WanTrackToVideo - ComfyUI Built-in Node Documentation

The WanTrackToVideo node converts motion tracking data into video sequences by processing track points and generating corresponding video frames. It takes tracking coordinates as input and produces video conditioning and latent representations that can be used for video generation. When no tracks are provided, it falls back to standard image-to-video conversion.

Inputs

Parameter	Description	Data Type	Required	Range
`positive`	Positive conditioning for video generation	CONDITIONING	Yes	-
`negative`	Negative conditioning for video generation	CONDITIONING	Yes	-
`vae`	VAE model for encoding and decoding	VAE	Yes	-
`tracks`	JSON-formatted tracking data as a multiline string (default: ”[]”). Each track is padded or truncated to a fixed length of 121 points.	STRING	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 output video (default: 81, step: 4)	INT	Yes	1 to MAX_RESOLUTION
`batch_size`	Number of videos to generate simultaneously (default: 1)	INT	Yes	1 to 4096
`temperature`	Temperature parameter for motion patching (default: 220.0, step: 0.1)	FLOAT	Yes	1.0 to 1000.0
`topk`	Top-k value for motion patching (default: 2)	INT	Yes	1 to 10
`start_image`	Starting image for video generation	IMAGE	No	-
`clip_vision_output`	CLIP vision output for additional conditioning	CLIP_VISION_OUTPUT	No	-

Note: When tracks contains valid tracking data, the node processes motion tracks to generate video. When tracks is empty, it switches to standard image-to-video mode. If start_image is provided, it initializes the first frame of the video sequence, and the motion patching result is added to both positive and negative conditioning. If clip_vision_output is provided, it is also added to both positive and negative conditioning.

Outputs

Output Name	Description	Data Type
`positive`	Positive conditioning with motion track information applied	CONDITIONING
`negative`	Negative conditioning with motion track information applied	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): e67fe326dd7e5ae63ddc35946d8144138d04d9523ec1ad2e08ea6bc1dc9325da

​Inputs

​Outputs

Inputs

Outputs