rCM: SOTA Diffusion Distillation & Few-Step Video Generation based on sCM/MeanFlow

Solve puzzles. Improve your pytorch.

Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

LongLive: Real-time Interactive Long Video Generation

SAM 3D Objects

LLM Council works together to answer your hardest questions

[NeurIPS 2025] Radial Attention: O(n\log n) Sparse Attention with Energy Decay for Long Video Generation

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

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

StreamDiffusion, Live Stream APP

Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

A timeline of notable generative AI events

PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

This is the repository that contains source code for the PhysGen3D.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Motion-Controllable Video Diffusion via Warped Noise

HaMeR: Reconstructing Hands in 3D with Transformers

The official implementation of Segment Any 3D GAussians (AAAI-25)

Official PyTorch Implementation of "History-Guided Video Diffusion"