civitai/civitai

A repository of models, textual inversions, and more

What it solves

This project provides the open-source codebase for a community-driven platform dedicated to sharing, discovering, and collaborating on AI-generated art models. It specifically supports various customization techniques for Stable Diffusion, such as textual inversions, hypernetworks, and aesthetic gradients.

How it works

The platform is built as a modern web application using Next.js for the frontend and a tRPC API. It uses Prisma and PostgreSQL for database management, with Cloudflare for storage. The repository includes the necessary infrastructure configurations (via Docker Compose) to run a local development environment, including database, caching, and object storage services.

Who it’s for

It is designed for developers and AI enthusiasts who want to contribute to the platform's infrastructure, host a local instance for development, or learn how a large-scale model-sharing ecosystem is architected.

Highlights

  • Supports a wide range of AI model types including textual inversions and VAEs.
  • Includes a robust local development setup using Docker and Nix for environment consistency.
  • Features a collaborative environment for users to share feedback and improve models.
  • Built on a scalable stack using Next.js, tRPC, and Prisma.

Related

  • Project
    Sygil-Dev/sygil-webui

    A web-based user interface for Stable Diffusion that provides tools for image generation, upscaling, and prompt engineering with optimizations for low-VRAM GPUs.

  • Project
    easydiffusion/easydiffusion

    A one-click installer and user interface for Stable Diffusion that allows users to run powerful image generation AI locally without requiring technical knowledge.

  • Project
    SamurAIGPT/AI-Influencer-Generator

    An open-source pipeline that uses Stable Diffusion, gTTS, and SadTalker to create and animate consistent virtual AI influencers for social media.

  • Project
    Stability-AI/StableSwarmUI

    StableSwarmUI is a modular, cross‑platform web UI for running Stable Diffusion locally. It offers a simple Generate tab for quick image creation, an advanced ComfyUI‑style workflow editor, multi‑GPU “swarm” support, and a plugin system. Installers are provided for Windows, Linux, macOS (Apple silicon) and Docker. The project is in Beta (v0.6.4.1) and now maintained independently of Stability AI. Core code is MIT‑licensed, but it pulls in several third‑party components under various open‑source licenses.

  • Project
    ShiftHackZ/Stable-Diffusion-KMP

    An open-source, cross-platform AI image generation client for Android and iOS that connects to self-hosted Stable Diffusion servers, cloud APIs, and local on-device runtimes.