civitai  by civitai

Platform for sharing AI models

created 2 years ago
6,757 stars

Top 7.7% on sourcepulse

GitHubView on GitHub
Project Summary

Civitai provides a platform for users to share, discover, and collaborate on Stable Diffusion models and customization files. It targets AI art enthusiasts and developers looking to share and find custom models, fostering a community around AI image generation.

How It Works

The platform utilizes a modern web stack: Next.js for the frontend and backend, TRPC for the API, and Prisma with PostgreSQL for the database. Cloudflare handles storage. This architecture aims for scalability and maintainability, enabling user accounts, model uploads, browsing, and community feedback.

Quick Start & Requirements

  • Installation: Clone the repository and use either Docker with devcontainers or make init for setup.
  • Prerequisites: Docker, Node.js (v20+), and optionally make. Windows users should use WSL or named container volumes for devcontainers to avoid performance issues.
  • Configuration: Requires setting S3 upload keys, a webhook token, and email properties in a .env file. Local development uses maildev for email.
  • Access: The application is accessible at http://localhost:3000.
  • Docs: Prerequisites

Highlighted Details

  • Supports sharing of various Stable Diffusion customization types: textual inversions, hypernetworks, aesthetic gradients, VAEs, and more.
  • Enables community collaboration through comments and feedback on shared models.
  • Offers a local development setup with Docker and a make init script for streamlined initialization.
  • Allows users to elevate their accounts to moderator status via direct database modification.

Maintenance & Community

  • Active community engagement is encouraged via Discord.
  • Information on joining the Community Development Team is available.

Licensing & Compatibility

  • License: Apache License 2.0.
  • Compatibility: Permissive license suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

Local development environments do not support features requiring external services, such as orchestration (generation, training) and real-time signals (chat, notifications).

Health Check
Last commit

1 day ago

Responsiveness

1 week

Pull Requests (30d)
27
Issues (30d)
5
Star History
201 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems) and Travis Fischer Travis Fischer(Founder of Agentic).

pezzo by pezzolabs

0.2%
3k
Open-source LLMOps platform for streamlining AI workflows
created 2 years ago
updated 1 month ago
Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Jeremy Howard Jeremy Howard(Cofounder of fast.ai), and
3 more.

cohere-toolkit by cohere-ai

0.2%
3k
RAG toolkit for LLM application development and deployment
created 1 year ago
updated 1 week ago
Feedback? Help us improve.