Home

LatentSync - Audio Conditioned Latent Diffusion Models for Lip Sync

1. Introduction 2. Related Work 2.1. Diffusion-based Lip Sync Diff2lip DiffusionVideoEditing MyTalk StyleSync Diffdub Diff2lip Soumik Mukhopadhyay, Saksham Suri, Ravi Teja Gadde, and Abhinav Shrivastava. Diff2lip: Audio conditioned diffusion models for lip-synchronization. In Proceedings of the IEEE/CVF Winter Conference on Applications o...

Read more