Remove backgrounds. 3 tiers. Batch. 100% yours.
Studio-quality cutouts, made locally.
No account, no API key, no watermark. Refine edges with a brush, then compose on presets with drop shadows and social aspect ratios.
No watermark, no sign-up
Export full-resolution transparent PNGs with no watermark. No account, no email, no credit card — open the page and start.
3 model tiers
Fast runs MODNet (~26 MB) for real-time portraits. Sharp and Sharp · GPU run BiRefNet Lite (~183 MB), a general-purpose segmenter for products, animals, logos, and hair. Both produce the same edges; the GPU tier is simply faster in WebGPU-capable browsers.
100% on-device and private
Your images never leave your device. No uploads, no servers, no tracking. Models download once and cache locally.
Refine, then compose
Brush the matte to erase leftovers or restore dropped hair, then place the cutout on a transparent, solid, or gradient background with a drop shadow at 1:1, 4:5, 9:16, or up to 4K.
Pick a tier, click, export.
- 01
Add your image
Drag and drop, paste, or browse. PNG, JPEG, WebP, AVIF, or BMP — one photo, or a batch of up to 500.
- 02
The AI removes the background
The selected model runs locally through WebGPU or WASM and returns a precise alpha matte in seconds, including semi-transparent hair strands.
- 03
Refine and export
Touch up edges with the erase and restore brush, then download a transparent PNG, a white-background JPEG, or a resized WebP — or export the entire batch as one ZIP.
remove.bg is shutting down on 1 December 2026
The standalone site closes, the web tool moves into Canva, and the API moves to Leonardo.Ai. Feyard needs no account, uploads nothing, and costs nothing.
About the background remover
A free AI background remover that produces transparent PNGs, white-background product shots, and social-ready crops entirely on your device. It is built for product photos, profile pictures, portraits, and design mock-ups where uploading client or personal images to a cloud editor is not an option — and for anyone who refuses a per-image fee for something their own GPU can do in seconds.
Three quality tiers, a manual edge brush, and a batch queue with one-click ZIP export make it usable for a single avatar as well as for a two-hundred-image storefront refresh.
Three models, one decision
Fast runs MODNet (~26 MB), a portrait matting network that returns a soft alpha matte in well under a second on WebGPU — ideal for people, avatars and quick previews. Sharp and Sharp · GPU both run BiRefNet Lite (~183 MB, MIT-licensed), a general-purpose dichotomous segmentation model that handles products, animals, logos and awkward edges far better than portrait-only matting. Sharp pins inference to CPU/WebAssembly so it works in every browser; Sharp · GPU runs the same weights through WebGPU, so the edges are identical but the run is usually several times faster. In other words the two upper tiers differ in speed, not in quality — the honest way to read the three tiers is a portrait/general axis plus a CPU/GPU axis. Every model runs locally through Transformers.js, and the weights are downloaded once then cached by the browser.
Refining edges the model got wrong
No matting model is perfect: stray hair, a chipped mug handle, a translucent veil, or a patch of background that shares the subject’s colour. The edge brush edits the alpha matte itself rather than the pixels. Erase wipes alpha to zero; Restore writes back the exact matte value the model produced, so semi-transparent hair strands return at their original opacity instead of a hard 100 % edge. Strokes are recorded per gesture with full undo and redo, and a 3× magnifier follows the cursor for hair-level work.
Three sliders cover the rest: Feather softens the cutout boundary, Shrink / Grow removes the halo or recovers thin hair the model dropped, and Edge contrast makes the transition crisper or more gradual. Brush strokes and sliders live in separate layers, so moving a slider never destroys manual work.
From cutout to deliverable
The export panel composites the cutout onto a transparent, solid or gradient background, adds a drop shadow, fits it into the aspect ratio a marketplace or social network expects (1:1, 4:5, 9:16, 1.91:1 and more), and resizes it to a native, 1K, 2K or 4K long edge. Output is PNG when you need transparency, JPEG for the smallest white-background product shot, or WebP for both. A “trim transparent edges” switch tightens the canvas around the subject before compositing. The on-screen preview is deliberately rendered at screen resolution; the full-resolution image is only composed when you export.
Batch mode
Drop up to 500 images and they are processed one at a time in the background — one at a time because a single ONNX session already saturates the WebAssembly heap, and parallel inference is the fastest way to crash a browser tab. Each finished image is encoded to a transparent PNG immediately, so the queue never holds more than a handful of full-resolution bitmaps in memory. When the run finishes, download everything as one ZIP. Changing the export settings afterwards only re-packs the ZIP: the model never runs twice.
Limits & requirements
Chrome or Edge with WebGPU is fastest; everywhere else the models fall back to WebAssembly with identical quality at a slower pace. Inference runs at a fixed internal resolution (512×512 for the BiRefNet Lite graph, 512 for MODNet), so the matte is upscaled to your photo’s full resolution on export — a 5000px photo and a 1600px photo therefore carry exactly the same model detail. That is why the tool caps the image it feeds the network, and why huge files do not get sharper. Camouflaged subjects (a snowman on snow, a black cat on a black sofa) may still need the brush. There is no file-size limit and no watermark.
Privacy
Images are decoded, processed and encoded in your browser’s memory; nothing is uploaded, logged, or stored on a server. There is no account, no usage counter, and no telemetry attached to your files. As a side effect, the tool keeps working offline once the model weights are cached.