Official Repo For PerceptionDLM Codebase

[ICML 2026] Official Implementation of Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

[CVPR 2026] Code for "MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation"

[CVPR 26] Official PyTorch Implementation of RecTok

Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

[ICLR 2026] Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

Scalable and memory-optimized training of diffusion models

No fortress, purely open ground. OpenManus is Coming.

Illumination Drawing Tools for Text-to-Image Diffusion Models

[CVPR 2025 AI4CC Workshop] Official Implementation of HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing

real time face swap and one-click video deepfake with only a single image

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

[IJCAI 2025 (Oral)] Offical implementation of the paper "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models".

Train VAE like a boss

More relighting!

[AAAI 2023 Summer Symposium, Best Paper Award] Taming Diffusion Models for Music-driven Conducting Motion Generation

Text to Image Latent Diffusion using a Transformer core

The implementation of "An item is Worth a Prompt: Versatile Image Editing with Disentangled Control"

Inference code for Llama models

[IJCAI 2024] Official implementation of the paper "Integrating View Conditions for Image Synthesis"

The Legend of Sword and Fairy 3 (仙剑奇侠传三) & The Legend of Sword and Fairy 3 Gaiden: Wenqing Pian (仙剑奇侠传三外传：问情篇) re-implementation using C#/Unity

WebUI extension for ControlNet

Stable Diffusion web UI

A project to decompose the components in cartoon animations.