How likely each dubbed shot is to have worked: a 0-100 score and PASS / REVIEW / FAIL, compared with the source (sync, mouth travel, silences, identity drift)…

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

render

shots

song

align

How likely each dubbed shot is to have worked: a 0-100 score and PASS / REVIEW / FAIL, compared with the source (sync, mouth travel, silences, identity drift).

Name	Type	Description
project	LSDUB_PROJECT	The LSDub project.
source	LSDUB_SOURCE	The video before the dub.
render	LSDUB_RENDER	The dub to verify.
shots	LSDUB_SHOTS	The triaged shots.
song	LSDUB_SONG	The song (its lead vocal).
align	LSDUB_ALIGN	The word timings.

Name	Type	Description
report	LSDUB_REPORT	Per-shot band and score, the shots to fix.
md	STRING	Markdown: worst first, with the reason.

LSDub Verify

Inputs (6)

Outputs (2)