
"summary": "The maintained high-capacity Wan2.2 text-to-video example with CPU offload settings encoded in its checked-in Python source.",
"model": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
"source": "examples/inference/basic/basic_wan2_2.py",
"command": "python examples/inference/basic/basic_wan2_2.py"
"command": "python examples/inference/basic/basic_wan2_2.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 2, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_wan2_2_14B_t2v/"
},
{
"id": "wan21-i2v",
"family": "wan",
"stage": "inference",
"task": "Image to video",
"label": "Wan2.1 14B 480P",
"summary": "Animate an input image at 480P using the maintained Wan2.1 YAML configuration and its recorded offload settings.",
"model": "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers",
"source": "scripts/inference/inference_wan_i2v.yaml",
"command": "fastvideo generate --config scripts/inference/inference_wan_i2v.yaml"
},
{
"id": "turbowan22-i2v",
"task": "Image to video",
"label": "TurboWan2.2 A14B",
"model": "loayrashid/TurboWan2.2-I2V-A14B-Diffusers",
"source": "examples/inference/basic/basic_turbodiffusion_i2v.py",
"command": "python examples/inference/basic/basic_turbodiffusion_i2v.py"
"command": "fastvideo generate --config scripts/inference/inference_wan_i2v.yaml",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 2, "evidence": "source-configured"},
"evidence": "Source-backed"
},
{
"id": "wan22-ti2v",
"family": "wan",
"stage": "inference",
"task": "Text or image to video",
"label": "Wan2.2 TI2V 5B",
"summary": "Use one maintained 5B checkpoint for text-to-video or add an image input to switch the same recipe to image-to-video.",
"model": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
"source": "examples/inference/basic/basic_wan2_2_ti2v.py",
"command": "python examples/inference/basic/basic_wan2_2_ti2v.py"
"command": "python examples/inference/basic/basic_wan2_2_ti2v.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_wan2_2_5B_ti2v/"
},
{
"id": "fastmetal-1-3b-mlx",
"family": "wan",
"stage": "inference",
"task": "Text to video",
"label": "FastMetal 1.3B",
"summary": "Run the released FastMetal 1.3B QAD checkpoint through FastVideo's native Apple Silicon MLX path.",
"model": "FastVideo/FastMetal-1.3B-QAD",
"source": "examples/inference/basic/mlx_wan_prompt_to_video.py",
"command": "hf download FastVideo/FastMetal-1.3B-QAD --local-dir ./FastMetal-1.3B-QAD\npython examples/inference/basic/mlx_wan_prompt_to_video.py --model-root ./FastMetal-1.3B-QAD --mlx-checkpoint ./FastMetal-1.3B-QAD --height 480 --width 832 --num-frames 81 --prompt \"A bird's-eye view of a misty forest valley at dawn.\" --output-path ./outputs/fastmetal_1_3b.mp4",
"gpu_types": ["Apple Silicon"],
"hardware": {
"platform": "mlx",
"accelerator": "Apple M4 Max",
"system_memory": "36 GB unified memory",
"minimum_memory": "16 GB+ unified memory",
"peak_memory": "3.87 GiB peak MLX memory",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1638"
},
"evidence": "Verified",
"expected_artifact": "MP4 video at outputs/fastmetal_1_3b.mp4",
"limitations": ["This is the native MLX FastMetal path. basic_mps.py is the older PyTorch MPS demo."]
},
{
"id": "fastmetal-5b-mlx",
"family": "wan",
"stage": "inference",
"task": "Text or image to video",
"label": "FastMetal 5B",
"summary": "Run the released Wan2.2 5B FastMetal checkpoint with MLX DiT denoising and MLX TAEHV decode.",
"model": "FastVideo/FastMetal-5B-QAD",
"source": "examples/inference/basic/mlx_wan22_generate.py",
"command": "hf download FastVideo/FastMetal-5B-QAD --local-dir ./FastMetal-5B-QAD\npython examples/inference/basic/mlx_wan22_generate.py --mlx-checkpoint ./FastMetal-5B-QAD --text-encoder-root ./FastMetal-5B-QAD --vae-root ./FastMetal-5B-QAD/vae --height 704 --width 1280 --num-frames 81 --prompt \"A cinematic portrait with soft neon lighting and smooth camera motion.\" --output-path ./outputs/fastmetal_5b.mp4",
"gpu_types": ["Apple Silicon"],
"hardware": {
"platform": "mlx",
"accelerator": "Apple M4 Max",
"system_memory": "36 GB unified memory",
"minimum_memory": "16 GB+ unified memory",
"peak_memory": "9.34 GiB peak MLX memory",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1638"
},
"evidence": "Verified",
"expected_artifact": "MP4 video at outputs/fastmetal_5b.mp4"
},
{
"id": "fastmetal-14b-mlx",
"family": "wan",
"stage": "inference",
"task": "Text to video",
"label": "FastMetal 14B",
"summary": "Run the released 14B FastMetal QAD checkpoint through the same Apple Silicon MLX entrypoint as the 1.3B release.",
"model": "FastVideo/FastMetal-14B-QAD",
"source": "examples/inference/basic/mlx_wan_prompt_to_video.py",
"command": "hf download FastVideo/FastMetal-14B-QAD --local-dir ./FastMetal-14B-QAD\npython examples/inference/basic/mlx_wan_prompt_to_video.py --model-root ./FastMetal-14B-QAD --mlx-checkpoint ./FastMetal-14B-QAD --height 480 --width 832 --num-frames 81 --prompt \"A wide cinematic landscape at sunrise.\" --output-path ./outputs/fastmetal_14b.mp4",
"gpu_types": ["Apple Silicon"],
"hardware": {
"platform": "mlx",
"accelerator": "Apple M4 Max",
"system_memory": "36 GB unified memory",
"minimum_memory": "36 GB+ unified memory",
"peak_memory": "21.68 GiB peak MLX memory",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1638"
},
"evidence": "Verified",
"expected_artifact": "MP4 video at outputs/fastmetal_14b.mp4"
},
{
"id": "turbodiffusion-wan21-1-3b-t2v",
"family": "turbodiffusion",
"stage": "inference",
"task": "Text to video",
