Remove the background from a photo
The model is downloaded once from Hugging Face and then runs on your own device with ONNX Runtime Web. Your photograph is never sent anywhere — which is unusual for this particular tool.
- Runs entirely in your browser
- Works offline
- No upload
- No sign-up
- No watermark
Loading the tool…
How it works
- Drop a photo and pick a model: general objects (4.4 MB) or people (6.3 / 24.7 MB).
- Choose a transparent or solid-colour background and how much to soften the edge.
- Run it and download the PNG.
Why nothing is uploaded
Every operation on this page is done by code running inside your browser tab, using the same engine that renders web pages. The file is read from disk into your tab’s memory, transformed there, and written back out as a download. It is never sent anywhere — not to us, not to a third party.
Verify it yourself
- Open your browser’s developer tools (F12) and select the Network tab.
- Load your file and run the tool.
- The only requests you will see are the tool’s own code and, once cached, none at all.
Frequently asked questions
How good is it, honestly?
Good on a clear subject against a distinct background. Weaker on fine hair, glass, chain-link and motion blur — that is a limitation of automatic matting in general, not of this implementation. The result is shown next to the original so you can judge before using it.
Why do other sites do this better?
Because they run much larger models on servers, and pay for that with your photograph. The models here are 4–25 MB because they have to reach your browser and run there. It is a genuine trade-off and we would rather state it than claim parity.
Which model should I choose?
Start with the general one: it handles products, objects and animals. Switch to the portrait model for people — it is trained for human matting and does noticeably better on shoulders and hair.
Which models are these, and under what licence?
U-2-Netp and MODNet, both Apache-2.0, loaded from Hugging Face. We deliberately avoided the popular alternatives: the best-known browser library for this is AGPL-3.0, and the best-known weights are licensed for non-commercial use only.