I believe one came out recently, I saw it on GitHub a few days ago. It mainly did landscape and searched for similar images then combined them to form a new one. It also supported image manipulation, eg turning a brown square purse into a green rounded one. I'll see if I can find it and edit the link in.

EDIT: https://github.com/junyanz/iGAN

Heres a good video showing it off https://www.youtube.com/watch?v=9c4z6YsBGQ0&feature=youtu.be