Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911944566374400 |
|---|---|
| author | Oppenlaender, Jonas Linder, Rhema Silvennoinen, Johanna |
| author_facet | Oppenlaender, Jonas Linder, Rhema Silvennoinen, Johanna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_13534 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering Oppenlaender, Jonas Linder, Rhema Silvennoinen, Johanna Human-Computer Interaction H.m; I.2 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. |
| title | Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering |
| topic | Human-Computer Interaction H.m; I.2 |
| url | https://arxiv.org/abs/2303.13534 |