Mercado Livre preset
- Input
- 1200 x 1200, margem 6%
- Expected output
- 89,3% do quadro
Product 600 x 300 px: 600 x 1.786 = 1071 px of 1200.
Carregando ferramenta… / Loading tool…
white background product photo for marketplace listing
Pick the Mercado Livre or Amazon size from the output list. The tool turns on the white background, crops tight to the product and centers it in the square, with a margin you can adjust.
Product 600 x 300 px: 600 x 1.786 = 1071 px of 1200.
Product 600 x 300 px: 600 x 3.086 = 1852 px of 2000.
Below the 85% quoted by Amazon.
Up to 10 MB per file.
The preset already picks this color; a JPG is produced because the background is opaque.
No. The photo is read and processed in your browser, inside a Web Worker. The internet is only used to download the cutout model (from Hugging Face) and the ONNX Runtime engine (from jsDelivr), once each. You can verify it in your browser's Network tab: after the model files are downloaded, no request carries your image.
Mercado Livre's developer documentation asks for 1200 x 1200 px, with a minimum of 500 x 500 px, a maximum of 1920 x 1920 px and up to 10 MB. The tool preset uses 1200 x 1200 px on a white background.
An Amazon employee stated an RGB 255, 255, 255 background for the main image in the Seller Forums. The official standards page needs a login, so check Seller Central, because rules vary by category.
Because a listing's main image usually calls for a clean product on white, and a shadow dirties the background. It stays available as an option for secondary photos and other uses.
Yes. Drop all the photos, set the size once and download everything as a ZIP; the settings apply to the whole batch and the touch-up brush is per photo.
Your photo never leaves your device. The cutout runs here, in your browser. Only the model (and the engine that runs it) is downloaded, once; no image is sent to any server.
MODNet, built for people and portraits. Small and quick; weaker on products, animals and objects.
All processing happens in your browser. The only things fetched from the internet are the cutout model (Hugging Face) and the ONNX Runtime inference engine (jsDelivr), downloaded once and checked by size and SHA-256. Your photos are never uploaded.