"label": "TurboWan2.1 1.3B",
"summary": "A TurboDiffusion-accelerated Wan2.1 1.3B text-to-video run from its maintained single-GPU example.",
"model": "loayrashid/TurboWan2.1-T2V-1.3B-Diffusers",
"source": "examples/inference/basic/basic_turbodiffusion.py",
"command": "python examples/inference/basic/basic_turbodiffusion.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_turbodiffusion/",
"related": ["turbodiffusion-wan21-14b-t2v", "turbowan22-i2v"]
},
{
"id": "turbodiffusion-wan21-14b-t2v",
"family": "turbodiffusion",
"stage": "inference",
"task": "Text to video",
"label": "TurboWan2.1 14B",
"summary": "TurboDiffusion acceleration applied to the 14B Wan2.1 text-to-video checkpoint; the checked-in source is configured for two GPUs.",
"model": "loayrashid/TurboWan2.1-T2V-14B-Diffusers",
"source": "examples/inference/basic/basic_turbodiffusion_14b.py",
"command": "python examples/inference/basic/basic_turbodiffusion_14b.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 2, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_turbodiffusion_14B/",
"related": ["turbodiffusion-wan21-1-3b-t2v", "turbowan22-i2v"]
},
{
"id": "turbowan22-i2v",
"family": "turbodiffusion",
"stage": "inference",
"task": "Image to video",
"label": "TurboWan2.2 A14B",
"summary": "A one-to-four-step image-to-video path using TurboDiffusion and the SLA attention backend from its maintained example.",
"model": "loayrashid/TurboWan2.2-I2V-A14B-Diffusers",
"source": "examples/inference/basic/basic_turbodiffusion_i2v.py",
"command": "python examples/inference/basic/basic_turbodiffusion_i2v.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 2, "evidence": "source-configured"},
"evidence": "Source-backed",
"related": ["turbodiffusion-wan21-14b-t2v"]
},
{
"id": "ltx2-distilled-t2v",
"family": "ltx2",
"stage": "inference",
"task": "Text to video",
"label": "LTX-2 distilled",
"summary": "The distilled LTX-2 text-to-video checkpoint with audio, from its maintained example. The source is configured for four GPUs.",
"model": "FastVideo/LTX2-Distilled-Diffusers",
"source": "examples/inference/basic/basic_ltx2_distilled.py",
"command": "python examples/inference/basic/basic_ltx2_distilled.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 4, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 (video with audio) at outputs_video/ltx2_basic/output_ltx2_distilled_t2v.mp4",
"related": ["ltx23-base-t2v"]
},
{
"id": "ltx23-base-t2v",
"family": "ltx2",
"stage": "inference",
"task": "Text to video",
"label": "LTX-2 base (1088p)",
"summary": "Base LTX-2 text-to-video at 1088x1920 using FastVideo default sampling for LTX2 base. The example loads a community Diffusers mirror of the base checkpoint; registered aliases include Lightricks/LTX-2 and FastVideo/LTX2-Diffusers.",
"model": "Davids048/LTX2-Base-Diffusers",
"source": "examples/inference/basic/basic_ltx2.py",
"command": "python examples/inference/basic/basic_ltx2.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 (video with audio) at outputs_video/ltx2_basic/output_ltx2_base_t2v_1088_1920_1.1.mp4",
"limitations": ["The maintained example loads the Davids048/LTX2-Base-Diffusers community mirror rather than a Lightricks upstream ID."],
"related": ["ltx2-distilled-t2v"]
},
{
"id": "hy15-t2v-480p",
"family": "hunyuan",
"stage": "inference",
"task": "Text to video",
"label": "HunyuanVideo 1.5 480P",
"summary": "HunyuanVideo 1.5 text-to-video at 480P with CPU offload enabled in the checked-in source for smaller GPUs.",
"model": "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v",
"source": "examples/inference/basic/basic_hy15.py",
"command": "python examples/inference/basic/basic_hy15.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_hy15/",
"related": ["hy15-1080p-upscale"]
},
{
"id": "hy15-1080p-upscale",
"family": "hunyuan",
"stage": "inference",
"task": "Text to video (upscaled)",
"label": "HunyuanVideo 1.5 1080P upscale",
"summary": "Run HunyuanVideo 1.5 through the 480p to 720p to 1080p upscale chain in one maintained script.",
"model": "weizhou03/HunyuanVideo-1.5-Diffusers-1080p-2SR",
"source": "examples/inference/basic/basic_hy15_1080p.py",
"command": "python examples/inference/basic/basic_hy15_1080p.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_hy15_1080p/",
"related": ["hy15-t2v-480p"]
},
{
"id": "cosmos25-t2w",
"family": "cosmos",
"stage": "inference",
"task": "Text to world",
"label": "Cosmos Predict 2.5 2B",
"summary": "Generate a navigable world video from a text prompt with Cosmos Predict 2.5 2B on a single GPU.",
"model": "KyleShao/Cosmos-Predict2.5-2B-Diffusers",
"source": "examples/inference/basic/basic_cosmos2_5_t2w.py",
"command": "python examples/inference/basic/basic_cosmos2_5_t2w.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed"
},
{
"id": "kandinsky5-t2v-lite-sft",
"family": "kandinsky5",
"stage": "inference",
"task": "Text to video",
"label": "Kandinsky 5.0 T2V Lite SFT",
"summary": "Kandinsky 5.0 text-to-video (Lite SFT variant) from the maintained example; alternative Lite/Pro checkpoints are listed in the source.",
"model": "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers",
"source": "examples/inference/basic/basic_kandinsky5_t2v.py",
"command": "python examples/inference/basic/basic_kandinsky5_t2v.py",
"gpu_types": ["NVIDIA"],
"hardware": {
"platform": "cuda",
"gpu_count": 1,
"accelerator": "NVIDIA B200",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1471"
},
"evidence": "Verified",
