Image
Remove Background
General, Portrait and Logo modes — runs in your browser, never uploads your image.
Loading tool…
Most background removers send your photo to a cloud server — your image travels the network and touches someone else's infrastructure. This tool does none of that. The AI models download once, stay in your browser, and every removal runs entirely on your own hardware. Three modes are available: Portrait uses MODNet (Apache-2.0, 26 MB), a compact portrait matting model that is fast on WebGPU and produces clean edges on faces and hair. General uses Silueta (Apache-2.0, 44 MB), a compressed U-2-Net variant optimised for salient object detection on products, graphics, and objects — it loads only the first time you run that mode, so portrait users never fetch it. Logo needs no model: it removes a plain background colour. The output is always a transparent PNG.
Background Removal by Subject
Use-case-specific tips and the right mode pre-selected for your subject.
Related Tools
Related Guides
How to Use
- 1
Choose a mode: "Portrait" (26 MB model) for photos of people, "General" (44 MB model) for products, objects, and other subjects, or "Logo" for a logo or graphic on a plain background.
- 2
Drop a PNG, JPEG, or WebP image onto the upload area, or click to browse.
- 3
On first use of an AI mode, its model is downloaded once and kept in your browser: Portrait 26 MB, General 44 MB. The progress bar shows the megabytes downloaded; later visits skip the download unless the browser has cleared its storage. Logo mode downloads nothing.
- 4
Preview the result on a checkerboard background to confirm the cutout, toggle between Before and After, then download the transparent PNG.
Frequently Asked Questions
Is my image ever uploaded to a server?
No. Everything runs in your browser. The AI models are downloaded once and kept in your browser; your image is processed locally and never leaves your device. Open your browser's Network tab while using it — you will see no upload request.
What is the difference between the modes?
"Portrait" uses MODNet (Apache-2.0, 26 MB), optimised for matting people, faces, and hair. "General" uses Silueta (Apache-2.0, 44 MB), a compressed U-2-Net model better suited to products, objects, and graphics — quality is good on subjects with clear separation from the background, though less precise on fine details like hair compared to Portrait. Both use WebGPU on supported hardware, otherwise WebAssembly. "Logo" needs no model: it removes a plain background colour, including areas enclosed by the logo.
Does selecting "General" download the model immediately?
No — the Silueta model (44 MB) is only downloaded the first time you actually click "Remove Background" in General mode. Switching the mode alone does not trigger a download. Portrait users who never use General mode will never fetch it.
Why does the first removal take longer?
The first run with an AI mode downloads its model from our own server. A progress bar shows the megabytes downloaded. After that the model is kept in your browser, so later removals skip the download unless the browser has cleared its storage.
What is the output format?
The output is always a transparent PNG. PNG keeps the alpha channel (transparency) needed for a clean subject cutout and opens in every app. You can convert the PNG to WebP using the Image Converter tool if you need a smaller web-ready version.