research featured Introducing lipsync-1.9-beta — a new standard for lipsync quality The most natural lipsyncing model in the world
research Lipsync-1.8.0-beta in research preview We bought a ton of gpus + baked a new zero-shot model that works on any video in the wild. It's our best yet, by far. A lot of you asked us to generate better teeth. well, we did. Challenge is our old approach wouldn't let us
research Audio-Visual Face Reenactment Madhav Agarwal, Rudrabha Mukhopadhyay, Vinay P. Namboodiri, C. V. Jawahar
research A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild K R Prajwal, Rudrabha Mukhopadhyay, Vinay P. Namboodiri, C V Jawahar
research Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis K R Prajwal*, Rudrabha Mukhopadhyay*, Vinay P. Namboodiri, C V Jawahar