"expected_artifact": "MP4 videos under video_samples_kandinsky5_t2v/",
"related": ["kandinsky5-i2v-pro-distilled"]
},
{
"id": "kandinsky5-i2v-pro-distilled",
"family": "kandinsky5",
"stage": "inference",
"task": "Image to video",
"label": "Kandinsky 5.0 I2V Pro distilled",
"summary": "Animate an input image with Kandinsky 5.0 I2V Pro (distilled) on a single GPU.",
"model": "kandinskylab/Kandinsky-5.0-I2V-Pro-distilled-5s-Diffusers",
"source": "examples/inference/basic/basic_kandinsky5_i2v.py",
"command": "python examples/inference/basic/basic_kandinsky5_i2v.py",
"gpu_types": ["NVIDIA"],
"hardware": {
"platform": "cuda",
"gpu_count": 1,
"accelerator": "NVIDIA B200",
"peak_memory": "10,365.89 MB peak GPU memory",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1471"
},
"evidence": "Verified",
"expected_artifact": "MP4 videos under video_samples_kandinsky5_i2v/",
"related": ["kandinsky5-t2v-lite-sft"]
},
{
"id": "flux2-klein-t2i",
"family": "flux",
"stage": "inference",
"task": "Text to image",
"label": "FLUX.2 Klein 4B",
"summary": "Generate an image in four denoising steps with the distilled FLUX.2 Klein checkpoint.",
"model": "black-forest-labs/FLUX.2-klein-4B",
"source": "examples/inference/basic/basic_flux2_klein.py",
"command": "python examples/inference/basic/basic_flux2_klein.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG image at outputs/flux2/flux2_klein.png",
"related": ["flux2-dev-t2i"]
},
{
"id": "flux2-dev-t2i",
"family": "flux",
"stage": "inference",
"task": "Text to image",
"label": "FLUX.2 dev",
"summary": "Full FLUX.2 dev text-to-image with embedded guidance and the Mistral3 text encoder, from its maintained example.",
"model": "black-forest-labs/FLUX.2-dev",
"source": "examples/inference/basic/basic_flux2.py",
"command": "python examples/inference/basic/basic_flux2.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG image at outputs/flux2/flux2.png",
"related": ["flux2-klein-t2i"]
},
{
"id": "flux1-dev-t2i",
"family": "flux",
"stage": "inference",
"task": "Text to image",
"label": "FLUX.1 dev",
"summary": "FLUX.1 dev text-to-image through the Diffusers-backed pipeline. The example defaults to a local weights directory, so this recipe passes the Hugging Face ID explicitly.",
"model": "black-forest-labs/FLUX.1-dev",
"source": "examples/inference/basic/basic_flux_dev.py",
"command": "python examples/inference/basic/basic_flux_dev.py --model-path black-forest-labs/FLUX.1-dev",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG images under outputs/flux_dev/samples/",
"limitations": ["FLUX.1 is loadable by ID but registers no model_family in fastvideo/registry.py; it is grouped under FLUX for documentation only."]
},
{
"id": "glm-image-t2i",
"family": "glm_image",
"stage": "inference",
"task": "Text to image",
"label": "GLM-Image",
"summary": "GLM-Image text-to-image generation from its maintained example.",
"model": "zai-org/GLM-Image",
"source": "examples/inference/basic/basic_glm_image.py",
"command": "python examples/inference/basic/basic_glm_image.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG image at image_output/landscape.png",
"related": ["glm-image-edit"]
},
{
"id": "glm-image-edit",
"family": "glm_image",
"stage": "inference",
"task": "Image editing",
"label": "GLM-Image editing",
"summary": "Edit an input image with an instruction prompt using GLM-Image, from its maintained editing example.",
"model": "zai-org/GLM-Image",
"source": "examples/inference/basic/edit_glm_image.py",
"command": "python examples/inference/basic/edit_glm_image.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG image at image_output/edited.png (input: assets/images/couple.jpg)",
"related": ["glm-image-t2i"]
},
{
"id": "zimage-turbo-t2i",
"family": "zimage",
"stage": "inference",
"task": "Text to image",
"label": "Z-Image Turbo",
"summary": "Z-Image Turbo text-to-image on a single GPU from its maintained example.",
"model": "Tongyi-MAI/Z-Image-Turbo",
"source": "examples/inference/basic/basic_zimage.py",
"command": "python examples/inference/basic/basic_zimage.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG image at outputs/zimage/zimage_turbo.png"
},
{
"id": "sd35-medium-t2i",
"family": "sd35",
"stage": "inference",
"task": "Text to image",
"label": "Stable Diffusion 3.5 Medium",
"summary": "Stable Diffusion 3.5 Medium text-to-image over a small built-in prompt set, from its maintained example.",
"model": "stabilityai/stable-diffusion-3.5-medium",
"source": "examples/inference/basic/basic_sd35_t2i.py",
"command": "python examples/inference/basic/basic_sd35_t2i.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "PNG images under outputs/sd35/samples/"
},
{
"id": "minimax-h3-t2v",
"family": "minimax_h3",
"stage": "inference",
"task": "Text to video (with audio)",
"label": "MiniMax H3 T2VA",
"summary": "Generate synchronized video and stereo audio from a structured text prompt with the full MiniMax H3 checkpoint.",
"model": "MiniMaxAI/MiniMax-H3",
"source": "examples/inference/basic/basic_minimax_h3_t2v.py",
"command": "python examples/inference/basic/basic_minimax_h3_t2v.py --prompt \"(S1) A presenter says <d>[English] FastVideo runs MiniMax H3.</d>\"",
"gpu_types": ["NVIDIA"],
"hardware": {"platform": "cuda", "gpu_count": 4, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 with synchronized audio at outputs/minimax_h3_t2v/minimax_h3_t2v.mp4",
"limitations": ["The checked-in example defaults to four-way sequence parallelism. It does not record a GPU model or memory requirement."]
