product photo background remover
Cut products out of messy desk and kitchen-table photos and drop them onto pure white for your shop listings — several photos at once, all on your own device.
Clean edges removes faint leftover background around the outline; soften edges blurs the cut so it blends in.
Marketplace-ready white backgrounds
Most marketplaces prefer, and Amazon requires, the main product image on a pure white background (RGB 255, 255, 255). A clean white backdrop also makes thumbnails look consistent in search results and lets buyers focus on the item.
This page uses the larger any-object model, which handles boxes, bottles, shoes, gadgets and jewellery far better than portrait models. Your photos are processed one after another on your device and the cut-out is applied to the full-resolution original, so detail isn't lost.
Step by step
- Shoot the product on a plain surface with soft, even light — a window on a cloudy day works well.
- Drop up to 20 photos. The first run downloads the model once.
- Check each result with the before/after slider; use “clean edges” if a faint outline of the old background remains.
- Download JPG on white for listings, or switch to transparent PNG for your own designs.
Tips for a better result
- Keep the product filling most of the frame; the model sees a scaled-down copy, so tiny items lose detail.
- Glass, clear plastic and shiny chrome reflect the old background — expect to retouch these.
- Marketplace rules (frame fill, minimum size, no added text) change: check your platform's current image guidelines.
- Need the file under a size limit? Run the result through the image compressor afterwards.
How it works
Your photo is shrunk to about 1,024 pixels on its longest side and given to an AI segmentation model running in your browser (through Transformers.js and ONNX Runtime, the people model on the CPU, the any-object model on your graphics chip via WebGPU). The model returns a mask — how much each pixel belongs to the subject — which is scaled back up and applied to your full-resolution photo, then combined with the background you choose. Nothing is uploaded: the model files come from Hugging Face once, your browser caches them, and every image stays on your device.
people & portraits (fast)
MODNet — made for people — fast on phones, not for products or objects.
Download: ~25 MB, once. Works on any device.
MODNet by Zhanghan Ke et al. (City University of Hong Kong / SenseTime). Licence: Apache-2.0. Model card.
any object (best quality)
BiRefNet lite — products, pets, logos, people — bigger download, slower on phones.
Download: ~110 MB, once. Needs a computer whose graphics chip supports WebGPU with half-precision (fp16).
BiRefNet by Peng Zheng et al. (Nankai University). Licence: MIT. Model card.
Honest limits
- Hair and fur come out soft but not strand-perfect; very fine flyaways against a busy background may be lost.
- Glass, water, smoke and shiny metal show the old background through or in them — no mask can fix that.
- Low contrast (a white mug on a white table, dark hair on a dark wall) confuses every model; a photo with more contrast works best.
- Very large photos are processed at up to 16 megapixels so they fit in browser memory on phones.
- On phones the any-object model is slow and memory-hungry; the people model is quick everywhere.
Frequently asked questions
Is the white exactly #FFFFFF?
Yes. The solid colour is painted as pure white (255, 255, 255) and JPGs are saved at high quality, which keeps the background at or within a hair of pure white.
Why is the first run slow?
The any-object AI model (about 110 MB) downloads once and is then cached by your browser. Later photos only take seconds. It needs a computer with a newer graphics chip; on other devices the page uses the people model, and the instant logo tool handles products on plain backgrounds.
Can I add a shadow?
Not yet — the tool removes and replaces backgrounds only. Many sellers keep the plain cut-out because marketplaces prefer it.
Are my product photos uploaded?
No. The AI runs inside your browser; your images never leave your device.
How is this different from the main background remover?
It's the same on-device tool with different starting settings and tips for this job. You can change the model and background at any time.