Ctrl + K
DocumentationLog inGet started

tessl/pypi-rembg

tessl install tessl/pypi-rembg@2.0.0

Remove image background using advanced AI models including U-Net, BiRefNet, and SAM with support for multiple input formats and GPU acceleration

Agent Success

Agent success rate when using this tile

84%

Improvement

Agent success rate improvement when using this tile compared to baseline

0.94x

Baseline

Agent success rate without this tile

89%

task.mdevals/scenario-8/

Image Edge Refiner

A tool that removes backgrounds from images with refined edge quality for semi-transparent and complex boundary regions.

Specification

Your task is to implement a background removal tool that produces high-quality edge refinement for images containing fine details like hair, fur, or semi-transparent materials. The tool should handle images with complex boundaries and produce natural-looking cutouts.

Capabilities

Background Removal with Edge Refinement

The tool removes backgrounds from images while applying advanced edge refinement techniques to preserve fine details and handle semi-transparent regions naturally.

  • Given an image file "input.png", the tool removes the background and saves refined output to "output.png" with transparency @test
  • The output image has an alpha channel for proper transparency @test
  • Edge refinement applies foreground threshold of 240, background threshold of 10, and erosion size of 10 @test

API

def remove_background_refined(input_path: str, output_path: str) -> None:
    """
    Remove background from image with advanced edge refinement.

    Args:
        input_path: Path to input image file
        output_path: Path to save output PNG with transparency
    """
    pass

Dependencies { .dependencies }

rembg { .dependency }

Provides background removal with alpha matting support for edge refinement.

@satisfied-by

Version

Workspace
tessl
Visibility
Public
Created
Last updated
Describes
pypipkg:pypi/rembg@2.0.x
tile.json