Skip to content
//Image Upscaler & Background Remover example\\

Remove backgrounds (transparent PNG + mask)

Cut the subject out of each photo as a transparent PNG and also save its black-and-white mask.

Updated November 12, 2026

What this example returns

The dataset’s “Processed images” view shows 14 columns: Result, Width, Height, MP, Format, Bytes, Operation, Scale, Background removed, Source, Source width, Source height, Note, and Error. See every output field.

What each setting does

The input this example runs Image Upscaler & Background Remover with. “Try this input” opens it in the console, where you can run it as-is or change any field first.

Image URLs imageUrls

https://upload.wikimedia.org/wikipedia/commons/thumb/2/26/YellowLabradorLooking_new.jpg/500px-YellowLabradorLooking_new.jpg, https://upload.wikimedia.org/wikipedia/commons/thumb/4/45/A_small_cup_of_coffee.JPG/500px-A_small_cup_of_coffee.JPG, https://upload.wikimedia.org/wikipedia/commons/thumb/3/35…

Direct links to the images, one per line: JPEG, PNG, WebP, GIF (first frame), AVIF, HEIC/HEIF, TIFF or BMP, up to 60 MB and 50 megapixels each. Google Drive, Dropbox and GitHub share links are turned into download links automatically. Every image gives one result row. You can also (or instead) take images from a…

What to do operation

Remove background

Upscale the image, remove its background, or both (the background is removed first, then the cut-out is upscaled).

Default: Upscale → this example uses Remove background

Background removal model backgroundModel

Standard

Standard (IS-Net): fast and clean on people, animals, products and most photos; works at the default 4 GB of memory. Detailed (BiRefNet): finer edges on hair, fur and thin parts, but about five times slower and it needs 8 GB of memory: set Memory to 8 GB in the run options (with less memory the standard model is used…

Clean edge colours refineEdges

Yes

Remove the old background's colour from soft edges such as hair, so the cut-out looks natural on any new background (images up to 12 MP).

Also save the mask outputMask

Yes

Save the black-and-white mask of the subject as a separate PNG (the maskUrl column), for your own compositing.

Default: No → this example uses Yes

Output format outputFormat

PNG

PNG is lossless and keeps transparency. WebP keeps transparency in a much smaller file. JPEG is smallest but has no transparency.

.json
{
  "imageUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/thumb/2/26/YellowLabradorLooking_new.jpg/500px-YellowLabradorLooking_new.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/thumb/4/45/A_small_cup_of_coffee.JPG/500px-A_small_cup_of_coffee.JPG",
    "https://upload.wikimedia.org/wikipedia/commons/thumb/3/35/Tux.svg/250px-Tux.svg.png"
  ],
  "operation": "removeBackground",
  "backgroundModel": "standard",
  "refineEdges": true,
  "outputMask": true,
  "outputFormat": "png"
}

What it costs

You pay for the events the actor reports, such as each result or page it produces. Platform usage is included in the event prices: compute, proxies, browser and storage cost nothing extra.

  • Image upscaledfrom $0.0102One image upscaled and saved, for source images up to 2 megapixels; larger sources count one more per started 2 megapixels. Failed images are free.
  • Background removedfrom $0.00595One image with its background removed and saved (transparent, coloured or cropped cut-out, with the optional mask). Failed images are free.

Full pricing

Other ways to run Image Upscaler & Background Remover

All examples of Image Upscaler & Background Remover

About Image Upscaler & Background Remover

Upscale images 2x to 4x with Real-ESRGAN and remove backgrounds with BiRefNet: sharper photos and illustrations, transparent PNG cut-outs, white or coloured backgrounds, crop to subject and masks. Links, datasets or uploaded files; one row per image with a download link.

Price:
from $10.20 / 1,000 results
Developer:
Echofield

Image Upscaler & Background Remover pageOutput fieldsPricing

Related actors

//From the blog\\

Latest articles

All articles

The internet is full of data.
Start owning yours.

Scrape.ly gives you the infrastructure, the tooling, and the team to extract, process, and operationalize web data at any scale. Setup takes minutes.

No credit card. No setup calls.