Starred repositories
Krea Realtime 14B. An open-source realtime AI video model.
Dataset for paper "OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation"
20
Updated Oct 27, 2025
[NeurIPS 2025] TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Community trainer for Lightricks' LTX Video model 🎬 ⚡️
Wan: Open and Advanced Large-Scale Video Generative Models
We write your reusable computer vision tools. 💜
An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation
HyperMotion is a pose guided human image animation framework based on a large-scale video diffusion Transformer.
MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head
Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions
SkyReels-V2: Infinite-length Film Generative model
[CVPR 2025 Oral] PyTorch re-implementation for Autoregressive Distillation of Diffusion Transformers (ARD).
[ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"
Lets make video diffusion practical!
[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo
Enjoy the magic of Diffusion models!
Wan: Open and Advanced Large-Scale Video Generative Models
A unified inference and post-training framework for accelerated video generation.