rembg

(β˜… 24,352)

Rembg is a tool to remove images background

  • .dockerignore
  • .editorconfig
  • .gitattributes
  • .gitignore
  • .markdownlint.yaml
  • .python-version
  • _build-exe.ps1
  • _modpath.iss
  • _setup-cpu.iss
  • _setup-gpu.iss
  • CITATION.cff
  • docker-compose.yml
  • Dockerfile
  • Dockerfile_nvidia_cuda_cudnn_gpu
  • LICENSE.txt
  • logo.png
  • MANIFEST.in
  • onnxruntime-installation-matrix.png
  • pyproject.toml
  • pytest.ini
  • README.md
  • rembg.ipynb
  • rembg.py
  • rembg.spec
  • USAGE.md

πŸš€ Installation Guide

1. Get the code
git clone https://github.com/danielgatis/rembg

Downloads the entire project code from GitHub to your computer.

cd rembg

Moves into the project folder you just downloaded.

2. Official Install Script

Easy Recommended
Prerequisites
  • Python 3 Python is required to use pip.
pip install "rembg[cpu]" # for library

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[cpu,cli]" # for library + cli

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[gpu]" # for library

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[gpu,cli]" # for library + cli

Installs the package published on PyPI directly β€” no need to clone the source.

βœ… After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.

Pulled directly from this repo's README.

3. Docker

Easy
Prerequisites
  • Git Needed to download the project code from GitHub.
  • Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker run -v .:/data danielgatis/rembg i /data/input.png /data/output.png

Runs the built image as an actual container.

docker build -t rembg-nvidia-cuda-cudnn-gpu -f Dockerfile_nvidia_cuda_cudnn_gpu .

Builds a runnable image based on the Dockerfile.

sudo docker run --rm -it --gpus all -v /dev/dri:/dev/dri -v $PWD:/data rembg-nvidia-cuda-cudnn-gpu i -m birefnet-general /data/input.png /data/output.png

Runs the built image as an actual container.

βœ… Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.

Pulled directly from this repo's README.

4. Python

Easy
Prerequisites
  • Git Needed to download the project code from GitHub.
  • Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.
pip install "rembg[cpu]" # for library

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[cpu,cli]" # for library + cli

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[gpu]" # for library

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[gpu,cli]" # for library + cli

Installs the package published on PyPI directly β€” no need to clone the source.

pip install "rembg[rocm]" # for library

Installs the package published on PyPI directly β€” no need to clone the source.

βœ… If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.

// repository documentation