LatentSync
Taming Stable Diffusion for Lip Sync!
About
We present LatentSync, an end-to-end lip-sync method based on audio-conditioned latent diffusion models without any intermediate motion representation, diverging from previous diffusion-based lip-sync methods based on pixel-space diffusion or two-stage generation. Our framework can leverage the powerful capabilities of Stable Diffusion to directly model complex audio-visual correlations.
Open Source Health
- Stars
- 6,067
- Forks
- 975
- License
- Apache-2.0
- Last commit
- 1 years ago
Related Categories
Vendor
ByteDance
Publisher of UI TARS Desktop, Trae Agent and danmu.js
Quick Links
Open Source
More by ByteDance
Related Products
Krea
Krea is the world's most powerful creative AI suite.
Top category match
AI Image Enlarger
Image Enlarger & Upscaler Online
Top category match
Kreator.ai
AI Creative Platform for Images, Video, Ads, and Brand Content
Top category match
The Algorithm
Source code for the X Recommendation Algorithm
Shared categories
Recommenders
TensorFlow Recommenders is a library for building recommender system models using TensorFlow.
Shared categories