Luozhou Wang

WorldDirector. Python

mira. Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

text-to-cad. A collection of agent skills for CAD, robotics and hardware design

StreamMA. Official implementation of "Streaming Communication in Multi-Agent Reasoning"

LongLive-RAG. Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

Pointer-CAD. Python

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Stable-Video-Infinity. [ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

lyra. Project Lyra: Open Generative 3D World Models

CC. TypeScript

AutoResearchClaw. Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

IndexCache. IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

RealWonder. Real-Time Physical Action-Conditioned Video Generation

Motion-Forcing. Official implementation of Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics

CLI-Anything. "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

PAP. Panoramic Affordance Prediction (PAP) (ECCV 2026)

autoresearch. AI agents running research on single-GPU nanochat training automatically

worldfm. Python

Helios. Helios: Real Real-Time Long Video Generation Model

Causal-Forcing. [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Lean. Lean Algorithmic Trading Engine by QuantConnect (Python, C#)

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Context-Forcing. Context Forcing: Consistent Autoregressive Video Generation with Long Context [ICML26]

lingbot-world. Advancing Open-source World Models

VideoMemory. VideoMemory's Homepage

Awesome-Video-World-Models. A Mechanistic View on Video Generation as World Models: State and Dynamics

YUME. The official code of Yume

open-p2p. Official Repo for paper: Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing

Wan-Alpha. [CVPR 2026 Highlight] High-Quality Text-to-Video Generation with Alpha Channel

TurboDiffusion. TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

StereoPilot. The official implementation of StereoPilot

titans-pytorch. Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

MemFlow. Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"

LongVie. Python

UnityVideo. [CVPR 2026]UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

DiT-Mem. Learning Plug-and-play Memory for Guiding Video Diffusion Models

ProphRL. Reinforcing Action Policies by Prophesying

DualCamCtrl. [ECCV 2026] DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation

VANS. [CVPR 2026] Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO

FastVideo. A unified inference and post-training framework for accelerated video generation.

TiViBench. [CVPR 2026] TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models

WorldMem. [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory

open-oasis. Inference script for Oasis 500M

STANCE. STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding

UniCalli. Official implementation of UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

MTI. [ACL 2026] Official implementation of "Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention"

PhysToolBench. PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

LongLive. Long Video Gen Infrastructure

T2I-CoReBench. [ICLR'26] Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

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

UniTEX. Official implementation of "UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes"

Matrix-3D. Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

Waver. Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

Long-RL. Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

ComfyMind. ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback

CausVid. (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

attention-gym. Helpful tools and examples for working with flex-attention

Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

UniTEX-FLUX. Flux training codes (lora) for UniTEX

FlexPainter. [Arxiv 2025] FlexPainter: Flexible and Multi-View Consistent Texture Generation

UniTEX. [CVPR 2026]Official implementation of "UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes"

diffusion-forcing-transformer. [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

FractFlow. Python

codex. Lightweight coding agent that runs in your terminal

FramePack. Lets make video diffusion practical!

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Fusion360GalleryDataset. Data, tools, and documentation of the Fusion 360 Gallery Dataset

onshape-cad-parser. Python

hawk. 🔥[NeurIPS 2024] Official Implementation of Hawk: Learning to Understand Open-World Video Anomalies

MovieDreamer. [ICLR'25] MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences

DeepCAD. code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

MSI-NeRF. [WACV2025] Linking Omni-Depth with View Synthesis through Multi-Sphere Image aided Generalizable Neural Radiance Field

EINRUL. [ICRA2023] Efficient Implicit Neural Reconstruction Using LiDAR

RectifiedHR. [CVPR Findings 2026] Official implementation of "RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification"

Kiss3DGen. [CVPR 2025] Official implementation of "Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation"

Uni-Renderer. Official implementation of "Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion" [CVPR2025]

DiT-Extrapolation. Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

HunyuanVideo-Training. Python

diffusion-pipe. A pipeline parallel training script for diffusion models.

Gaussian-Property. Official implementation of GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs.

Awesome-Physics-aware-Generation. Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and shaping the future!

DeepSeek-R1.

star-history. The de facto GitHub star history graph.

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

LeviTor. [CVPR'25 Highlight] Official implementation for paper - LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

TransPixeler. CVPR2025

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

CoPRA. [AAAI 2025] CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

common_metrics_on_video_quality. You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

VideoTuna. Let's finetune video generation models!

