GitHub radar

Edit a photo with AI in your browser — no install, no signup

This is a free demo on Hugging Face: type what you want changed on a photo and get back an edited image — one AI model makes the edit, another polishes it. Nothing to download, it all runs in your browser.

It's a web page where two AI models take turns changing your photo based on a text description: Qwen makes the edit, then FLUX.2 Klein — an open model from Black Forest Labs, a research lab — cleans up the result.

When it helps

Useful for a one-off quick fix — removing an object, changing a background, tidying a photo before posting. Not for precise, pixel-level controlled edits.

Pros

  • Free and no install — runs right in your browser
  • Edit and polish happen in one pass, no switching tools
  • Built on open models under the Apache 2.0 license

Cons

  • Made by one person — don't expect support if it breaks
  • Not for precise, pixel-level controlled edits
  • Unofficial project, not from Alibaba or Black Forest Labs

How to set it up — step by step

  1. 1Open https://huggingface.co/spaces/AST-1320/Qwen-2511-Plus-Flux.2-klein in your browser
  2. 2Send your agent the text in the block below — it'll explain what to upload and type
  3. 3Upload your photo to the space
  4. 4Type what to change in the prompt box: remove an object, swap the background, etc.
  5. 5Run it and wait for Qwen and FLUX.2 Klein to finish
  6. 6Download the finished photo to your computer

Text for your agent

Copy this and send it to your agent — Claude Code, Codex, any of them:

Open this Space https://huggingface.co/spaces/AST-1320/Qwen-2511-Plus-Flux.2-klein and explain how to use it: what to upload, what to write in the prompt, and how to download the result.

Nothing to install — it runs in the browser.

Open on Hugging Face