WanUni3CControlnetApply - ComfyUI Built-in Node Documentation

Overview

This node applies a Uni3C ControlNet to a Wan video diffusion model, using a rendered guidance video (e.g., warped point cloud renders) to influence the model’s output. It injects control signals at specific block layers, enabling camera‑trajectory‑based guidance during video generation.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The Wan diffusion model to patch.	MODEL	Yes	–
`model_patch`	A Uni3C ControlNet patch (must be an instance of `comfy.ldm.wan.uni3c.WanUni3CControlnet`).	MODEL_PATCH	Yes	–
`vae`	The VAE used to encode the guidance video into latents.	VAE	Yes	–
`render_video`	The guidance video rendered from the camera trajectory, most commonly warped point cloud renders of the input image.	IMAGE	Yes	–
`strength`	The strength of the control signal applied.	FLOAT	Yes	-10.0 to 10.0 (default: 1.0)
`start_percent`	The percentage of the denoising process at which the control starts.	FLOAT	Yes	0.0 to 1.0 (default: 0.0)
`end_percent`	The percentage of the denoising process at which the control ends.	FLOAT	Yes	0.0 to 1.0 (default: 1.0)

Notes:

The model_patch must be a Uni3C ControlNet; otherwise the node raises an error.
The controlnet’s internal dimension must match the Wan model’s dimension – an error is raised if they differ.
The render_video input image is expected to be in RGB format (only the first 3 channels are used).

Outputs

Output Name	Description	Data Type
`MODEL`	The patched Wan model with the Uni3C ControlNet applied.	MODEL

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): f69253f06aba9208778f713ad36e9995f53a15d2e61243b853b9ac9131637371

​Overview

​Inputs

​Outputs

Overview

Inputs

Outputs