Abstract
Recently, text-to-image generative Artificial Intelligence (AI) models have demonstrated their ability to generate high-quality art with text prompts. However, generative AI is still incapable of creating images that precisely reflect emotion. We propose Prompirit, an automatic prompt engineering assistance for improving AI-generated art in terms of expressiveness of emotion and aesthetics. We explored various approaches to refine users' free-form text input by incorporating user emotion and style modifiers. Statistical analysis and user evaluation with 100 respondents showed that Prompirit significantly improved the alignment of image-emotion and the aesthetics of the generated image while precisely conveying the content of the original input text. Based on the results, we provide implications for creating affective images.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2024 IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2024 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 138-143 |
| Number of pages | 6 |
| ISBN (Electronic) | 9798350351187 |
| DOIs | |
| State | Published - 2024 |
| Event | 25th IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2024 - San Jose, United States Duration: 7 Aug 2024 → 9 Aug 2024 |
Publication series
| Name | Proceedings - 2024 IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2024 |
|---|
Conference
| Conference | 25th IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2024 |
|---|---|
| Country/Territory | United States |
| City | San Jose |
| Period | 7/08/24 → 9/08/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
Keywords
- Emotional and Art Technology
- Prompt Engineering
- Text-to-Image Generative AI