A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.
Haidra-Org/AI-Horde
A free, community-run distributed service where volunteer GPUs generate AI images and text for anyone who submits a request.
Open-source alternative to:Midjourney
- Stars
- 1,634
- Forks
- 180
- Open issues
- 95
- Last commit
- 8 days ago
What is it?
AI Horde is a crowdsourced inference cluster for AI image and text generation. Volunteers run worker software on their own machines, and the middleware routes incoming requests to whichever workers can handle each job. Users can ask for images from Stable Diffusion-style models or text from LLMs, including models such as Pygmalion and Llama, without owning a powerful GPU.
The system uses a kudos point economy to balance load. Workers earn kudos for processing requests, and users with more kudos get higher queue priority. Kudos cannot be bought or sold. Anonymous access is available, and registered accounts receive better priority and can track their balance.
Besides the public instance, the middleware can be deployed privately inside an organization. It is built in Python with PostgreSQL and Redis, and it ships with Docker support. Clients such as third-party websites, games and apps consume the service through its REST API.
Key features
- 01Distributes image and text generation jobs to volunteer GPU workers.
- 02Uses a kudos points system to set queue priority and keep access fair.
- 03Allows anonymous use as well as registered accounts via OAuth2.
- 04Exposes a REST API for third-party websites, games and apps.
- 05Can be deployed privately with PostgreSQL, Redis and Docker.
Use cases
- Generating AI art without a local high-end GPU.
- Adding AI text or image generation to a third-party app or game via the API.
- Contributing idle GPU time to help others create content.
- Running a private AI generation cluster inside an organization.
Quick start
- 1
Register an account at the AI Horde website to get an API key
- 2
Use the public service anonymously with API key 0000000000 (no registration needed)
- 3
To contribute image generation, run the officially supported worker software horde-worker-reGen
Things to know
- Anonymous users get the lowest queue priority and may be restricted during high load.
- Contributing a GPU requires running separate worker software, which needs capable hardware.
- Self-hosting the middleware requires PostgreSQL, Redis and Python 3.9 or later.
In collections
Topics
FAQ
- What is AI-Horde?
- A free, community-run distributed service where volunteer GPUs generate AI images and text for anyone who submits a request. AI Horde is a crowdsourced inference cluster for AI image and text generation. Volunteers run worker software on their own machines, and the middleware routes incoming requests to whichever workers can handle each job. Users can ask for images from Stable Diffusion-style models or text from LLMs, including models such as Pygmalion and Llama, without owning a powerful GPU.
- Is AI-Horde free to use? What license does it have?
- AI-Horde is open source under the AGPL-3.0 license. Check the license terms before using it in commercial products.
- Is AI-Horde still maintained?
- Actively maintained. The last commit to AI-Horde was on Oct 14, 2026.
- What can I use AI-Horde for?
- Generating AI art without a local high-end GPU. Adding AI text or image generation to a third-party app or game via the API. Contributing idle GPU time to help others create content. Running a private AI generation cluster inside an organization.
- How do I install AI-Horde?
- Register an account at the AI Horde website to get an API key Use the public service anonymously with API key 0000000000 (no registration needed) To contribute image generation, run the officially supported worker software horde-worker-reGen
- Where can I get AI-Horde?
- The source code and installation instructions are on GitHub: https://github.com/Haidra-Org/AI-Horde
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A modular web UI for AI image, video and audio generation, built on Stable Diffusion, Flux, Wan and other models, with a ComfyUI workflow tab.
A Gradio-based web UI for running Stable Diffusion and newer image/video models, continuing the Forge fork with added model support and optimizations.
A suite of developer tools for building, testing, evaluating and deploying LLM-based applications, with a VS Code flow designer and a pf CLI.
Python framework for building LLM applications with multiple cooperating agents, tools, and retrieval-augmented generation.
Offline, open-source image generator built on Stable Diffusion XL that lets you focus on prompts instead of manual parameter tuning.