How to create art with deep neural networks

The advent of easily accessible, mondo computing power could open up lots of possibilities in the arts, not just in the startup and tech world.

Brooklyn startup Paperspace has a new post out about how to use its product (which is sort of like AWS for the computational power required of machine learning) to make art.

The photos are incredible.

The post centers on “style transfer,” which is taking the style of one image and imparting it onto the content of another.

“The central problem of style transfer revolves around our ability to come up with a clear way of computing the ‘content’ of an image as distinct from computing the ‘style’ of an image,” the post reads. “Before deep learning arrived at the scene, researchers had been handcrafting methods to extract the content and texture of images, merge them and see if the results were interesting or garbage.”

Read the full post