},
{
"id": "fasth3-preview-cuda",
"group": "fasth3-preview",
"group_label": "FastH3 Preview",
"group_task": "4-step text to video + audio",
"family": "minimax_h3",
"stage": "inference",
"task": "Few-step text to video (with audio)",
"label": "FastH3 Preview on CUDA",
"summary": "Run the DMD2-distilled FastH3 Preview with four DiT forwards, trained H3 sparse attention, compiled decode, and synchronized audio.",
"model": "FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2",
"source": "examples/inference/basic/basic_fasth3.py",
"command": "UV_TORCH_BACKEND=cu130 uv pip install -e \".[fasth3]\"\npython examples/inference/basic/basic_fasth3.py --prompt \"(S1) A presenter says <d>[English] FastVideo runs FastH3.</d>\" --profile all",
"gpu_types": ["NVIDIA"],
"hardware": {
"platform": "cuda",
"gpu_count": 4,
"accelerator": "NVIDIA GB200",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1731"
},
"evidence": "Verified",
"expected_artifact": "Warmup and measured MP4 files under outputs/fasth3/",
"limitations": ["The default all profile is the measured GB200 performance route and can change floating-point operation order. Use --profile strict --no-inference-torch-compile for the eager strict route."]
},
{
"id": "fasth3-preview-mlx",
"group": "fasth3-preview",
"group_label": "FastH3 Preview",
"group_task": "4-step text to video + audio",
"family": "minimax_h3",
"stage": "inference",
"task": "Few-step text to video (with audio)",
"label": "FastH3 Preview on MLX",
"summary": "Run FastH3 Preview on Apple Silicon with a locally converted INT6 DiT, streamed Qwen3-VL conditioning, and native MLX video and audio VAEs.",
"model": "FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2",
"source": "examples/inference/basic/mlx_fasth3.py",
"command": "hf download FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2 --local-dir ./FastH3-Preview-v0.2\npython scripts/checkpoint_conversion/convert_minimax_h3_mlx.py --model-root ./FastH3-Preview-v0.2/transformer --out ./FastH3-MLX --formats \"int6\"\npython examples/inference/basic/mlx_fasth3.py --model-root ./FastH3-Preview-v0.2 --mlx-checkpoint ./FastH3-MLX/int6 --prompt \"(S1) A presenter says <d>[English] FastVideo runs FastH3.</d>\" --height 480 --width 832 --num-frames 124 --seed 2026 --output-path ./outputs/fasth3_int6.mp4",
"gpu_types": ["Apple Silicon"],
"hardware": {
"platform": "mlx",
"accelerator": "Apple M4 Max",
"system_memory": "36 GB unified memory",
"peak_memory": "19.63 GiB peak MLX memory during denoising",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1770"
},
"evidence": "Verified",
"expected_artifact": "MP4 with H.264 video and stereo AAC audio at outputs/fasth3_int6.mp4",
"limitations": ["The MLX path supports T2VA and optional temporal --fast mode. FL2VA, Ref2VA, spatial fast mode, two-pass refinement, and VSA are not wired."]
},
{
"id": "minimax-h3-fl2va",
"family": "minimax_h3",
"stage": "inference",
"task": "First/last frame to video (with audio)",
"label": "MiniMax H3 FL2VA",
"summary": "Animate a first frame, optionally guide the final frame, and generate synchronized audio with the full MiniMax H3 checkpoint.",
"model": "MiniMaxAI/MiniMax-H3",
"source": "examples/inference/basic/basic_minimax_h3_fl2va.py",
"command": "python examples/inference/basic/basic_minimax_h3_fl2va.py --image path/to/first-frame.png --prompt \"(S1) The subject turns toward the camera and says <d>[English] Hello.</d>\"",
"gpu_types": ["NVIDIA"],
"hardware": {"platform": "cuda", "gpu_count": 4, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 with synchronized audio at outputs/minimax_h3_fl2va/minimax_h3_fl2va.mp4",
"limitations": ["Pass --last-image to constrain the final frame. The checked-in source defaults to four GPUs."]
},
{
"id": "minimax-h3-ref2va",
"family": "minimax_h3",
"stage": "inference",
"task": "Reference media to video (with audio)",
"label": "MiniMax H3 Ref2VA",
"summary": "Condition H3 on an ordered reference video and optional audio reference, then generate a new synchronized video and audio result.",
"model": "MiniMaxAI/MiniMax-H3",
"source": "examples/inference/basic/basic_minimax_h3_ref2va.py",
"command": "python examples/inference/basic/basic_minimax_h3_ref2va.py --reference-video path/to/reference.mp4 --prompt \"Create a new scene that preserves the reference identity and motion language.\"",
"gpu_types": ["NVIDIA"],
"hardware": {"platform": "cuda", "gpu_count": 4, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 with synchronized audio at outputs/minimax_h3_ref2va/minimax_h3_ref2va.mp4",
"limitations": ["Pass --reference-audio for an additional audio reference. The checked-in source defaults to four GPUs."]
},
{
"id": "fasth3-lora-preview",
"family": "minimax_h3",
"stage": "inference",
"task": "LoRA-adapted few-step video (with audio)",
"label": "FastH3 LoRA Preview",
"summary": "Apply a FastH3 preview adapter at load time while keeping the shared four-forward performance profile and synchronized audio output.",
"model": "MiniMaxAI/MiniMax-H3",
"source": "examples/inference/basic/basic_fasth3_lora_preview.py",
"command": "python examples/inference/basic/basic_fasth3_lora_preview.py --lora-path path/to/adapter.safetensors --prompt \"(S1) A presenter says <d>[English] This is an adapted Fast H3 run.</d>\"",
"gpu_types": ["NVIDIA"],
"hardware": {
"platform": "cuda",
"gpu_count": 4,
"accelerator": "NVIDIA B200",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1771"
},
"evidence": "Verified",
"expected_artifact": "Warmup and measured MP4 files under outputs/fasth3_lora_preview/",
"limitations": ["Supply a compatible FastH3 adapter. The script infers dense or VSA attention from the adapter payload unless you override it."]
