Stars
A generative world for general-purpose robotics & embodied AI learning.
Official inference repo for FLUX.1 models
Train transformer language models with reinforcement learning.
Janus-Series: Unified Multimodal Understanding and Generation Models
Lets make video diffusion practical!
Wan: Open and Advanced Large-Scale Video Generative Models
Wan: Open and Advanced Large-Scale Video Generative Models
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Witness the aha moment of VLM with less than $3.
MAGI-1: Autoregressive Video Generation at Scale
[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers
Sky-T1: Train your own O1 preview model within $450
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
Efficient vision foundation models for high-resolution generation and perception.
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think