Cosmos-Tokenizer. A suite of image and video neural tokenizers

Harmonizer. High-Resolution Image/Video Harmonization [ECCV 2022]

finetrainers. Scalable and memory-optimized training of diffusion models

mochi. The best OSS video generation models, created by Genmo

Allegro. Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

LucidFusion. Official implementation of “LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images”

cogvideox-loras. CogVideoX-LoRAs is a centralized repository for all LoRA models created for CogVideoX, filling the gap for a unified sharing space. With the rising demand for customized video generation, this hub enables users, developers, and researchers to easily access, contribute to, and collaborate on various tailored LoRA models.

DDBM. Python

ViewCrafter. [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

VideoSys. VideoSys: An easy and efficient system for video generation

sam2. 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 the model.

flux. Official inference repo for FLUX.1 models

Awesome-Video-Datasets. Video datasets

diffusion-forcing. code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Defect_Spectrum. Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics (ECCV2024)

SEED-Story. SEED-Story: Multimodal Long Story Generation with Large Language Model

FilmRemoval. [CVPR 2024] Official Implementation of Learning to Remove Wrinkled Transparent Film with Polarized Prior

via-video.

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

MGM. Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

mvdream_diffusers. A unified diffusers implementation for MVDream and ImageDream

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

diffusion-motion-transfer. Official Pytorch Implementation for "Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer""

MotionDirector. [ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

DDSM. Denoising Diffusion Step-aware Models (ICLR2024)

MotionInversion. [SIGGRAPH 2025] Official implementation of 'Motion Inversion For Video Customization'

Moore-AnimateAnyone. Character Animation (AnimateAnyone, Face Reenactment)

HumanML3D. HumanML3D: A large and diverse 3d human motion-language dataset.

magvit2-pytorch. Implementation of MagViT2 Tokenizer in Pytorch

Video-Swin-Transformer. This is an official implementation for "Video Swin Transformers".

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

MotionCtrl. Official Code for MotionCtrl [SIGGRAPH 2024]

LLaMA2-Accessory. An Open-source Toolkit for LLM Development

magic-animate. [CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

TASC. Python

InstaFlow. :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

LucidDreamer. Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"

gpt4free. The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

langchain-gpt4free. LangChain x gpt4free

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

open_flamingo. An open-source framework for training large multimodal models.

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

ReLA. [CVPR 2023 Highlight & IJCV 2026] GRES: Generalized Referring Expression Segmentation

Link-Context-Learning. Python

SUR-adapter. ACM MM'23 (oral), SUR-adapter for pre-trained diffusion models can acquire the powerful semantic understanding and reasoning capabilities from large language models to build a high-quality textual semantic representation for text-to-image generation.

SG-Adapter. Python

HyperThumbnail. [CVPR 2023] Real-time 6K Image Rescaling with Rate-distortion Optimization. Official implementation.

Selective-Diffusion-Distillation. Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation (ICCV 2023)

Emu. Emu Series: Generative Multimodal Models from BAAI

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

refer. Referring Expression Datasets API

detrex. detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

StableLM. StableLM: Stability AI Language Models

consistency_models. Official repo for consistency models.

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

ControlNet. Let us control diffusion models!

DifFace. DifFace: Blind Face Restoration with Diffused Error Contraction (TPAMI, 2024)

dream-textures. Stable Diffusion built-in to Blender

prompt-to-prompt. Jupyter Notebook

CrossAttentionControl. Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion

einops. Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

DAI2I. This is the repository for CVPR paper "Domain Adaptive Image-to-image Translation"

ResizeRight. The correct way to resize images or tensors. For Numpy or Pytorch (differentiable).

pytorch-fid. Compute FID scores with PyTorch.

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

guided-diffusion. Python

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Models in PyTorch

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

DALLE2-pytorch. Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

open_clip. An open source implementation of CLIP.

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

pytorch_diffusion. PyTorch reimplementation of Diffusion Models

ddim. Denoising Diffusion Implicit Models

mmgeneration. MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

stylegan3. Official PyTorch implementation of StyleGAN3

latent-transformer. Official implementation for paper: A Latent Transformer for Disentangled Face Editing in Images and Videos.

dan_mmediting. Python

mmagic. OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

lola. LoL (League of Legends) game data analysis / analytics

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

SongRecogn. A Song Recognition Program using Shazam Algorithm

dota2-win-rate-prediction-v1. This is our first version of vpesports dota2 win rate prediction model. Learning and Testing only now