danielgatis/rembg

Rembg is a tool to remove images background

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 16 minutes ago
Added to GitGenius on September 2nd, 2026
Created on August 10th, 2020
Open Issues & Pull Requests: 1 (+0)
GitHub issues: Enabled
Number of forks: 2,412
Total Stargazers: 24,645 (+1)
Total Subscribers: 172 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

Rembg is a background removal tool that works as a command-line interface, Python library, HTTP server, or Docker container.

The tool solves the problem of isolating subjects in images by removing their backgrounds. It uses deep learning models to detect and separate foreground objects from background elements, making it suitable for product photography, portrait editing, and other image processing workflows where clean backgrounds are needed.

Rembg suits developers and users who need programmatic or scriptable background removal without building machine learning models from scratch. The tool supports multiple deployment modes: as a standalone CLI for batch processing, as a Python library for integration into larger applications, as an HTTP server for remote processing, or containerized for cloud deployment. It offers flexible hardware support, with options to run on CPU, NVIDIA GPUs with CUDA, or AMD GPUs with ROCm, allowing users to choose based on their available hardware and performance requirements.

The project maintains active development with regular updates addressing hardware compatibility issues and dependency management. The maintainers provide detailed installation guidance for different GPU backends and document known compatibility challenges, such as CUDA and cuDNN requirements for NVIDIA systems. The tool is distributed across multiple accessible platforms including web-based demos and notebook environments, indicating ongoing effort to lower barriers to experimentation and adoption.