zest

<h1 align="center" >Remove Objects Server</h1> <!-- TABLE OF CONTENTS --> <details> <summary>Table of Contents</summary> <ol> <li><a href="#about-the-project">About</a></li> <li><a href="#built-with">Installation</a></li> <li><a href="#usage">Usage</a></li> <li><a href="#license">License</a></li> </ol> </details>

About

This is a Python project for removing unwanted objects from images using the inpainting technique. It includes a server implemented with FastAPI and an endpoint for processing images by applying inpainting techniques. This project uses a deep learning library, PyTorch, for training and testing the inpainting model.

<p align="center"> <img src="lama_cleaner_video.gif" /> </p>

Installation

To install this project, you should first create a virtual environment using the following commands:

python3 -m venv venv
source venv/bin/activate

After creating the virtual environment, you can install the required libraries using pip:

pip install -r requirements.txt

Usage

To use this project, first start the server by running main.py:

python main.py

After the server has started, you can test following endpoints:

• http://{localhost}:{port}/lama/paint

  • This endpoint accepts an image file in the file parameter and applies inpainting techniques to remove unwanted objects.

• http://{localhost}:{port}/mask

  • Mask endpoint is used to apply a mask to an image. The route accepts img and mask as input parameters. Then, it applies a mask on an image.
  • You can use testX.png image and testX_mask.png mask in image folder for testing.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Other command

docker build -t zest .