This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

rCM: SOTA Diffusion Distillation & Few-Step Video Generation

LongLive: Real-time Interactive Long Video Generation

My learning notes/codes for ML SYS.

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

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capab…

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

PyTorch distributed training acceleration framework

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

High performance inference engine for diffusion models

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

Official GitHub repository for FLUX.1 Krea [dev].

Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation