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-1/

Model Download Manager

A utility for managing rembg AI model downloads with validation and status reporting. This tool should leverage rembg's model management capabilities to handle downloading and checking model availability.

Capabilities

Download Specific Models

Build a tool that downloads specific rembg models and validates they are properly stored.

  • Downloads a single specified model name and returns True if successful @test
  • Downloads multiple model names in a single operation and returns True if all succeed @test
  • Returns False when attempting to download an invalid model name @test

Check Downloaded Models

Build functionality to check which models are already downloaded locally.

  • Returns a list of model names that are currently downloaded @test
  • Returns an empty list when no models are downloaded @test

Verify Model Availability

Build functionality to verify if specific models are available locally before processing.

  • Returns True when checking for a model that is downloaded @test
  • Returns False when checking for a model that is not downloaded @test

Implementation

@generates

API

def download_models(model_names: list[str]) -> bool:
    """
    Download specified rembg models.

    Args:
        model_names: List of model names to download (e.g., ['u2net', 'birefnet_portrait'])

    Returns:
        True if all models downloaded successfully, False otherwise
    """
    pass

def list_downloaded_models() -> list[str]:
    """
    Get a list of all models currently downloaded locally.

    Returns:
        List of downloaded model names
    """
    pass

def is_model_downloaded(model_name: str) -> bool:
    """
    Check if a specific model is downloaded locally.

    Args:
        model_name: Name of the model to check

    Returns:
        True if the model is downloaded, False otherwise
    """
    pass

Dependencies { .dependencies }

rembg { .dependency }

Provides background removal and model management capabilities.

Version

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