Catalog

Marketplace background & framing studio

Details

How to use Marketplace background & framing studio

What the tool does, how to run it, and what to expect from the result.

How to clean a product photo background

To clean a product photo, upload one image, brush over the rough background areas such as wall edges, tabletop seams, or shadow corners, choose a white or neutral fill, frame the product, and export. The entire process runs locally in your browser, so the photo is never uploaded to a server.

This is honest manual cleanup rather than automatic cutout: it shines when the product is already usable and only the background needs tidying. You decide exactly what gets cleaned, which avoids the ragged edges that automatic removal can leave on tricky products.

  • Upload one product photo
  • Brush away edge distractions and seams
  • Apply a white, off-white, or neutral fill
  • Frame with a preset, then export locally

Why manual cleanup is useful without server-side AI

A lot of seller-side image prep does not need a full cutout. Often the product is already fine, but a wall edge, tabletop seam, shadow corner, or stray room detail makes the listing feel unpolished. Manual cleanup fixes exactly those distractions without trying to isolate the whole subject.

The result is practical listing prep: clean small distractions, keep the canvas shape consistent, frame the product clearly, and save an upload-ready file that looks more intentional on Etsy, Amazon, eBay, or Shopify. Square, portrait, and landscape presets match common product-photo destinations.

  • Manual cleanup for corners, shadows, and room details
  • White, off-white, or neutral fills for cleaner catalogs
  • Square, portrait, and landscape presets
  • Browser-only export with metadata stripped on save
Tips

Getting a better result out of Marketplace background & framing studio

Specific settings and thresholds, not general advice.

  • Auto cleanup runs a real segmentation model (MODNet) locally in a web worker through WebGPU, falling back to WASM. The first run downloads the model to your browser cache, so it is slow once and fast after that, and it times out after 45 seconds on a slow fallback path.
  • The model resizes the input to a maximum edge of 1600 px before segmenting, so the mask it returns is limited by that even if your photo is 4000 px wide. Fine hair, wisps, and thin straps will need the manual brush afterwards.
  • Auto cleanup is explicitly a beta pass on simple subjects. Treat it as a first cut and finish the edges with the erase and restore brushes, which run from 12 to 140 px.
  • The four workflow presets all export PNG, because a cutout with transparency has to. If you then choose Transparent as the background tone and export JPG, the transparency collapses to black, so pick a white or neutral fill if you need a JPG.
  • Amazon's main image requires a pure white (RGB 255,255,255) background. The White fill tone here is exactly #ffffff, but the off-white (#f5f1e9) and neutral (#edf1f4) tones are not, so keep those for secondary and lifestyle slots.
Limits

What Marketplace background & framing studio does not do

The honest boundary, so you do not lose time finding it yourself.

  • One photo at a time. There is no batch queue.
  • Auto cleanup is a beta segmentation pass, not a professional cutout. Hair, glass, and fine mesh will need manual work.
  • No shadow generation, no reflection, and no relighting. The cutout sits flat on the fill colour.
  • No colour correction, exposure, or retouching of the product itself.
Reference

Terms used on this page

Short, plain-language definitions for the formats and settings above.

At a glance

Who Marketplace background & framing studio is for

A quick way to understand who this helps, what it solves, and where it connects next.

Best fit

Etsy, Amazon, eBay, and Shopify sellers who need cleaner product photos with more consistent framing and simpler background presentation

Ideal for

Preparing product images that do not need full retouching, but do need cleaner edges, a lighter background fill, better centering, and a more consistent listing frame

FAQ

Common questions

Short answers for the questions people usually have before trying a utility like this.

Is this an AI background remover?

No. This tool is intentionally manual cleanup plus background fill and framing. It is best when the source is already close and only needs a cleaner listing presentation.

Does the image leave my device?

No. Upload, preview, cleanup, and export all run locally in your browser, and the downloaded file is rebuilt through canvas so common metadata is stripped on save.

What kinds of photos work best here?

Photos where the subject is already easy to recognize and the remaining issue is mostly background cleanliness, centering, or framing rather than complex cutout work.

Is it free to use?

Yes. The background cleaner runs in your browser at no cost, with no signup and no watermark on the exported image.

Which marketplaces does it suit?

The square, portrait, and landscape presets fit common destinations like Etsy, Amazon, eBay, and Shopify storefronts.

Is the automatic cleanup an AI background remover?

It runs the MODNet segmentation model, but entirely on your own machine inside a web worker, preferring WebGPU and falling back to WASM. Nothing is sent to a server. It is labelled beta because it works well on simple product shots with a clear subject and struggles with hair, glass, and busy backdrops.

Why is the first run slow?

The model has to be fetched and prepared in the browser the first time. After that it is cached, so later runs start immediately. If the browser lacks WebGPU it falls back to WASM, which is markedly slower and can hit the 45 second timeout on a large photo.

What canvas presets does it export?

Square listing at 1600x1600, portrait listing at 1200x1500, and landscape listing at 1600x1200. The four workflow presets pair those with a background tone and an export format: Amazon clean, Etsy portrait, eBay practical, and Shopify catalog.

Which background fill should I choose for Amazon?

White, which is exactly #ffffff and matches Amazon's pure white requirement for a main product image. Off-white and neutral are deliberately slightly tinted, so they suit secondary images and storefront cards but will not pass a main-image check.

Can I undo a bad brush stroke?

Yes, the cleanup stage keeps a stroke history and has an undo. The brush also has a restore mode, so you can paint a wrongly erased area back in rather than starting over.

Does the photo ever leave the device?

No. Both the manual brush and the automatic segmentation model run in the browser, and the export is rebuilt from a canvas, which drops the original EXIF along the way.

Recommendations

You Might Also Like

Nearby tools from the catalog that fit the same job or workflow.

Cleanor app

Do it all on your device

Cleanor puts these tools in one app: compress and convert images, video, and audio, work with PDFs, and scan text right on your device. Plus free up storage and clear inbox clutter with Email Cleaner. Start with a free trial.

  • iPhone
  • Android
  • Macsoon
  • Windowssoon