withoutbg/withoutbg-python

Python SDK for local and cloud background removal (pip install withoutbg)

What it solves

It provides a simple way to remove backgrounds from images using Python, offering a flexible choice between running a model locally for privacy and cost, or using a high-quality cloud API for better precision on complex details like hair and fur.

How it works

The library allows users to switch between two modes:

  • Local Mode: Uses an ONNX bundle (based on DINOv3, Depth Anything V2, and BiRefNet) that runs on CPU or GPU. A router determines whether to use a specialized matting model for fine details or a segmentation model for hard objects.
  • Cloud Mode: Connects to the withoutBG API for professional-grade results without requiring local infrastructure.

Who it’s for

Developers building scripts, notebooks, backends, or batch processing jobs who need to automate image background removal.

Highlights

  • Hybrid Approach: One API for both local open-weights inference and cloud-based processing.
  • Batch Processing: Optimized for processing multiple images by loading the model once.
  • Privacy-First: Local mode operates entirely offline after the initial weight download.
  • CLI Tool: Includes a command-line interface for quick background removal without writing code.
  • PIL Integration: Returns images as PIL Image objects in RGBA mode for easy compositing.

Related

  • Project
    danielgatis/rembg

    A tool for removing image backgrounds using pre-trained AI models, available as a CLI, Python library, or HTTP server.

  • Project
    pymatting/pymatting

    A Python library for alpha matting that estimates the transparency of foreground objects using trimaps to enable precise background removal and composition.

  • Project
    zhongweili/imagenie

    A privacy-focused desktop app for local AI image upscaling, face restoration, and background removal.

  • Project
    Faceplugin-ltd/Open-Source-Face-Recognition-SDK

    A free, on‑premise Python SDK for face detection, landmark extraction, embedding generation and similarity scoring, targeting Windows/Linux applications that need privacy‑preserving biometric matching.

  • Project
    Kaggle/kagglehub

    A Python library for programmatically downloading, uploading, and loading Kaggle datasets, models, and competition resources into data science frameworks.