},
{
"id": "longcat-t2v",
"family": "longcat",
"stage": "inference",
"task": "Text to video",
"label": "LongCat Video T2V",
"summary": "LongCat Video text-to-video at 480p (50 steps), with distilled and 720p refinement passes included in the same maintained script.",
"model": "FastVideo/LongCat-Video-T2V-Diffusers",
"source": "examples/inference/basic/basic_longcat_t2v.py",
"command": "python examples/inference/basic/basic_longcat_t2v.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under outputs_video/longcat_t2v_basic/, longcat_t2v_distill/, and longcat_t2v_refine_720p/",
"related": ["longcat-i2v"]
},
{
"id": "longcat-i2v",
"family": "longcat",
"stage": "inference",
"task": "Image to video",
"label": "LongCat Video I2V",
"summary": "LongCat Video image-to-video with optional distilled and refinement passes, from its maintained example.",
"model": "FastVideo/LongCat-Video-I2V-Diffusers",
"source": "examples/inference/basic/basic_longcat_i2v.py",
"command": "python examples/inference/basic/basic_longcat_i2v.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under outputs_video/longcat_i2v_basic/ and longcat_i2v_distill/",
"related": ["longcat-t2v"]
},
{
"id": "stable-audio-open-t2a",
"family": "stable_audio",
"stage": "inference",
"task": "Text to audio",
"label": "Stable Audio Open 1.0",
"summary": "Six-second text-to-audio generation with Stable Audio Open 1.0 from its maintained example; duration and steps are documented knobs in the source.",
"model": "FastVideo/stable-audio-open-1.0-Diffusers",
"source": "examples/inference/basic/basic_stable_audio.py",
"command": "python examples/inference/basic/basic_stable_audio.py",
"gpu_types": ["NVIDIA"],
"hardware": {
"platform": "cuda",
"gpu_count": 1,
"accelerator": "NVIDIA B200",
"evidence": "validated",
"evidence_url": "https://github.com/hao-ai-lab/FastVideo/pull/1260"
},
"evidence": "Verified",
"expected_artifact": "WAV audio at outputs_audio/stable_audio_basic/output_stable_audio.wav",
"limitations": ["Must load the FastVideo converted Diffusers repo; upstream stabilityai monolithic checkpoints are not loader-compatible (see scripts/checkpoint_conversion/stable_audio_to_diffusers.py)."],
"related": ["stable-audio-small-t2a"]
},
{
"id": "stable-audio-small-t2a",
"family": "stable_audio",
"stage": "inference",
"task": "Text to audio",
"label": "Stable Audio Open Small",
"summary": "The smaller Stable Audio Open variant with its own shorter training window, from its maintained example.",
"model": "FastVideo/stable-audio-open-small-Diffusers",
"source": "examples/inference/basic/basic_stable_audio_small.py",
"command": "python examples/inference/basic/basic_stable_audio_small.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"related": ["stable-audio-open-t2a"]
},
{
"id": "mmaudio-v2a",
"family": "mmaudio",
"stage": "inference",
"task": "Video/Text to audio",
"label": "MMAudio large 44k v2",
"summary": "Add synchronized audio to a video (or from a prompt) with MMAudio large 44k v2. The example reads the model path from MMAUDIO_MODEL_PATH; this recipe passes the converted Hugging Face repo explicitly.",
"model": "FastVideo/MMAudio-large-44k-v2-Diffusers",
"source": "examples/inference/basic/basic_mmaudio.py",
"command": "MMAUDIO_MODEL_PATH=FastVideo/MMAudio-large-44k-v2-Diffusers python examples/inference/basic/basic_mmaudio.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"limitations": ["The upstream checkpoint must be converted to Diffusers layout via scripts/checkpoint_conversion/convert_mmaudio_to_diffusers.py unless loaded from the FastVideo converted repo as done here."]
},
{
"id": "matrix-game-2",
"family": "matrixgame",
"stage": "inference",
"task": "Interactive world",
"label": "Matrix Game 2.0",
"summary": "Generate an interactive-world sequence from the maintained Matrix Game 2.0 example.",
"model": "FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
"source": "examples/inference/basic/basic_matrixgame2.py",
"command": "python examples/inference/basic/basic_matrixgame2.py"
"command": "python examples/inference/basic/basic_matrixgame2.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"related": ["matrix-game-3-i2w"]
},
{
"id": "matrix-game-3-i2w",
"family": "matrixgame",
"stage": "inference",
"task": "Interactive world",
"label": "Matrix Game 3.0",
"summary": "Drive Matrix Game 3.0 from an input image plus prompt at 720p, three steps, from its maintained example.",
"model": "FastVideo/Matrix-Game-3.0-Base-Distilled-Diffusers",
"source": "examples/inference/basic/basic_matrixgame3.py",
"command": "python examples/inference/basic/basic_matrixgame3.py",
"gpu_types": ["NVIDIA"],
"hardware": {"gpu_count": 1, "evidence": "source-configured"},
"evidence": "Source-backed",
"expected_artifact": "MP4 videos under video_samples_matrixgame3/",
"related": ["matrix-game-2"]
}
]
}
docs/assets/cookbook.js
+344 -44
View File
@@ -1,57 +1,357 @@
(() => {
let recipesPromise;
const patternCharacters = "0123456789ABCDEF";
const loadRecipes = (url) => {
recipesPromise ||= fetch(url).then((response) => {
const loadRecipes = (url) =>
fetch(url).then((response) => {
if (!response.ok) throw new Error(`HTTP ${response.status}`);
return response.json();
});
return recipesPromise;
const initPatterns = (root) => {
root.querySelectorAll("[data-cookbook-pattern]").forEach((pattern, patternIndex) => {
if (pattern.dataset.patternReady) return;
pattern.dataset.patternReady = "true";
let value = "";
for (let index = 0; index < 1800; index += 1) {
const characterIndex = (index * 7 + patternIndex * 11) % patternCharacters.length;
value += patternCharacters.charAt(characterIndex);
if (index % 4 === 3 && index % 32 !== 31) value += " ";
if (index % 32 === 31) value += "\n";
}
pattern.textContent = value;
});
};
const groupIdFor = (recipe) => recipe.group || recipe.id;
const gpuCountLabel = (hardware) => {
const count = hardware?.gpu_count;
return `${count} GPU${count === 1 ? "" : "s"}`;
};
const runtimeFor = (recipe) => {
const platform = recipe.hardware?.platform || "cuda";
if (platform === "mlx") {
