The Prompt Artists

TL;DR

This paper explores the artistic practices and community of users engaging with text-to-image generative AI, highlighting how prompts and stylistic techniques are developed and valued as art forms.

Contribution

It introduces the concept of prompts as art and details the community practices, including prompt templates and stylistic innovations, around generative AI art.

Findings

Prompts and images are collectively considered art.

Prompt templates facilitate style creation.

Community values unique and distinctive outputs.

Abstract

This paper examines the art practices, artwork, and motivations of prolific users of the latest generation of text-to-image models. Through interviews, observations, and a user survey, we present a sampling of the artistic styles and describe the developed community of practice around generative AI. We find that: 1) the text prompt and the resulting image can be considered collectively as an 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 styles. We discover that the value placed by this community on unique outputs leads to artists seeking specialized vocabulary to produce distinctive art pieces (e.g., by reading architectural blogs to find phrases to describe images). We also find that some artists use "glitches" in the model that can be turned into artistic styles of their own right. From these findings, we outline specific implications for design regarding future prompting and image editing options.