Titan AI LogoTitan AI

LatentSync

4,463
706
Python

项目描述

LatentSync is an end-to-end lip-sync method using audio-conditioned latent diffusion models to model complex audio-visual correlations without intermediate motion representation.

项目信息

创建于 12/11/2024
更新于 7/2/2025

分类

speech-technology
ai-content-generation
machine-learning-framework

标签

algorithm-model
model-deployment
data-processing
open-source-community
research-frontier

主题

video-gen
diffusion-models
lipsync
research
virtual-avatars