VeedFabricNode - ComfyUI Built-in Node Documentation - ComfyUI

Turn a still image and a speech track into a talking, lip-synced video with VEED Fabric. It works with photos, illustrations and mascots as long as the face is clearly visible; the video keeps the image’s aspect ratio and is as long as the audio.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	Model to use. Selecting a model reveals the parameters specific to it: `image`, `audio` and `resolution`.	DYNAMIC_COMBO	Yes	`"fabric-1.0"`
`image`	Image with a clearly visible face. The video keeps its aspect ratio.	IMAGE	Yes	-
`audio`	Speech to lip-sync to, up to 300 seconds. Sets the video length.	AUDIO	Yes	Up to 300 seconds
`resolution`	Output size class: about 0.4 megapixels at `"480p"` (864x480 at 16:9) and 0.9 megapixels at `"720p"` (1312x736 at 16:9). (default: `"720p"`)	COMBO	Yes	`"480p"` `"720p"`

The node stops with an error when the speech track is longer than 300 seconds.

Outputs

Output Name	Description	Data Type
`VIDEO`	The talking video: the input image animated to match the speech track.	VIDEO

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): 69cabfa5f03885ce770e8502419305dacee49d7e89a748f31abe3775d682a33a