Neural Style Transfer WebApp

Neural style transfer is an optimization technique used to take two images—a content image and a style reference image (such as an artwork by a famous painter)—and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image.

Access

Check the Heroku Deployment Here : https://nst-tf.herokuapp.com .

Heroku Servers provide limited memory. So, server might crash after single use. Also, loading time is much higher.

OR

Better method to access the web-app is described below.

Getting started (Better way to access WebApp)

Google Colab provides the virtual environment to run a Flask based Web-App which is tunneled to Internet with the help of Ngrok. A Bare Minimum Setup 😉

All you have to do is to open the colab instance and run the only cell and you are ready to stylize the images.

Built With

• ReactJS
• Tensorflow 2.0
• Open-CV
• Flask
• Ngrok

Web-App Interface

Licensing

Distributed under the MIT License. See LICENSE for more information.

Contact

Sneh Sagar - snehsagarajput@gmail.com

Project Link: https://github.com/snehsagarajput/nst-app