Categories
Self-Hosted AI Agents Generative AI Creative Tools AI Image Generation Image Editing Image Gallery Prompt PlaygroundStars
Forks
Watchers
Developer links
GPT Image Playground
One prompt box, four model families, and a gallery that never leaves your browser: GPT Image Playground turns any compatible image API into a tidy studio for text-to-image and reference-based editing. Attach reference photos by paste, drag, or link, then paint a mask or sketch notes directly on the picture to show the model what to change. Agent mode keeps a multi-turn conversation going, calls the image tool as needed, generates related pictures in parallel, and branches whenever you edit and resend a message. Every task is saved with its size, quality, elapsed time, and the prompt as the model actually rewrote it, so you can compare what you asked for with what happened. Favorites sort into several collections that download as ZIP archives, and failed jobs retry in one click. Saved API configurations switch from a dropdown, covering OpenAI-compatible endpoints, Google, xAI, ByteDance, fal.ai, and custom HTTP providers. Output formats include PNG, WebP, animated GIF, and SVG, with transparent backgrounds on request. Operators can preload configurations through environment variables and route calls through a built-in proxy. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Edit Images With Marks
- Paint a mask, draw shapes, add text, or leave position-tagged comments on a reference image, so the model receives clear instructions about exactly which region to change.
- Switch Providers In Seconds
- Keep several saved API configurations and models, then change between OpenAI-compatible endpoints, Gemini, Grok, Seedream, and fal.ai from the prompt box without retyping keys or URLs.
- History Stays In Your Browser
- Every task and image is stored in your own browser with duplicates compressed, so prompts and results never pass through a third-party server and can be exported as a ZIP backup.
- See What The Model Did
- Compare requested settings with the size, quality, timing, and rewritten prompt that the API actually reported, which makes it easy to spot gateways that silently change a request.
Features
- Agent Chat Mode
- A multi-turn conversation that remembers context, calls image tools, generates batches in parallel, and branches when you edit or regenerate a message.
- Mask And Sketch Editor
- A zoomable canvas with brush, shape, text, eraser, and comment tools for annotating reference images or starting from a blank page.
- Gallery And Collections
- A masonry gallery with status filters, drag selection, multiple favorite collections, full-screen preview, and ZIP downloads for each collection.
- Multiple Output Formats
- Choose PNG, WebP, animated GIF, or SVG output, with transparent background support and 1K, 2K, and 4K size presets.
- Preset Deployment Config
- Docker environment variables preload API configurations, lock their parameters, and enable a same-origin proxy that avoids browser cross-origin limits.
- Batch Prompt Queue
- Paste several prompts at once to queue or run them concurrently with shared reference images and settings, then follow progress or stop jobs.