NST-Project

Turn any photo into an artistic masterpiece using Neural Style Transfer

Table of Contents

• About The Project
• Getting Started
  • Prerequisites
  • Installation
• Usage
• Contact
  • Maintainer(s)
  • creators(s)
• Additional documentation

About The Project

Neural Style Transfer (NST) is a deep learning technique that merges the content of one image with the style of another. This project uses PyTorch to implement NST, allowing you to generate stylized images with pre-trained VGG-19 features. You can experiment with different styles, content images, and tuning parameters to get unique results.

(back to top)

Getting Started

To set up a local instance of the application, follow the steps below.

Prerequisites

The following dependencies are required to be installed for the project to function properly:

• Python 3.8+
• PyTorch
• torchvision
• Pillow

(back to top)

Installation

Now that the environment has been set up and configured to properly compile and run the project, the next step is to install and configure the project locally on your system.

1. Clone the repository

   git clone https://github.com/cgs-iitkgp/NST-Project.git
   cd NST-Project

2. Install dependencies

   pip install -r requirements.txt

(back to top)

Usage

Once installed, you can run the script from the command line to apply style transfer.

• Execute the script

  python nst.py --content path/to/content.jpg --style path/to/style.jpg --output output.jpg

(back to top)

Contact

Maintainer(s)

The currently active maintainer(s) of this project.

• Shaurya Choudhary

Creator(s)

Honoring the original creator(s) and ideator(s) of this project.

• Shaurya Choudhary

(back to top)

Additional documentation

• License

(back to top)