Image to Video with Wan

Turn still images into amazing videos with just prompts, using the SOTA Wan video model.

Video/Image2Video_Wan.json

Verified to work on ThinkDiffusion Build: April 1, 2025

Why do we specify the build date? ComfyUI and custom node versions that are part of this workflow that are updated after this date may change the behavior or outputs of the workflow.

Minimum machine size: ULTRA

Use the specified machine size or higher to ensure it meets the VRAM and performance requirements of this workflow.

Key Inputs

Load: Use any JPG or PNG showing your subject clearly

Width & height: Make sure the resolution does not exceed 1280 x 720. Once exceeded, there will be a decrease in quality.

Keep Proportion: Enable keep_proportion if you want to keep the same size for the input and output.

Prompt: as descriptive a prompt as possible

Video Length: 96 Frames maximum

File Format: H.264 and more

Output Path

../outputs/Image2Video_Wan/

Examples