source
Character Animation (AnimateAnyone, Face Reenactment)
[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation
GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code
Memory mapped numpy arrays of varying shapes
faster-whisper as serverless endpoint
A PyTorch Implementation of Single Shot MultiBox Detector
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
This is the official source for our ICCV 2023 paper "EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation"
Small scale distributed training of sequential deep learning models, built on Numpy and MPI.
Exporting Segment Anything, MobileSAM, and Segment Anything 2 into ONNX format for easy deployment
A quick-start Leptos template with TailwindCSS and Nix.
Official PyTorch implementation of StyleGAN3
FFmpeg Kit for applications. Supports Android, Flutter, iOS, Linux, macOS, React Native and tvOS. Supersedes MobileFFmpeg, flutter_ffmpeg and react-native-ffmpeg.
Machine Learning Journal for Intermediate to Advanced Topics.
[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
Best practices & guides on how to write distributed pytorch training code
Programming assignments and quizzes from all courses within the GANs specialization offered by deeplearning.ai
gradio WebUI for AdvancedLivePortrait
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
使用onnxruntime部署LivePortrait人像动画生成，包含C++和Python两个版本的程序
Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Accelerating Image Super-Resolution Networks with Pixel-Level Classification (ECCV 2024)
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation