Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

An multi-platform GUI library for Python based on Dear ImGui with a lot of customization possibilities.

Deep Contextual Video Compression

Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.

[Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models

Run Nintendo Switch homebrew & games on your Android device!

Common 2D and 3D image registration methods such as rigid, affine, and flow field for PyTorch.

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

Hosts the Multiface dataset, which is a multi-view dataset of multiple identities performing a sequence of facial expressions.

High-resolution models for human tasks.

Offical implement of Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for talking head Video Generation

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

uYouEnhanced (by @arichornlover) is an expanded version of uYou+ (made by @qnblackcat) with additional features and mainly made for non jailbroken users!

Advanced player for set-top boxes and tvs running Android OS

Official implementation for the SIGGRAPH Asia 2024 paper SPARK: Self-supervised Personalized Real-time Monocular Face Capture

Port of MediaPipe tflite models to PyTorch

[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"

A collaboration friendly studio for NeRFs

DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer

A novel apporach for personalized speech-driven 3D facial animation

TEMPEH reconstructs 3D heads in dense semantic correspondence from calibrated multi-view images in about 0.3 seconds.

This is the official source for our ICCV 2023 paper "EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation"

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

ComfyUI related stuff and things

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model