Free Segment Anything
Segment Anything selects any object you click and cuts it out as a full-resolution transparent PNG. Right-click to exclude parts, pick one of three suggested masks, combine several objects, or download a black-and-white mask instead. You can also drag a box around an object, feather the edge and crop the download to the object.
- Output:
- Cut-out PNG, mask or on a color
- Prompts:
- Points, exclude points, box
- Model:
- SlimSAM, about 28 MB
- Price:
- Free
- Runs:
- AI model in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
Is my photo uploaded?
No. The model is downloaded once from Hugging Face and runs in your browser. Your photo never leaves your device.
Why are there three mask options?
A click can mean a part, an object or a whole group (a wheel, the car, the car and its shadow). The model proposes three shapes and the most likely one is selected; click another thumbnail to change it.
Processed on your device: your files are never uploaded. How it works
Network activity in this tab
What this page has requested since you opened the site in this tab. An upload is any request that sends data: POST, PUT, PATCH or a request with a body.
No uploads: nothing has been sent from this page.
No network requests yet.
To see every request, open your browser's developer tools (Network tab).
How to use the Segment Anything
- Drop a photo and download the AI model once (about 28 MB).
- Click an object: it is highlighted. Right-click (or Alt/Shift+click) to exclude parts, or drag a box with the Box tool.
- Pick one of the three mask options if needed, then Add to selection; add or subtract more objects.
- Download the cut-out PNG, the mask, or the object on a color, at full resolution.
Credits & open source
Open-source AI model running in your browser. Thank you to the people who make these projects.
- Transformers.jsRuns Hugging Face AI models in the browser with ONNX Runtime. © Hugging Face, Inc. and contributors · Apache-2.0
- ONNX Runtime WebExecutes ONNX models with WebGPU or WebAssembly (self-hosted from /vendor/ort). © Microsoft Corporation · MIT
Web platform APIs used: Web Workers, WebAssembly, OffscreenCanvas, Canvas 2D, createImageBitmap, Pointer Events, Keyboard Events, File API, Clipboard API.
- Xenova/slimsam-77-uniform by Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang (SlimSAM), compressed from Segment Anything by Meta AI; ONNX export by Joshua Lochner (Xenova) (Apache-2.0) — AI image encoder and mask decoder
Full license texts: third-party notices · all credits
Frequently asked questions
How do I select several things?
Select the first one and press Add to selection, then click the next one. Use Subtract to cut a hole in the selection.
Can I get just the mask?
Yes. Choose Mask to download a black-and-white PNG (white = selected) at the size of your photo, ready for other editors.