A couple of moths ago we started doing some tests using a project known as deep style.This project combines the content of one image with the style of another image using convolutional neural networks (you don’t know what that is? No problem, it’s just some deep learning black magic stuff).
What it basically does is detect the main features from the style image and applies them to the content image. We did some tests of our own and would like to share the results with you:
##One style
##Landscape
##Two styles
Videos
The project we used has been employed to generate videos:
We tested it in a small image sequence:
Other related projects:
There is a project that is improved for video generation: artistic-videos