WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Remove Anything/bria/remove-background

image-to-image

bria/remove-background

Bria AI's remove background model.

Hint: You can drag and drop a file or click to upload

preview
Whether to preserve the alpha channel of the image.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

Your request will cost $0.018 per run.

For $1 you can run this model approximately 55 times.

One more thing:

ExamplesView all

README

Bria Remove Background

Bria Remove Background extracts clean subjects from images with a high-quality alpha matte. It’s fast, consistent, and production-ready for e-commerce listings, ad creatives, social posts, and compositing. The model is trained on licensed data, supporting safe, compliant commercial use.

Highlights

  • Clean cutouts with detailed edges (hair, fur, semi-transparent areas).
  • Alpha workflow: preserve or drop the alpha channel to match your pipeline.

Parameters

  • image* (required) Source image (URL or upload). Missing image will fail.

  • preserve_alpha (checkbox) Keep the alpha channel in the returned asset for immediate compositing.

Pricing

  • Per run: $0.018

How to Use

  1. Upload/Paste image (required).
  2. Toggle preserve_alpha if you need a premultiplied cutout for direct compositing.
  3. Click Run to generate your cutout and download the result.

Output & Workflow Tips

  • Post background: Place the cutout over solid color, gradient, or generated scenes (e.g., with Bria Background Generation).
  • Edge finesse: For extremely fine hair or translucent fabric, a light feather/refine-edge pass can achieve pixel-perfect results.
  • Consistent catalogs: Use identical lighting shots and batch the same settings for uniform store pages.