In this episode of A.I. stuff - I’ve applied a bunch of different neural networks in an attempt to generate realistic faces of people from famous paintings. In the results, you’ll see an estimation of the face, so we can’t consider those faces as historically accurate, but it is a fun thing to do.  

💌 You can reach me here: https://neural.love/

Algorithms from this video:
🔗 First Order Model – https://github.com/tg-bomze/Face-Image-Motion-Model (I have used it offline, but for you, Google Colab will be more useful);
🔗 StyleGAN 2 – https://github.com/tg-bomze/StyleGAN2-Face-Modificator (I have used it offline, but for you, Google Colab will be more useful);
🔗 DAIN – https://github.com/baowenbo/DAIN (You can google for DAIN APP if you want to work with it as an app, I have not tried it, but people are happy)
🔗 ESRGAN – https://github.com/xinntao/ESRGAN
🔗 Additional faces generation tool – http://artbreeder.com/

I have started this project 3 months ago, I don't know the exact amount of hours that I have spent…