The Prompt Artists

Video

This paper examines the art practices, artwork, and motivations of prolific users of the latest generation of text-to-image (TTI) models. Through interviews, observations, and a survey, we provide a sampling of TTI artwork and find that: 1) the text prompt and the resulting image combine into a single art piece (prompts as art), and 2) prompt templates (prompts with ``slots'' for others to fill in with their own words) are developed to create generative art pieces. We discover that the desire for unique outputs leads artists to seek specialized vocabulary to produce distinctive art pieces (e.g., by adopting words from architecture). We also find that some artists look for ``glitches'' in the model that can be turned into artistic styles of their own right. From these findings, we outline specific implications for this emergent group of prompt artists.