return {
id: "mlx",
label: "Apple Silicon · MLX",
hint:
recipe.hardware?.minimum_memory ||
[recipe.hardware?.accelerator, recipe.hardware?.system_memory].filter(Boolean).join(" · ") ||
"Memory not recorded",
};
}
if (platform === "mps") {
return {
id: "mps",
label: "Apple Silicon · MPS",
hint: recipe.hardware?.minimum_memory || recipe.hardware?.system_memory || "Memory not recorded",
};
}
const hardware = recipe.hardware || {};
return {
id: "cuda",
label: "NVIDIA CUDA",
hint: hardware.accelerator
? `${hardware.accelerator} · ${gpuCountLabel(hardware)}`
: `${gpuCountLabel(hardware)} configured · GPU model not recorded`,
};
};
const runtimeSummary = (recipe) => {
const runtime = runtimeFor(recipe);
const hardware = recipe.hardware || {};
if (runtime.id === "mlx") {
return [hardware.accelerator || "Apple Silicon", hardware.system_memory || hardware.minimum_memory, "MLX"]
.filter(Boolean)
.join(" · ");
}
if (runtime.id === "mps") {
return [hardware.accelerator || "Apple Silicon", hardware.system_memory || hardware.minimum_memory, "PyTorch MPS"]
.filter(Boolean)
.join(" · ");
}
if (hardware.accelerator) return [hardware.accelerator, gpuCountLabel(hardware)].join(" · ");
return `NVIDIA CUDA · ${gpuCountLabel(hardware)} configured · GPU model and VRAM not recorded`;
};
const renderHardwareEvidence = (container, badge, recipe) => {
const hardware = recipe.hardware || {};
const runtime = runtimeFor(recipe);
const isValidated = hardware.evidence === "validated";
container.classList.toggle("cookbook-hardware-state--verified", isValidated);
container.classList.toggle("cookbook-hardware-state--source", !isValidated);
badge.classList.toggle("cookbook-badge--verified", isValidated);
badge.classList.toggle("cookbook-badge--configured", !isValidated);
badge.textContent = isValidated ? "Recorded run" : "Source config";
const heading = document.createElement("strong");
heading.textContent = isValidated ? "Recorded hardware" : "Source configuration";
const details = document.createElement("span");
if (isValidated) {
const recorded = [
hardware.accelerator,
runtime.id === "cuda" ? gpuCountLabel(hardware) : hardware.system_memory,
].filter(Boolean);
const statements = [`${recorded.join(" · ")}.`];
if (hardware.minimum_memory) statements.push(`Documented minimum: ${hardware.minimum_memory}.`);
if (hardware.peak_memory) statements.push(`Measured: ${hardware.peak_memory}.`);
if (!hardware.minimum_memory) statements.push("This recorded device is not a minimum requirement.");
details.textContent = ` ${statements.join(" ")}`;
} else if (runtime.id === "cuda") {
details.textContent = ` NVIDIA CUDA · ${gpuCountLabel(hardware)}. The source does not record the GPU model or VRAM.`;
} else {
details.textContent = ` ${runtime.label}. The source does not record a device or memory requirement.`;
}
container.replaceChildren(heading, details);
if (hardware.evidence_url) {
const evidenceLink = document.createElement("a");
evidenceLink.href = hardware.evidence_url;
evidenceLink.textContent = "View run evidence";
evidenceLink.setAttribute("aria-label", `View recorded hardware evidence for ${recipe.label}`);
container.append(" ", evidenceLink);
}
};
const compactLifecycle = (root) => {
const lifecycle = root.querySelector(".cookbook-lifecycle");
if (!lifecycle || lifecycle.dataset.compact) return;
lifecycle.dataset.compact = "true";
const stages = [...lifecycle.querySelectorAll(".cookbook-lifecycle__stage")];
const active = stages.find((stage) => stage.classList.contains("cookbook-lifecycle__stage--active"));
const planned = stages
.filter((stage) => stage !== active)
.map((stage) => stage.childNodes[0]?.textContent?.trim())
.filter(Boolean);
const summary = document.createElement("span");
summary.className = "cookbook-lifecycle__summary";
summary.textContent = `Next: ${planned.join(", ")}`;
lifecycle.replaceChildren(...(active ? [active] : []), summary);
};
const initFamilyBuilder = async (root) => {
const family = root.dataset.family;
if (!family) return;
compactLifecycle(root);
const builderHeading = root.querySelector(".cookbook-builder__intro h2");
const builderIntro = root.querySelector(".cookbook-builder__intro > p");
if (builderHeading) builderHeading.textContent = "Pick a recipe and runtime";
if (builderIntro) {
builderIntro.textContent =
"Start with the result you want, then choose one of the runtimes FastVideo actually maintains for it.";
}
const selectionLabels = root.querySelectorAll(".cookbook-selection-row__label");
if (selectionLabels[0]) {
selectionLabels[0].querySelector("strong").textContent = "Recipe";
selectionLabels[0].querySelector("span").textContent = "Task and checkpoint";
}
if (selectionLabels[1]) {
selectionLabels[1].querySelector("strong").textContent = "Runtime";
selectionLabels[1].querySelector("span").textContent = "Maintained paths only";
}
const modelOptions = root.querySelector("[data-cookbook-model-options]");
const hardwareOptions = root.querySelector("[data-cookbook-hardware-options]");
const description = root.querySelector("[data-cookbook-description]");
const hardwareNote = root.querySelector(".cookbook-hardware-note");
const label = root.querySelector("[data-cookbook-label]");
const model = root.querySelector("[data-cookbook-model]");
const task = root.querySelector("[data-cookbook-task]");
const hardwareValue = root.querySelector("[data-cookbook-gpus]");
const artifact = root.querySelector("[data-cookbook-artifact]");
const evidenceCell = root.querySelector("[data-cookbook-evidence]");
const source = root.querySelector("[data-cookbook-source]");
const modelLink = root.querySelector("[data-cookbook-model-link]");
const command = root.querySelector("[data-cookbook-command]");
const status = root.querySelector("[data-cookbook-status]");
const hardwareState = root.querySelector("[data-cookbook-hardware-state]");
const hardwareBadge = root.querySelector("[data-cookbook-hardware-badge]");
const count = root.querySelector("[data-cookbook-count]");
const result = root.querySelector(".cookbook-result");
