Official implementation of the paper "Generative Inbetweening through Frame-wise Conditions-Driven Video Generation"

一个超轻量级、可以在移动端实时运行的数字人模型

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko,…

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

Using Claude Opus to reverse engineer code from Megaportrait white paper - WIP

Using Claude Opus to reverse engineer code from VASA white paper - WIP - (this is for La Raza 🎷)

offline 2d digitalhuman demo for edge devices (android/ios/etc.)

HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior

[CVPR2024] Official implementation of SplattingAvatar.

Realtime Holistic Mocap with Ground Contact

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

Luna AI - 全自动的 AI 直播系统

Codes and data for the TIP 2023 paper: Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image

Official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"

Use the Audio2Face headless server and interact with it through a requests API. Generate animation sequences for Unreal Engine 5, Maya and MetaHumans

unofficial implementation of Few-Shot Head Swapping in the Wild

This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].

The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."

AAAI paper diverse diffusion code

The official repository of our CVPR2023 paper "FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction".

HARP: Personalized Hand Reconstruction from a Monocular RGB Video

metahuman 5.1 plugin

A high-fidelity 3D face reconstruction library from monocular RGB image(s)