leeguooooo/chatgpt-imagegen

Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no daemon. Zero-dep Python CLI + AI-agent skill.

What it solves

It provides a way to generate images using a ChatGPT or Gemini subscription without needing a paid OPENAI_API_KEY. It allows users to leverage their existing web-based subscriptions (including free tiers) to create images via a command-line interface (CLI) or as a skill for AI agents.

How it works

The tool is a zero-dependency Python CLI that interacts with the internal endpoints of ChatGPT or Gemini. It can drive a logged-in Chrome browser session (web backend) or use a headless fallback (codex backend). It supports text-to-image prompts, image-to-image references for subject or composition, and the creation of simple animations by generating sprite sheets and processing them into WebP or GIF loops using ImageMagick and libwebp.

Who it’s for

  • Developers and power users who want to generate images from the terminal.
  • AI agent users (e.g., Claude Code, Cursor) who want to give their agents the ability to create images.
  • Users who want to avoid additional API billing by using their existing ChatGPT/Gemini subscriptions.

Highlights

  • Zero Dependencies: Written in Python using only the standard library.
  • Multi-Backend Support: Works with ChatGPT (web/codex) and Gemini (web/agy).
  • Agent Integration: Can be easily added as a skill to AI agents via npx skills.
  • Community Styles: Access to a public gallery of tuned art styles and character references to maintain visual consistency.
  • Animation Support: Ability to generate simple ping-pong animations from sprite sheets.

Related

  • Project
    WJZ-P/gemini-skill

    A tool that automates the Gemini web interface via CDP and MCP, enabling AI agents to perform text conversations, image generation, and image extraction.

  • Project
    google-gemini/gemini-cli

    An open-source AI agent for the terminal that provides direct access to Gemini models for code analysis, automation, and system integration.

  • Project
    Code-with-Beto/snapai

    A CLI tool for mobile developers to generate app icons and Google Play feature graphics using OpenAI and Google Gemini image models.

  • Project
    YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

    An AI agent skill that allows AI assistants to search and recommend 10,000+ curated prompts for the Nano Banana Pro (Gemini) image generation model.

  • Project
    buluslan/gpt-image2-ecommerce

    A tool for generating professional e-commerce product images using GPT-Image-2 and Codex CLI, featuring 25 specialized scene templates and reference image support.