Training and Critiquing AI Through Art at WashU

""I chose abstract painting as a mode on purpose - its intention is to interrupt an image and make it harder to look at, so you have to think about your own process of looking," she says."

""They're so incredibly detailed that in some ways they become abstract - they're no longer realistic," she remarks."

""I was so happy to be at WashU at that moment, because there is real intent and motivation behind putting together teams for interdisciplinary research," she says."

Tiffany Calvert creates large-scale still life oil paintings that integrate images produced by generative AI. The practice builds on Dutch and Flemish still life traditions and a collected dataset of about 650 images. Earlier work used a StyleGAN to generate springboard images that Calvert painted abstractly over, interrupting realism to activate viewer perception. A protocol change in existing software halted progress and prompted a collaboration with Washington University engineers. The engineers developed a custom diffusion model capable of training on smaller datasets, enabling precise control and continuation of the hybrid historical–AI painting process.

Read at Hyperallergic