/Artistic-Neural-Style-Transfer

Style transfer is a computer vision technique that takes two image a content image and a style reference image and blends them together so that the resulting output image retains the core elements of the content image, but appears to be “painted” in the style of the style reference image.

Primary LanguagePythonMIT LicenseMIT

Artistic Neural Style Transfer

The Artistic Neural Style Transfer project is an interactive web application that leverages the power of deep learning to apply artistic styles to images. Using a pre-trained TF-Hub fast neural style transfer model, this project enables users to transform their photos into visually appealing pieces of art inspired by famous paintings and other artistic styles.

The system utilizes convolutional neural networks to extract the content and style features of the input image and a chosen artistic style. By combining these features, it generates a new image that retains the content of the original image while adopting the style characteristics. This creates a fascinating blend of content and style, resulting in unique and captivating visuals.

Demo

Check out the live demo of the Artistic Neural Style Transfer application here.


APP Demo

Features

  • Apply various artistic styles to your images in real-time.
  • User-friendly web-based GUI powered by Streamlit.
  • Utilizes a pre-trained TF-Hub fast neural style transfer model for efficient and high-quality style transfer.
  • Deployed on Streamlit Cloud for easy accessibility.
  • Interactive and intuitive design for a seamless user experience.

Outputs

Content Image Style Image Generated Image

MIT License