Skip to content

Free background remover

Remove the background from any image, right in your browser. No upload, no account, no credits, no watermark.

Free, no account needed. Runs in your browser: nothing is uploaded.

4.9/537 reviews on Capterra, as of October 2026

What the remover does

AI segmentation that runs on your machine, with the outputs the job actually needs.

Nothing is uploaded

The model runs inside your browser tab. Your image never touches a server — ours or anyone’s.

Transparent, white, or your color

Keep true transparency, or swap the background instantly without re-processing.

Free without a meter

No credits, no per-image pricing, no watermark, no account. Paste and go.

How to remove a background

  1. Choose an image, drop it on the page, or paste it from the clipboard.
  2. Wait a moment — the first use loads the model (about 16 MB), then it is cached.
  3. Pick transparent, white, or a custom color behind the cutout.
  4. Download the PNG.

Background removal in your browser

Use the tool to remove an image background and download a transparent PNG.

The tool runs the open-source U²-Net model in your browser through WebAssembly. The tool is free to use and keeps the image on your device.

The model works best when a person, product, or logo stands out from the background. Check the edges of hair and fur and review images with busy backgrounds before using the result.

Add a cutout to a video as a clickable image in Mindstamp. You can review clicks by viewer.

Common questions

Is this a remove.bg alternative?

For the everyday workflow, yes: image in, background removed, transparent PNG out, free. It runs in your browser instead of on a server, so there are no credits, accounts, or upload steps — and no server-side quality tier either.

Is my image uploaded anywhere?

No. The AI model downloads to your browser once and runs locally. The image, the mask, and the result never leave your machine.

Is it really free and unlimited?

Yes. Because processing happens on your device, each image costs nothing to anyone — so there is nothing to meter, watermark, or upsell.

How does it work?

It runs U²-Net, a well-known open-source segmentation model, through ONNX Runtime compiled to WebAssembly. The model predicts which pixels are the subject, and the mask becomes the alpha channel of your PNG.

Why is the first image slower?

The first use downloads the model and runtime (about 16 MB), which your browser then caches. After that, most images process in a few seconds.

What images work best?

People, products, and logos that stand apart from the background. Very fine hair, fur, glass, and busy scenes are harder for any compact model — check the edges before publishing those.

Put the cutout to work in video

Mindstamp places images on video as clickable hotspots, buttons, and overlays — and reports every viewer who clicks.

Works on the video you already have. No re-encoding.