anliyuan/FeatherTalk

一个超轻量级、可以在移动端实时运行的数字人模型

Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

We propose LeapTalk, a novel framework that achieves stable and real-time talking-head generation with a single forward step, scaling to arbitrarily long videos.

ACM MM | IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer

Official implementation of Talk Like You

AnyTalker: Scaling Multi-person Talking Video Generation with Interactivity Refinement

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

AVTR-1: Avatars that listen back

Real-time, long-horizon audio-driven avatar generation via decoupled parallel training.