Checkout http://deepart.io/. You'll have to pay a little bit but they provide a very convenient interface for doing this.

I'm interested in the question too and, if he's of similar mind to me, that's not what he meant.

I'm curious what it takes to make a piece of software like this. People say "Using NN" and stuff. But if I make an app with a way to load a picture and then add NN to it, this won't come out. I'm wondering what the specific function of the networks are here.

Definitely. I want to understand what's going on here and be able to apply some creativity to the process, not just use existing tools without understanding.

From another comment: https://github.com/jcjohnson/neural-style