Does my image get uploaded anywhere?

No. The model runs entirely in your browser with WebGPU or WebAssembly. The image never leaves your device.

How does it keep the subject sharp?

An AI model finds the subject and separates it from the background. The background is blurred and the original, sharp subject is composited back on top.

Can I change the blur strength?

Yes. The Blur slider adjusts the amount live — the model only runs once, so dragging it re-renders instantly.

Why is the first run slow?

The AI model (~44MB) downloads once on first use and is cached by your browser. After that it is fast — usually a second or two.

Blur Background

An AI segmentation model keeps the subject sharp and softly blurs everything behind it.

What this does

Blur Background uses the RMBG-1.4 segmentation model (via Transformers.js) to find the subject, then keeps it sharp and blurs everything behind it — all in your browser, with no upload.

The first time you drop an image, the model (~44MB) downloads from the Hugging Face CDN and is cached, so later images start instantly. Inference runs in a background worker, so the page stays responsive. Links to the model and library are below.

How it works

1Drop your image.
2The first time, the background-removal model downloads once (~44MB) and is cached for next time.
3Drag the Blur slider to taste, then download the result.

Built with open source

Transformers.js — Hugging Face's library for running ONNX machine-learning models in the browser, on WebGPU or WebAssembly. The model weights download from the Hugging Face CDN on first use and are cached. · Apache-2.0
RMBG-1.4 (BRIA AI) — Image-segmentation model that separates the foreground subject from the background. · Non-commercial

Frequently asked questions

Related tools

All Edit image →

Remove BackgroundRemove the background from an image and download a transparent PNG. Runs entirely in your browser.Resize ImageResize an image to any width and height. Lock the aspect ratio so nothing stretches.Image UpscalerUpscale an image 2× or 4× in your browser with an AI super-resolution model. Sharper than plain resizing.Crop ImageCrop an image by dragging a box around the exact part you want to keep.Pixelate ImagePixelate an image by averaging it into square blocks. You set the block size.Grayscale ImageConvert an image to grayscale, mapping each pixel to its luminance.