Official implementation of AnimateDiff.

Official repo and evaluation implementation of VSI-Bench

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.

Memory-optimized training scripts for video models based on Diffusers

GenXD: Generating Any 3D and 4D Scenes

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

田柯宇 (Tian Keyu)恶意攻击集群事件的证据揭露

[TPAMI 2023] SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

[CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

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

ECCV 2024: Controllable Motion Generation through Language Guided Pose Code Editing

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Generative Models by Stability AI

Code release for https://kovenyu.com/WonderWorld/

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".

Grounding Image Matching in 3D with MASt3R

DUSt3R: Geometric 3D Vision Made Easy

Evaluating Multiview Object Correspondence between Humans and Image models

Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.