Official code for paper Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

PyTorch Code for Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

[arXiv 2026] This is the official PyTorch implementation of "MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators".

[ICML 2026] Elastic Diffusion Transformer: Accelerating SOTA generation models (e.g., Qwen-Image, Hunyuan3d ) through adaptive computation

AlphaGRPO[ICML 2026] and SpectraReward

Official codes for the paper "GARDO: Reinforcing Diffusion Models without Reward Hacking"

[ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

OPRD: On-Policy Representation Distillation (https://arxiv.org/abs/2606.06021)

JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

Official implementation of "TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment"

Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

Official inference code for Krea 2

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

[SIGGRAPH Asia 2026] DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

[ICML 2026] Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Official Repo of "Flow-OPD: On-Policy Distillation for Flow Matching Models"

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

[AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

[NeurIPS 2025] Improving Video Generation with Human Feedback

[CVPR 2026 Oral] Official implementation for ChordEdit: One-Step Low-Energy Transport for Image Editing

[ECCV 2026] Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

Enjoy the magic of Diffusion models!

Generate images locally

[ICML 2026][Ultra Powerful Few-Step Diffusion RL] TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward