Available now

BiRefNet Background Removal V2: background removal

Cut a person or object out of a photo with BiRefNet V2. Use the transparent result in a new composition, or export the mask for further editing.

Model ID

Input

Fields marked * are required. Review the price before generating.

The image to remove background from

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

Whether to output the mask used to remove the background

Whether to refine the foreground using the estimated mask

Price$0.28 / run

You sign up first. Your settings are kept.

About this model

Overview

Upload one image and get the subject back with the background removed, as PNG, WebP or GIF. You can also ask for the black and white mask alongside the cutout, or for the mask alone.

Pick the variant that fits the picture: a light general model for most images, a heavier one for harder edges, one tuned for portraits and one for matting fine detail such as hair. A higher working resolution helps with large photos.

What you can build

  • Product cutouts for a shop or catalog
  • Portraits ready to place on a new background
  • Masks for compositing in an image editor
  • Transparent stickers and overlays

Prompting tips

  • Use the portrait variant for people and the matting variant when hair or fur edges matter.
  • Raise the working resolution for large, detailed photos; the largest size needs the dynamic variant.
  • Turn on the mask option when you want to adjust the cut yourself later.

What to check

Check hair, glass and gaps against light and dark backgrounds. Compare the selected foreground with the untouched source.

Inputs

  • Model (optional): Model to use for background removal. The 'General Use (Light)' model is the original model used in the BiRefNet repository. The 'General Use (Light 2K)' model is the original model used in the BiRefNet repository but trained with 2K images. The 'General Use (Heavy)' model is a slower but more accurate model. The 'Matting' model is a model trained specifically for matting images. The 'Portrait' model is a model trained specifically for portrait images. The 'General Use (Dynamic)' model supports dynamic resolutions from 256x256 to 2304x2304. The 'General Use (Light)' model is recommended for most use cases. The corresponding models are as follows: - 'General Use (Light)': BiRefNet - 'General Use (Light 2K)': BiRefNet_lite-2K - 'General Use (Heavy)': BiRefNet_lite - 'Matting': BiRefNet-matting - 'Portrait': BiRefNet-portrait - 'General Use (Dynamic)': BiRefNet_dynamic. Options: General Use (Light), General Use (Light 2K), General Use (Heavy), Matting, Portrait, General Use (Dynamic).
  • Operating Resolution (optional): The resolution to operate on. The higher the resolution, the more accurate the output will be for high res input images. The '2304x2304' option is only available for the 'General Use (Dynamic)' model. Options: 1024x1024, 2048x2048, 2304x2304.
  • Output Mask (optional): Whether to output the mask used to remove the background.
  • Refine Foreground (optional): Whether to refine the foreground using the estimated mask.
  • Image (required): URL of the image to remove background from.
  • Output Format (optional): The format of the output image. Options: webp, png, gif.
  • Mask Only (optional): Whether to return only the segmentation mask without applying it to the image. When set to `True`, only the mask will be returned and foreground refinement will be skipped. Useful for reducing computation and data transfer when only the mask is needed.

Output and limits

  • File formats: WEBP, PNG, GIF.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to: $0.28 / run