Skip to content

MLSysTeam/fastavatar

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 

Repository files navigation

FastAvatar

Build a fast interactive avatar on your laptop and mobile phones.

Avatar Models

2D talking-face synthesis (milestone tasks, representative pipelines, challenge-insight tree, best practice)

The Pipeline of Interactive Avatars

xxx

Optimization Techniques

Model Acceleration

Pipeline Acceleration

Runtime Optimization

Hands-on Demos

  • MobileAvatar on Huawei Mate 30
  • LaptopAvatar on NVIDIA GeForce GTX 1070
  • WebAvatar on NVIDIA Tesla V100

References

  1. Chunyu Li et al. "LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision". arXiv preprint arXiv:2412.09262.
  2. Lingteng Qiu et al. "LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds". arXiv preprint arXiv:2503.10625.
  3. Yisheng He et al. "LAM: Large Avatar Model for One-shot Animatable Gaussian Head". SIGGRAPH 2025.
  4. Alibaba Group. "Open Avatar Chat". GitHub repo.
  5. Jianchuan Chen et al. "TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting". CVPR 2025 (Highlight).

About

Build a fast interactive avatar on your laptop and mobile phones

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published