LTX Video AlphaGen - ComfyUI Built-in Node Documentation

Extracts a grayscale alpha matte, white for foreground, that matches the input video frame for frame. Feed the matte to Get Video Components and Image To Mask to turn it into a mask. Audio is not kept.

Inputs

Parameter	Description	Data Type	Required	Range
`video`	Video to matte, up to 10 seconds and 3840x2160 in either orientation.	VIDEO	Yes	-
`seed`	Controls whether the node re-runs; results are non-deterministic regardless of the seed. Default: 42.	INT	No	0 to 4294967295

Outputs

Output Name	Description	Data Type
`matte`	The alpha matte as a video, one frame per input frame and without audio.	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): 54a8304c2d092a736ad7fb86c8497aceda6340886beb81b6068a3de5a387a746