The Creativity of Text-to-Image Generation

05/13/2022

∙

by   Jonas Oppenlaender, et al.

∙

0

∙

share

Text-to-image synthesis has made a giant leap towards becoming a mainstream phenomenon since 2021. With text-to-image systems, anybody can create digital images and artworks. This provokes the question of whether text-to-image art is creative. This paper expounds on the nature of human creativity involved in text-to-image art with a specific focus on the practice of "prompt engineering". The paper argues that the current product-centered view of creativity may fall short in the context of text-to-image generation. A case exemplifying this shortcoming is provided and the importance of online communities for the creative ecosystem of text-to-image art is highlighted. We provide a high-level summary of this online ecosystem drawing on Rhodes's conceptual model of creativity. We provide a discussion on the challenges for evaluating the creativity of text-to-image generation and discuss opportunities for research on text-to-image art in the field of Human-Computer Interaction (HCI).