WeichenFan

openpi. Python

FastWAM. Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

stable-worldmodel. A platform for reproducible world model research and evaluation

minit2i-jax. Official JAX code of MiniT2I.

Spectral_Forcing. Code of "Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion"

tuna-2. Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

SenseNova-U1. SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

dino_wm. Python

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

SpectrumMatching. official code for the paper 'Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion'

NEO. NEO Series: Native Vision-Language Models from First Principles

EAR. Python

BiFlow. Official Implementation of BiFlow https://arxiv.org/abs/2512.10953

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

UniTok. [NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

DynamicVLA. The official implementation of "DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation". (arXiv 2601.22153)

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

DCTdiff. [ICML 2025] Official code for the paper 'DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space'

CE7455. Jupyter Notebook

UAE. Official repo for UAE [ECCV 2026]

pico-banana-400k. Python

awesome-nanobanana-pro. 🚀 An awesome list of curated Nano Banana pro prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of the Nano banana pro(Nano banana 2) AI image model.

JiT. PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

mf-rae. Python

Diffusion-Explorer. Interactive visualizations of the geometric intuition behind diffusion models.

UniFlow. Official Implementation of "UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation"

NFIG. The source code of NFIG

RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Infinity. [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Awesome-Autoregressive-Visual-Generation. This is a repo to track the latest autoregressive visual generation papers.

TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework

Awesome-From-Video-Generation-to-World-Model. A list of works on video generation towards world model

model-immunization-cond-num. [ICML 2025 Oral] Model Immunization from a Condition Number Perspective

perception_models. State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Harmon. [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

sdnext. SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

EasyControl. Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)

ComfyUI-KJNodes. Various custom nodes for ComfyUI

Wan2GP. A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

CFG-Zero-star. Official repo for CFG-Zero*

VideoWorld. [CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.

Video-Depth-Anything. [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

SkyReels-V1. SkyReels V1: The first and most advanced open-source human-centric video foundation model

HRS_benchmark. Jupyter Notebook

ELLA. ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

CFGpp. Official repository for "CFG++: manifold-constrained classifier free guidance for diffusion models" (ICLR2025)

RepVideo. The official implementation of ”RepVideo: Rethinking Cross-Layer Representation for Video Generation“

flow_matching. 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.

FlowAR. “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with any VAE.

geneval. GenEval: An object-focused framework for evaluating text-to-image alignment

large_concept_model. Large Concept Models: Language modeling in a sentence representation space

LaVi-Bridge. [ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

T2I-CompBench. [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation

text2image-benchmark. Benchmark for generative image models

NOVA. [ICLR 2025] Autoregressive Video Generation without Vector Quantization

VIMA. Official Algorithm Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"

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

LIBERO. Benchmarking Knowledge Transfer in Lifelong Robot Learning

Dancing2Music. Python

PantoMatrix. PantoMatrix: Generating Face and Body Animation from Speech

VideoClaw. 🚀 AI 全自动化视频生成员工 | Your First AIGC Coworker. Chat an Idea. Get a Film. 🦞

mvp. NeurIPS-2021: Direct Multi-view Multi-person 3D Human Pose Estimation

echomimic_v2. [CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

GIMM-VFI. [NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolation

Emu3. Next-Token Prediction is All You Need

Vchitect-2.0. Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

awesome-RLHF. A curated list of reinforcement learning with human feedback resources (continually updated)

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!

chameleon. Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

clvr_jaco_play_dataset. Official release of the CLVR Jaco Play Dataset, Dass et al. 2023

robotics_transformer. Python

Lumina-mGPT. Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"

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

flux. Official inference repo for FLUX.1 models

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.

Segment-and-Track-Anything. An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

data-juicer. Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Intuitive-Fine-Tuning. [ACL 2025, Main Conference, Oral] Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process

openvla. OpenVLA: An open-source vision-language-action model for robotic manipulation.

jynew. JinYongLegend-like RPG Game Framework with full Modding support and 10+ hours playable samples of game.

VBench. [CVPR2024 Highlight] VBench - We Evaluate Video Generation

VADER. Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.

SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers

VILA. VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

SimpleTuner. A general fine-tuning kit geared toward image/video/audio diffusion models.

LlamaGen. Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

EasyAnimate. 📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

taichi_dem. A minimal DEM simulation demo written in Taichi.

deep-fluids. Deep Fluids: A Generative Network for Parameterized Fluid Simulations

diffmpm. Differentiable Material Point Method

EasySynth. Unreal Engine plugin for easy creation of synthetic image datasets

CityDreamer. The official implementation of "CityDreamer: Compositional Generative Model of Unbounded 3D Cities". (CVPR 2024)

DiT-3D. 🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

U-ViT. A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".

video2game. Code release of Video2Game

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

hypernerf. Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

Dynamic3DGaussians. Python

Lumina-T2X. Lumina-T2X is a unified framework for Text to Any Modality Generation