VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

Code of LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

Genome modeling and design across all domains of life

Wan: Open and Advanced Large-Scale Video Generative Models

[IEEE TPAMI] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

Original implementation of "Radiant Foam: Real-Time Differentiable Ray Tracing"

Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

real time face swap and one-click video deepfake with only a single image

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

This Git offers a faster and easy-to-use 3DMM tracking pipeline with FaceVerse V4 (CVPR 2022), which is a full head model that includes separate eyeballs, teeth, and tongue.

A generative world for general-purpose robotics & embodied AI learning.

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25).

Code of [CVPR2025] AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

HunyuanVideo: A Systematic Framework For Large Video Generation Model

This is a repository for GraspXL, which can generate objective-drive grasping motions for 500k+ objects with different dexterous hands.

More relighting!

Official repository for LTX-Video

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

MikuDance: Animating Character Art with Mixed Motion Dynamics

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar