ChatGpt-Image-Studio  by peiyizhi0724

AI image generation and editing studio

Created 1 week ago

New!

275 stars

Top 93.8% on SourcePulse

GitHubView on GitHub
Project Summary

Summary This project offers a self-hosted, single-service image generation workflow studio, leveraging ChatGPT's capabilities for text-to-image, inpainting, and editing. It targets engineers, researchers, and power users seeking a local, configurable alternative to web UIs, providing session management, account pooling, and API compatibility for enhanced control.

How It Works The architecture features a Go backend for API handling and account management, coupled with a Vite + React frontend. It supports text-to-image generation, reference-guided generation, continuous editing, and inpainting, with session history and retry mechanisms. Compatible /v1/chat/completions and /v1/responses API endpoints are provided. Account management includes access_token import, pooling, and synchronization from CPA, NewAPI, and Sub2API, with quota refresh features. Data storage is flexible, supporting file, SQLite, or Redis for accounts, configurations, and history, enabling stateless deployments.

Quick Start & Requirements

  • Primary Install/Run: Local development: clone repo, run ./scripts/dev.sh (macOS/Linux) or ./scripts/dev.ps1 (Windows). Docker: docker compose pull, docker compose up -d. Stateless cloud deployment via docker run with Redis is also supported.
  • Prerequisites: Go 1.25+, Node.js 24+, npm 10+. Docker for containerized deployments.
  • Links: Repo: https://github.com/peiyizhi0724/ChatGpt-Image-Studio.git. Community: https://linux.do/.

Highlighted Details

  • Image Generation: Text-to-image, reference-based generation, continuous editing, and inpainting with configurable resolution/quality.
  • Account Management: Import access_token, manage pools, perform single/batch quota refreshes. Sync accounts from CPA, NewAPI, Sub2API.
  • API Endpoints: Compatible with /v1/chat/completions and /v1/responses for image tasks.
  • Flexible Storage: File, SQLite, Redis backends for accounts, configs, and history, enabling stateless deployments.

Maintenance & Community GitHub Actions automate Docker image builds. Community support is available via the Linux.do forum. No core maintainer or sponsorship details are provided.

Licensing & Compatibility Licensed under the MIT License. Usage is strictly restricted to personal learning, technical research, and non-commercial exchange. Commercial use, profit-making, mass operations, automated abuse, or scaled calls are prohibited.

Limitations & Caveats This project is for research and non-commercial use only. It carries risks of OpenAI account limitations or bans; avoid using important accounts. Generating illegal, violent, pornographic, or child-related content, or using it for fraud/harassment, is prohibited. All usage must comply with OpenAI terms and local laws. Users assume all risks and legal responsibilities.

Health Check
Last Commit

4 days ago

Responsiveness

Inactive

Pull Requests (30d)
4
Issues (30d)
14
Star History
275 stars in the last 10 days

Explore Similar Projects

Starred by Peter Norvig Peter Norvig(Author of "Artificial Intelligence: A Modern Approach"; Research Director at Google).

NanoBananaEditor by markfulton

0.1%
674
Advanced AI image generation and editing platform
Created 8 months ago
Updated 7 months ago
Feedback? Help us improve.