Score every shot of the cut 0-100 (sync, silences, snap, face size, mouth visible, motion, pops, sharpness), worst first. — ComfyUI node from LSDub. Run it in…

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

source

shots

song

align

render

Score every shot of the cut 0-100 (sync, silences, snap, face size, mouth visible, motion, pops, sharpness), worst first.

Name	Type	Description
project	LSDUB_PROJECT	The LSDub project.
source	LSDUB_SOURCE	The video (judged in test_learn, when there is no dub).
shots	LSDUB_SHOTS	The shots.
song	LSDUB_SONG	The song (its lead vocal).
align	LSDUB_ALIGN	The word timings.
renderopt	LSDUB_RENDER	The dub to score (else the source).

Name	Type	Description
report	LSDUB_REPORT	Per-shot class and score.
md	STRING	Markdown scorecard.

LSDub Scorecard

Inputs (6)

Outputs (2)