Artificial intelligence's effects on design process creativity: "A study on used A.I. Text-to-Image in architecture"

被引:5
|
作者
Hanafy, Nervana Osama [1 ]
机构
[1] Modern Univ Technol & Informat, Dept Architecture Engn, Mokattam 11571, Egypt
来源
关键词
Artificial intelligence; Image in architecture; Text-to-Image; Natural language processing; Computer vision; MIND;
D O I
10.1016/j.jobe.2023.107999
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The field of artificial intelligence has introduced a groundbreaking process called text-to-image generation, which allows humans to visualize ideas in new ways. This study suggests that architects and designers can utilize these tools in conceptual design to enhance their creativity. AI provides designers with fresh perspectives and opens up new possibilities for design concepts. These tools also allow for easier manipulation of data and the development of innovative solutions to complex problems, expanding the designer's range of creative abilities beyond traditional methods. We are examining the application of usage-based models to different activities, exploring the suitability of DALL-E 2, Midjourney, and StableDi platforms for typical examples in architectural design. By using NLP techniques to extract typical usage patterns from a data collection of 40 million Midjourney inquiries, we can analyze these patterns and how they are currently being used. We examined architectural glossaries to identify keywords related to architecture. We only included keywords that appeared at least 10 % of the time, and the names of 941 famous architects from Wikipedia were added to the keyword list. This allowed us to identify 2.6 million searches (6.8 %) that potentially had an architectural intention, including 1 million (2.6 %) that specifically mentioned "architect", "interior", or "exterior" design. Our filters ensured the accuracy of our findings. Conclusions, the use of technology can greatly enhance the engineering design process. Architects and other creatives find it particularly exciting and useful due to its user-friendly interface and ability to generate a wide range of images.
引用
收藏
页数:17
相关论文
共 4 条
  • [1] Considerations on the use of artificial intelligence in generating anatomical images: Comment on "Evaluating AI-powered text-to-image generators for anatomical illustration: A comparative study"
    Cornwall, Jon
    Krebs, Claudia
    Hildebrandt, Sabine
    Gregory, Jill
    Pennefather, Patrick
    [J]. ANATOMICAL SCIENCES EDUCATION, 2024, 17 (05) : 1097 - 1099
  • [2] How do people experience the images created by generative artificial intelligence? An exploration of people's perceptions, appraisals, and emotions related to a Gen-AI text-to-image model and its creations
    Rapp, Amon
    Di Lodovico, Chiara
    Torrielli, Federico
    Di Caro, Luigi
    [J]. International Journal of Human Computer Studies, 2025, 193
  • [3] I Don't Know, Is AI Also Used in Airbags? An Empirical Study of Folk Concepts and People's Expectations of Current and Future Artificial Intelligence
    Alizadeh F.
    Stevens G.
    Esau M.
    [J]. i-com, 2021, 20 (01): : 3 - 17
  • [4] IMPROVING EFFICIENCY OF LIVING SYSTEMATIC LITERATURE REVIEWS (SLR) WITH ARTIFICIAL INTELLIGENCE (AI): ASSISTED EXTRACTION OF POPULATION, INTERVENTION/COMPARATOR, OUTCOME, AND STUDY DESIGN (P-I/C-O-S)
    Liu, R.
    Jafar, R.
    Girard, L. A.
    Thorlund, K.
    Rizzo, M.
    Forsythe, A.
    [J]. VALUE IN HEALTH, 2023, 26 (12) : S6 - S6