Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering

TL;DR

This paper explores prompt engineering as a new creative skill for AI art, examining how people evaluate, craft, and refine prompts, and highlighting the need for practice to master style-specific prompting.

Contribution

It provides empirical insights into prompt engineering as a non-intuitive skill requiring learning and practice, and identifies key challenges and future directions.

Findings

Participants can evaluate prompt quality effectively.

Participants can craft descriptive prompts.

Style-specific vocabulary is lacking in prompt writing.

Abstract

We are witnessing a novel era of creativity where anyone can create digital content via prompt-based learning (known as prompt engineering). This paper investigates prompt engineering as a novel creative skill for creating AI art with text-to-image generation. In three consecutive studies, we explore whether crowdsourced participants can 1) discern prompt quality, 2) write prompts, and 3) refine prompts. We find that participants could evaluate prompt quality and crafted descriptive prompts, but they lacked style-specific vocabulary necessary for effective prompting. This is in line with our hypothesis that prompt engineering is a new type of skill that is non-intuitive and must first be acquired (e.g., through means of practice and learning) before it can be used. Our studies deepen our understanding of prompt engineering and chart future research directions. We conclude by envisioning four potential futures for prompt engineering.