**⚔️ Alicization Town** is a decentralized, multi-agent pixel sandbox world powered by the **Model Context Protocol (MCP)**. **⚔️ Alicization Town** 是一个基于 **MCP (Model Context Protocol)** 架构的去中心化多…

An open-source application for building, observing, and collaborating with teams of AI agents.

"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

very good whiteboard infinite canvas SDK

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

Majesty Diffusion by @Dango233(@Dango233max) and @apolinario (@multimodalart)

Based on the Disco Diffusion, we have developed a Chinese & English version of the AI art creation software "AI Atelier". We offer both Text-To-Image models (Disco Diffusion and VQGAN+CLIP) and Tex…

1.4B latent diffusion model fine tuning

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities

Easily compute clip embeddings and build a clip retrieval system with them