Making Pictures with Generative Adversarial Networks

In this first non-technical introduction to emerging AI techniques, artist Casey Reas explores what it’s like to make pictures with generative adversarial networks (GANs), specifically deep convolutional generative adversarial networks (DCGANs). This text is imagined as a primer for readers interested in creative applications of AI technologies. Ideally, readers will explore the strategies of this emerging field as outlined, and remix them to suit their desires. We hope to inspire future research and collaboration, and to encourage a rigorous discussion about art in the age of machine intelligence.

The second revised edition of Making Pictures with Generative Adversarial Networks now includes an introduction by Nora Khan and additional artwork plates.