CPA Image
A local-first, browser-based console for generating and editing images through any OpenAI-compatible image API, with request queuing, multi-endpoint debugging and prompt history.
CPA Image is a local-first console for OpenAI-compatible image generation and editing. The interface is built with React, TypeScript, Vite, Tailwind CSS and shadcn/ui; the application has no backend of its own, and every request goes straight from the browser to a user-configured OpenAI-compatible API address.
It supports text-to-image generation, editing a local image, and reusing a previous result as a new edit's input; debugging against the images/generations, images/edits, responses and chat/completions endpoints; queued and concurrent requests with configurable intervals; and canceling or clearing failed or completed requests. Prompt history, pinning, reuse, image download, batch export to a ZIP file and viewing raw response JSON all run locally in the browser.
An optional cross-origin proxy option routes requests through a relay when a target API does not set CORS headers; the project warns that this proxy can see the API URL, headers, prompt, image and response content. It is MIT licensed but not published as an npm package.