The picture to dub. Bring a finished video, or animate a still with LTX-2.5 (open weights) from a prompt. Saved in the project, keyed by its bytes or its…

Lip-sync for music videos in ComfyUI: dub the singers' mouths to the song, shot by shot, with QA. Every input is a slot (bring a clip and song, or generate them with LTX-2.5, Qwen-Image-Edit and ACE-Step); vocal split, lyric alignment, lip kits, sync QA.

LSDub

project

prompt

negative_prompt

seconds

video

still

The picture to dub. Bring a finished video, or animate a still with LTX-2.5 (open weights) from a prompt. Saved in the project, keyed by its bytes or its settings.

Name	Type	Default	Description
project	LSDUB_PROJECT		The LSDub project.
prompt	STRING		What happens in the clip (generated from the still). Ignored when video is connected.
negative_prompt	STRING		What to avoid in the generated clip.
seconds	FLOAT	5.01–20	Length of a generated clip, s.
videoopt	VIDEO		The finished video (e.g. from Load Video). Takes priority.
stillopt	IMAGE		A still: dubbed as is, or animated when a prompt is given (use LSDub Still to make or edit one).

Name	Type	Description
source	LSDUB_SOURCE	The source record: path, hash, fps, frames, size.
video	VIDEO	The video, for previews.

LSDub Video

Inputs (6)

Outputs (2)