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

Создание произведений искусства с помощью подсказок для ИИ: исследование творческого навыка разработки подсказок
Johanna Silvennoinen, Jonas Oppenlaender, Rhema Linder
2024-11-28

AI artprompt engineeringprompt qualitystyle-specific vocabularytext-to-image generation
We are witnessing a novel era of creativity where anyone can create digital content via prompt-based learning (known as prompt engineering). This article 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 at a level of high quality. Our studies deepen our understanding of prompt engineering and chart future research directions. We conclude by envisioning four potential futures for prompt engineering.
1
Across three studies, participants could assess prompt quality, write descriptive prompts, and refine existing prompts.
2
Participants lacked the style-specific vocabulary needed for effective prompting, limiting the quality of their generated prompts.
3
The article investigates prompt engineering as a distinct creative skill for generating AI art with text-to-image systems.
4
The findings suggest prompt engineering is non-intuitive and requires practice or learning before it can be performed at a high level.
5
The research advances understanding of prompt engineering and outlines four potential future directions for the skill.

prompt engineering for text-to-image AI art generation

the creative skill of prompt engineering, including the ability to evaluate, write, and refine prompts and the acquisition of style-specific vocabulary

Publication Details
Publication Date
2024-11-28
Journal
Publisher
ISSN
Cited by
189
Access Type
Author Information
Authors
Johanna Silvennoinen
Jonas Oppenlaender
Rhema Linder
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat
Make a presentation
100%