Pictures combined using Neural networks

Isn't this thread enough to proof the movie wouldn't have to be hand-painted? I'm not going to find the Van Gogh themed NN posted before.

Now we just need another neural network to remove the watermark from the free version :)

"Estimated waiting time: 9145.0 minutes"

This is not how you are going to earn billions ;)

A Billion second photo app.

Build a database, randomly assemble.

Recurse.

Use whatever language generator deemed appropriate* to assign proper titles for the newly-evolved art movement.

*this may be delegated to a meat-computer, in pity.

Before that becomes the main problem, that other problem must be solved where you give it your picture and the Mona Lisa whose style is to be copied and the way it copies the style is it paints her eyebrow atop your mouth. 'Cause it's not like this thing can really distinguish between "style" and "content". What it does is it pastes patches from the "style" image onto the "content" image. Sometimes the result is interesting, much of the time it's between boring and terrifying. It's cool and all, but it's not much more intelligent than your favorite Photoshop filter.

"Going the way of the dodo..."

Do you know how they get stable videos from DeepDream? I've seen it elsewhere too, but my initial guess would have been that DeepDream would give ridiculous results if you ran it on each frame individually. I expect it's sensitive to tiny differences between frames.

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.