WanFunInpaintToVideo - ComfyUI Built-in Node Documentation

The WanFunInpaintToVideo node prepares conditioning and latent data for inpainting-style video generation, using an optional start image and end image to guide the result.

The WanFunInpaintToVideo node prepares conditioning and latent data for inpainting-style video generation, using an optional start image and end image to guide the result. It works by passing the supplied conditioning, VAE, and image frames through the same logic used for first-and-last-frame video generation, and returns updated conditioning plus an empty latent for sampling.

Inputs

Parameter	Description	Data Type	Required	Range
positive	Positive conditioning prompts for video generation	CONDITIONING	Yes	-
negative	Negative conditioning prompts to avoid in video generation	CONDITIONING	Yes	-
vae	VAE model used for encoding and decoding the video frames	VAE	Yes	-
width	Output video width in pixels (default: 832, step: 16)	INT	Yes	16 to MAX_RESOLUTION
height	Output video height in pixels (default: 480, step: 16)	INT	Yes	16 to MAX_RESOLUTION
length	Number of frames in the video sequence (default: 81, step: 4)	INT	Yes	1 to MAX_RESOLUTION
batch_size	Number of videos to generate in a batch (default: 1)	INT	Yes	1 to 4096
clip_vision_output	Optional CLIP vision output used as conditioning for the start image	CLIP_VISION_OUTPUT	No	-
start_image	Optional starting frame image for video generation	IMAGE	No	-
end_image	Optional ending frame image for video generation	IMAGE	No	-

Outputs

Output Name	Description	Data Type
positive	Processed positive conditioning output	CONDITIONING
negative	Processed negative conditioning output	CONDITIONING
latent	Generated video latent representation	LATENT

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): 70b58e961c5df12f94183245ce320197439b2505b47d0bb3ff643b25c9fe6175