const commandBlock = root.querySelector(".cookbook-command");
modelOptions.setAttribute("aria-label", "Recipe");
hardwareOptions.setAttribute("aria-label", "Runtime");
if (hardwareNote) {
hardwareNote.textContent = "Exact device and memory details appear only when a recorded run supports them.";
}
const runtimeFactLabel = hardwareValue?.closest("div")?.querySelector("dt");
if (runtimeFactLabel) runtimeFactLabel.textContent = "Hardware";
let recipes;
try {
({ recipes } = await loadRecipes(root.dataset.recipes));
} catch (error) {
if (status) status.textContent = "Recipes could not be loaded. Use the maintained examples link below.";
console.error("Failed to load FastVideo cookbook recipes", error);
return;
}
const familyRecipes = recipes.filter((recipe) => recipe.family === family);
if (!familyRecipes.length) return;
const byId = new Map(familyRecipes.map((recipe) => [recipe.id, recipe]));
const groups = new Map();
familyRecipes.forEach((recipe) => {
const groupId = groupIdFor(recipe);
if (!groups.has(groupId)) groups.set(groupId, []);
groups.get(groupId).push(recipe);
});
if (count) count.textContent = `${familyRecipes.length} maintained recipes`;
modelOptions.replaceChildren();
groups.forEach((groupRecipes, groupId) => {
const representative = groupRecipes[0];
const option = document.createElement("button");
option.type = "button";
option.dataset.recipeGroup = groupId;
option.setAttribute("aria-pressed", "false");
const optionLabel = document.createElement("strong");
optionLabel.textContent = representative.group_label || representative.label;
const optionTask = document.createElement("span");
optionTask.textContent = representative.group_task || representative.task;
option.append(optionLabel, optionTask);
modelOptions.append(option);
});
const query = new URLSearchParams(window.location.search);
const requestedRecipe = query.get("recipe");
const defaultRecipeId = familyRecipes[0].id;
let selectedRecipeId = requestedRecipe && byId.has(requestedRecipe) ? requestedRecipe : defaultRecipeId;
let selectedGroupId = groupIdFor(byId.get(selectedRecipeId));
const renderRuntimeOptions = () => {
const groupRecipes = groups.get(selectedGroupId) || [];
hardwareOptions.replaceChildren();
groupRecipes.forEach((recipe) => {
const runtime = runtimeFor(recipe);
const option = document.createElement("button");
option.type = "button";
option.dataset.recipeId = recipe.id;
option.dataset.runtimeId = runtime.id;
option.setAttribute("aria-pressed", "false");
const optionLabel = document.createElement("strong");
optionLabel.textContent = runtime.label;
const optionHint = document.createElement("span");
optionHint.textContent = runtime.hint;
option.append(optionLabel, optionHint);
hardwareOptions.append(option);
});
};
let notes = root.querySelector("[data-cookbook-notes]");
if (!notes) {
notes = document.createElement("aside");
notes.className = "cookbook-recipe-notes";
notes.dataset.cookbookNotes = "";
notes.hidden = true;
result.insertBefore(notes, commandBlock);
}
const render = ({ groupChanged = false, historyMode = "replace" } = {}) => {
if (!byId.has(selectedRecipeId)) selectedRecipeId = defaultRecipeId;
let recipe = byId.get(selectedRecipeId);
if (groupChanged || groupIdFor(recipe) !== selectedGroupId) {
const currentRuntime = runtimeFor(recipe).id;
const groupRecipes = groups.get(selectedGroupId) || [];
recipe = groupRecipes.find((candidate) => runtimeFor(candidate).id === currentRuntime) || groupRecipes[0];
selectedRecipeId = recipe.id;
}
selectedGroupId = groupIdFor(recipe);
renderRuntimeOptions();
const runtime = runtimeFor(recipe);
modelOptions.querySelectorAll("button").forEach((option) => {
const selected = option.dataset.recipeGroup === selectedGroupId;
option.classList.toggle("cookbook-option--selected", selected);
option.setAttribute("aria-pressed", String(selected));
});
hardwareOptions.querySelectorAll("button").forEach((option) => {
const selected = option.dataset.recipeId === recipe.id;
option.classList.toggle("cookbook-option--selected", selected);
option.setAttribute("aria-pressed", String(selected));
});
description.textContent = recipe.summary;
label.textContent = recipe.label;
model.textContent = recipe.model;
task.textContent = recipe.task;
hardwareValue.textContent = runtimeSummary(recipe);
if (artifact) artifact.textContent = recipe.expected_artifact || "Not yet documented for this recipe.";
if (evidenceCell) {
evidenceCell.textContent = recipe.evidence || "Source-backed";
evidenceCell.classList.toggle("cookbook-badge--verified", recipe.evidence === "Verified");
evidenceCell.classList.toggle("cookbook-badge--source-backed", recipe.evidence !== "Verified");
}
source.href = `https://github.com/hao-ai-lab/FastVideo/blob/main/${recipe.source}`;
modelLink.href = `https://huggingface.co/${recipe.model}`;
command.textContent = recipe.command;
renderHardwareEvidence(hardwareState, hardwareBadge, recipe);
const limitations = recipe.limitations || [];
notes.replaceChildren();
notes.hidden = limitations.length === 0;
if (limitations.length) {
const notesHeading = document.createElement("strong");
notesHeading.textContent = "Know before you run";
const notesList = document.createElement("ul");
limitations.forEach((item) => {
const listItem = document.createElement("li");
listItem.textContent = item;
notesList.append(listItem);
});
notes.append(notesHeading, notesList);
}
const nextQuery = new URLSearchParams(window.location.search);
nextQuery.set("recipe", recipe.id);
nextQuery.set("runtime", runtime.id);
nextQuery.delete("gpus");
const nextUrl = `${window.location.pathname}?${nextQuery.toString()}${window.location.hash}`;
if (historyMode === "push") window.history.pushState({}, "", nextUrl);
else if (historyMode === "replace") window.history.replaceState({}, "", nextUrl);
status.textContent = `${recipe.label} selected for ${runtime.label}.`;
};
modelOptions.addEventListener("click", (event) => {
const option = event.target.closest("button[data-recipe-group]");
if (!option) return;
selectedGroupId = option.dataset.recipeGroup;
render({ groupChanged: true, historyMode: "push" });
});
hardwareOptions.addEventListener("click", (event) => {
const option = event.target.closest("button[data-recipe-id]");
if (!option) return;
selectedRecipeId = option.dataset.recipeId;
selectedGroupId = groupIdFor(byId.get(selectedRecipeId));
render({ historyMode: "push" });
});
render();
window.addEventListener("popstate", () => {
const nextQuery = new URLSearchParams(window.location.search);
const nextRecipe = nextQuery.get("recipe");
selectedRecipeId = nextRecipe && byId.has(nextRecipe) ? nextRecipe : defaultRecipeId;
selectedGroupId = groupIdFor(byId.get(selectedRecipeId));
render({ historyMode: "none" });
});
};
const init = () => {
document.querySelectorAll("[data-cookbook]").forEach(async (root) => {
initPatterns(document);
document.querySelectorAll("[data-cookbook][data-family]").forEach((root) => {
if (root.dataset.initialized) return;
root.dataset.initialized = "true";
const select = root.querySelector("[data-cookbook-recipe]");
const model = root.querySelector("[data-cookbook-model]");
const source = root.querySelector("[data-cookbook-source]");
const command = root.querySelector("[data-cookbook-command]");
const status = root.querySelector("[data-cookbook-status]");
try {
const { recipes } = await loadRecipes(root.dataset.recipes);
const byId = new Map(recipes.map((recipe) => [recipe.id, recipe]));
const groups = new Map();
select.replaceChildren();
recipes.forEach((recipe) => {
if (!groups.has(recipe.task)) {
const group = document.createElement("optgroup");
group.label = recipe.task;
groups.set(recipe.task, group);
select.append(group);
}
groups.get(recipe.task).append(new Option(recipe.label, recipe.id));
});
const render = () => {
const recipe = byId.get(select.value);
model.textContent = recipe.model;
source.textContent = recipe.source;
source.href = `https://github.com/hao-ai-lab/FastVideo/blob/main/${recipe.source}`;
command.textContent = recipe.command;
status.textContent = `${recipe.label} selected.`;
};
select.addEventListener("change", render);
select.disabled = false;
render();
} catch (error) {
status.textContent = "Recipes could not be loaded. Use the examples link below.";
console.error("Failed to load FastVideo cookbook recipes", error);
}
initFamilyBuilder(root);
});
};
docs/assets/custom.css
+1409 -38
View File
File diff suppressed because it is too large Load Diff
docs/assets/logos/SOURCES.md
+26
View File
@@ -0,0 +1,26 @@
# Cookbook logo sources
All marks are official publisher assets from Hugging Face organization pages
(vendored byte-for-byte from each org's public avatar). No imitation or
redrawn logos are used. Families without a publisher-appropriate mark use a
plain typographic tile instead — that tile is a UI placeholder, not a logo.
| Asset | Source | Purpose |
| --- | --- | --- |
| `wan-ai.webp` | [Official Wan-AI Hugging Face organization avatar](https://huggingface.co/Wan-AI) | Wan family card and page header |
| `ltx.webp` | [Official Lightricks Hugging Face organization avatar](https://huggingface.co/Lightricks) | LTX family card and page header |
| `tencent-hunyuan.webp` | [Official Tencent Hunyuan Hugging Face organization avatar](https://huggingface.co/Tencent-Hunyuan) | Hunyuan and GameCraft cards, Hunyuan page header |
| `nvidia.webp` | [Official NVIDIA Hugging Face organization avatar](https://huggingface.co/nvidia) | Cosmos and GEN3C cards, Cosmos page header |
| `kandinsky.webp` | [Official Kandinsky Lab Hugging Face organization avatar](https://huggingface.co/kandinskylab) | Kandinsky 5 family card and page header |
| `black-forest-labs.webp` | [Official Black Forest Labs Hugging Face organization avatar](https://huggingface.co/black-forest-labs) | FLUX family card and page header |
| `minimax.webp` | [Official MiniMax Hugging Face organization avatar](https://huggingface.co/MiniMaxAI) | MiniMax H3 family card and page header |
| `tongyi.webp` | [Official Tongyi MAI Hugging Face organization avatar](https://huggingface.co/Tongyi-MAI) | Z-Image family card and page header |
| `zai.webp` | [Official Z.ai Hugging Face organization avatar](https://huggingface.co/zai-org) | GLM-Image family card and page header |
| `stabilityai.webp` | [Official Stability AI Hugging Face organization avatar](https://huggingface.co/stabilityai) | Stable Diffusion and Stable Audio cards and page headers |
| `meituan-longcat.webp` | [Official Meituan LongCat Hugging Face organization avatar](https://huggingface.co/meituan-longcat) | LongCat family card and page header |
| `fastvideo.webp` | [Official FastVideo Hugging Face organization avatar](https://huggingface.co/FastVideo) | Matrix Game and MMAudio cards (converted weights published by this org), DreamX card |
Typographic tiles (no vendored image): TurboDiffusion ("Turbo"), HY-World
("HY"), LingBot ("LB"), MMAudio page header ("MMA"). These publishers have no
single official mark appropriate for reuse in the catalog; add a licensed
asset here if one becomes available.
docs/assets/logos/black-forest-labs.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.2 KiB

docs/assets/logos/fastvideo.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.9 KiB

docs/assets/logos/kandinsky.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.1 KiB

docs/assets/logos/ltx.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.3 KiB

docs/assets/logos/meituan-longcat.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.1 KiB

docs/assets/logos/minimax.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.1 KiB

docs/assets/logos/nvidia.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 3.5 KiB

docs/assets/logos/stabilityai.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.8 KiB

docs/assets/logos/tencent-hunyuan.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 7.6 KiB

docs/assets/logos/tongyi.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.0 KiB

docs/assets/logos/wan-ai.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.8 KiB

docs/assets/logos/zai.webp
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.4 KiB