Lip-Sync Dubbery, designed for music videos.
Photoreal lip-sync dubbing that warps the face's own mouth — its teeth, gums, lips and tongue — to say new words. No painted mouth. No face swap. Open weights only. Every pixel on screen is the clip's own, moved to fit the audio frame by frame.
Our entry in the Open Source Higgsfield ComfyUI contest.
Submissions for Open Source Higgsfield close Oct 30, 9:00 am PT. Winners featured on comfy.org/hub.
One render opens every 15 minutes. Pick a face, drop in audio and the words, and take your place in line.
Join the line ▸ Next slot opens soon · live queue belowA 30-second cut, dubbed line by line. The teeth, the gums, the tongue covering the lower teeth — all harvested from the face itself, then warped to the new vocal.
Every other lip-sync tool paints a new mouth over the face or swaps the face outright. LSDub does neither. We harvest the clip's own mouth, build it in a canonical dental-arch atlas, and warp that atlas to the audio target for every frame. The result is the person's real teeth and lips — never a model's guess.
Teeth, gums, tongue and lips are the face's own, lifted from its best frames and re-posed. No inpainting, no painted enamel, no borrowed smile.
Built on LTX-2.5 and open-weights tooling only. No partner APIs, no closed models — qualifies for Open Weights Only + the LTX bonus.
One vocal track drives a whole gallery of faces. The same words, the same timing, across every character — a face-chain you play.
Pick a face, give it words, hear it sing. One render opens every 15 minutes — you'll take a numbered place in line and the clip comes back to you.
Built with LTX-2.5. Open weights only. Every mouth is the face's own. #OpenSourceHiggsfield
We'll let you know when the line opens, and when LSDub ships as a ComfyUI node pack you can run yourself.