Prompirit: Automatic Prompt Engineering Assistance for Improving AI-Generated Art Reflecting User Emotion

被引:0
|
作者
Kim, Hannah [1 ]
Lee, Hyun [1 ]
Pang, Sunyu [1 ]
Oh, Uran [1 ]
机构
[1] Ewha Womans Univ, Dept Comp Sci & Engn, Seoul, South Korea
来源
2024 IEEE INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE, IRI 2024 | 2024年
关键词
Prompt Engineering; Text-to-Image Generative AI; Emotional and Art Technology;
D O I
10.1109/IRI62200.2024.00038
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:138 / 143
页数:6
相关论文
共 3 条
  • [1] Enhancing Historical Extended Reality Experiences: Prompt Engineering Strategies for AI-Generated Dialogue
    Kouzelis, Lazaros Rafail
    Spantidi, Ourania
    APPLIED SCIENCES-BASEL, 2024, 14 (15):
  • [2] Meta-prompt Engineering in ChatGPT-4 for AI-Generated BPM Reference Models
    Piller, Christoph
    SUBJECT-ORIENTED BUSINESS PROCESS MANAGEMENT: MODELS FOR DESIGNING DIGITAL TRANSFORMATIONS, S-BPM ONE 2024, 2025, 2206 : 315 - 331
  • [3] Optimizing Mobile-Edge AI-Generated Everything (AIGX) Services by Prompt Engineering: Fundamental, Framework, and Case Study
    Liu, Yinqiu
    Du, Hongyang
    Niyato, Dusit
    Kang, Jiawen
    Cui, Shuguang
    Shen, Xuemin
    Zhang, Ping
    IEEE NETWORK, 2024, 38 (05): : 220 - 228