GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

Light Image Video Generation Inference Framework

MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B

Code release for: Controllable Layer Decomposition for Reversible Multi-Layer Image Generation

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

Train transformer language models with reinforcement learning.

rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

[CVPR 2025] Official repo for ART:Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Official Implementations for Paper - MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

Official inference repo for FLUX.2 models

code for Holistically-Nested Edge Detection

ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Hackable and optimized Transformers building blocks, supporting a composable construction.

Official implementation of NerualSVG