Generative Zoology with Neural Networks (corte.si)

Beautiful!

If the images are all black and white, why not train in a two tone, or greyscale colour space?

Silhouettes don't have enough information for a neural network to really learn the structural relations. You can do "generative zoology" with full color and get very convincing results-- here's a GAN trained on beetle illustrations: https://www.cunicode.com/works/confusing-coleopterists

What neat results! Did you exclude the plants and shellfish? How many images were in the training set?

By my calculations that training would cost you ~$700 on AWS. Is that right?

4 * 24h * $7.20/h = $691.20

$7.20/h for an 8 GPU instance: https://aws.amazon.com/ec2/instance-types/p2/