Generate images using ChatGPT's GPT-Image-2 model via browser automation (CDP). Shares the user's daily Brave Browser (port 9222) via the brave-browser-agent skill. Navigate to chatgpt.com, input a prompt, trigger generation, and extract the result. Use when: (1) User asks to generate/create/draw an image or picture using GPT/ChatGPT (2) User mentions "GPT生成图片", "ChatGPT画图", "gpt-image" (3) Need high-quality AI image generation via ChatGPT (4) User wants photorealistic images, complex scenes, or text-in-image generation (5) Fallback/complement to Gemini image generation Requires: Brave Browser running with --remote-debugging-port=9222, ChatGPT logged in, Python 3, websockets pip package.

Install

openclaw skills install @mayf3/gpt-image-gen