There was a paper [https://github.com/taoxugit/AttnGAN/] recently where a
research team trained a machine learning algorithm (a GAN they called AttnGAN
[https://github.com/taoxugit/AttnGAN/]) to generate pictures based on written
descriptions. It’s like Visual Chatbot
[http://aiweirdness.com/post/175110257767/the-visual-chatbot] in reverse. When
![This AI is bad at drawing but will try anyways.](/content/images/size/w795/image/fetch/w_1200-c_limit-f_jpg-q_auto:good-fl_progressive:steep/https-3A-2F-2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com-2Fpublic-2Fimages-2F0e7e5d38-1916-4e9f-a89e-0fa528857c0e_1598x756.png)