PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Solve puzzles. Improve your pytorch.

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Official implementation of MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models

Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

[ICML 2026] Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion".

[to appear at NeurIPS 2026] Official implementation of "MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation"

Sekai2: From World Exploration to Interactive World Modeling

A unified multimodal model toolkit

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

An open-source AI agent that brings the power of Gemini directly into your terminal.

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

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

NVIDIA FastGen: Fast Generation from Diffusion Models

🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

Official implementation of "Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer" (ECCV 2026)

The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…

Florence-2 is a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks.

Gemma open-weight LLM library, from Google DeepMind

Code repository for "Spectral Progressive Diffusion for Efficient Image and Video Generation"

Code release for "Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation"

SGLang is a high-performance serving framework for large language models and multimodal models.

An agentic skills framework & software development methodology that works.

Ideogram 4: Open image model at the forefront of design

Wrapper of 50+ image matching models with a unified interface

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players