Queue size: 0
diff --git a/dev/macos-desktop/debug/electron_inspect/driver.mp4 b/dev/macos-desktop/debug/electron_inspect/driver.mp4 index fdda7acd..4500eaac 100644 Binary files a/dev/macos-desktop/debug/electron_inspect/driver.mp4 and b/dev/macos-desktop/debug/electron_inspect/driver.mp4 differ diff --git a/dev/macos-desktop/debug/electron_inspect/final.html b/dev/macos-desktop/debug/electron_inspect/final.html index c85e2754..75eef1c5 100644 --- a/dev/macos-desktop/debug/electron_inspect/final.html +++ b/dev/macos-desktop/debug/electron_inspect/final.html @@ -1,4 +1,4 @@ -


Upload two reference images and input a short text description. Generate a detailed Seedance 2.0 style prompt automatically with an LLM helper.

Generate cinematic videos from reference images and text prompts. Preserve subject identity and composition while adding expressive motion with synchronized audio. Control camera movement and lighting through detailed prompts.

Generate cinematic videos from text prompts with synchronized audio, controlled camera motion, and stable visuals. Input text descriptions to output high quality video sequences.

Upload the first and last frames of your video. Generate a high quality video sequence using the Seedance2.0 model.

Upload a reference image of a real person for identity verification and generate a personalized video with first and last frame control using Seedance2.0 FLF2V.

Upload a reference video of a real person for identity verification. Use your own photo to validate and generate a personalized video output.
Upload an image of your character and get multiple views of that image from different angles
Apply the ltx2.3 transition LoRA to create smooth style and scene transitions. This workflow uses a specialized model to blend visual elements.

Upload your character, scene and product. Integrates all images into a fashion editorial style photograph.


Upload 8 images (in order) to be used as keyframes for 7 Kling 3.0 FL2V videos.

Upload a portrait of your character and create multiple cinematic lighting conditions while maintaining character consistency.

Upload a graphic design and select your desired aspect ratio. Generates and recomposes the graphic to fit the new aspect ratio.



Upload an image to generate AI prompts and synthesize speech. Create a final video with accurate lip sync using Eleven Labs and LTX Video.


Swap products into a reference scene while preserving composition and lighting. Generates a final product image and an automatic video prompt for creating polished product videos.
A t2v workflows for a style LoRA built on Qwen Image. Produces images spanning cute anime character design, European bande dessinee, indie risograph prints, storybook watercolor, retro shoujo manga, and graphic novel illustration.
Apply a Qwen Image LoRA to transform any subject into a sour gummy candy style character. Enter an animal name in the prompt to generate a stylized, edible looking creature.

Generate high contrast, clickable YouTube thumbnails using Nano Banana Pro. Creates dramatic compositions with exaggerated subjects and bold color strategies for maximum engagement.


This is the base workflow behind my viral Wes Anderson style reel on Instagram. It shows how to go from a simple prompt to a Wes Anderson style image using a cinematic image model, then enhance it with Nanobanana to improve textures and details, and finally turn it into a video using the current best video model, Kling 3.0.

Transform uploaded images into realistic poster designs. Change character poses, faces, and clothing while maintaining artistic style and color schemes. Outputs a visually impactful poster with artistic typography.

Upload a reference image, uses Grok to caption and generate variations with a fast 2x upscale for added details.
Upload your target image and a reference lighting image. Relights your target image.

Upload a product image and a cinematic style reference. Generate a sequence of stylized product advertisements with consistent composition and lighting.

Use an outline reference, and a style reference as input to generate 2D sprite as model textures. Useful for background set dressing in 2D/2.5D game.


Upload an image to automatically generate a descriptive script. This script is then used to create a video with the Kling 3.0 Omni model.

Upload an image that you want a variation of. The workflow captions the input image, generates with Grok Image, and upscales with Z image to add realistic textures.

Upload your character and generate 360 turnaround views for full body and close ups.
Upload a portrait of your character and a reference lighting image. Generate an image with reference lighting applied and character consistency.
Input an illustration and generate a hyper realistic version using Qwen Image Edit 2509.

Upload your character portrait and outfit reference. Generate a new portrait with the specific outfit applied for consistent wardrobe control. Affordable alternative to Nano Banana Pro and Nano Banana 2.


Upload an image of a device or object to generate start and end frames. The workflow animates the transition to an exploded view and back, outputting a seamless video loop.

Upload 1 5 style references and create a style ID to generate consistent, on brand images.
Upload an image of your scene and generate multiple views of your input scene with 1 click.

Upload an image and generate 12 stylized variations in under 15 seconds.
Take a picture with your phone, upload it and generate a studio grade product video.
Creates a smooth video using 6 key frames.It auto fills in the motion between frames and stitches the segments together seamlessly.





upload one input image and select multiple editing models. generate side by side outputs to directly compare model effects and quality.

Upload a photo of a character holding a product and your brands product. Generate an image with the products swapped.

Upload an image of your product and background. Composite them and seamlessly relight and fuse together using Seedream 4.5.


Upload a starting image and its prompt to generate a looping video from the first to the last frame.


Upload a vector image of your logo, and prompt your desired texture. Generate a textured 3D first and last frame with automated prompting for the final animation.
Upload a photo of your vehicle and generate a studio quality video of the vehicle from multiple angles.


Upload your logo, texture and elements. Generate a video of the textured logo for an on brand asset.

Upload a photo of your character and your product. Generate an image of that character holding the product.


Upload your logotype and apply a texture + elements for on brand asset

Upload a dieline of your product and assemble into a 3D package.


Create static ads for your product in the style of a reference advertisement

Input a black and white illustration and generate a colored output.

Design the text layout for your magazine cover photo, and explore packaging options for it.