The main people in the pictures are real. We met them as usual in a real place and photographed them, tried out different poses and backgrounds and finally chose a picture.
Everything else in the pictures is fiction – created by an artificial intelligence (AI) in collaboration with us humans. First, we asked the main characters portrayed to name keywords that we could use to guide the AI. These keywords are identified below the pictures. Then we experimented until we had a picture that fit. To do this, we had to interpret, modify and add to the keywords. The commands – or "prompts" – finally given to the Midjourney AI are also shown.
It is exciting that the AI often generated completely different images than we humans had imagined, which can be quite irritating.
New magazine uniFOKUS
Subscribe free of charge now!
This article first appeared in uniFOKUS, the new University of Bern print magazine. Four times a year, uniFOKUS shows what academia and science are capable of. Thematically, each issue focuses on one specialist area from different points of view and thus aims to bring together as much expertise and as many research results from scientists and other academics at the University of Bern as possible.