The Impact of AI Text-to-Image Generator on Product Styling Design

被引:4
|
作者
Lee, Yu-Hsu [1 ]
Chiu, Chun-Yao [1 ]
机构
[1] Natl Yunlin Univ Sci & Technol, Touliu 64002, Yunlin, Taiwan
关键词
Image generation; Product Styling Design; Visual Stimuli; Creativity;
D O I
10.1007/978-3-031-35132-7_38
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
AI text-to-image generators have recently been used in a variety of fields, including graphic design, interior design, architectural design, and product design. This study aims to: (1) examine the effect of AI-generated visual stimuli (using Midjourney) on product design. (2) assess designers' acceptability of using AI technology. (3) explore the potential workflow of product designers in the future. Six industrial design students (aged 23-26) with at least four years of design experience were recruited using purposive random sampling. The experimental group used AI-generated visual stimuli from Midjourney, while the control group used visual stimuli searched on Pinterest. The participants performed the same design task twice, once using AI-generated visual stimuli as a reference and once using visual stimuli from an online source. The impact of using the new technology on the design outcome was then observed. Semi-structured interviews were conducted to gather the participants' perceptions regarding the use of AI-generated visual stimuli as design inspiration. The resulting qualitative data was coded for key themes. The results of the interviews showed that AI-generated visual stimuli provide a limited range of variation for the same design task, but also allow for new combinations of text to create new patterns. Its computational characteristics make it almost impossible to duplicate its images, and its uniqueness and ambiguity allows designers to freely extract elements, which is very suitable for the early stage of product design. However, there was no significant difference in the performance of the participants for the different visual stimuli, although design fixation was observed in the sketches generated by both types of visual stimuli, it was less pronounced in the sketches produced using the AI-generated visual stimuli as a reference. AI is likely to be used in various industries in the future. Overall, the participants had a positive attitude of using AI technology in product design and expressed a willingness to try it out.
引用
收藏
页码:502 / 515
页数:14
相关论文
共 50 条
  • [31] Mobile App for Text-to-Image Synthesis
    Kang, Ryan
    Sunil, Athira
    Chen, Min
    [J]. MOBILE COMPUTING, APPLICATIONS, AND SERVICES, MOBICASE 2019, 2019, 290 : 32 - 43
  • [32] Semantics Disentangling for Text-to-Image Generation
    Yin, Guojun
    Liu, Bin
    Sheng, Lu
    Yu, Nenghai
    Wang, Xiaogang
    Shao, Jing
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 2322 - 2331
  • [33] Text-to-Image Generation for Abstract Concepts
    Liao, Jiayi
    Chen, Xu
    Fu, Qiang
    Du, Lun
    He, Xiangnan
    Wang, Xiang
    Han, Shi
    Zhang, Dongmei
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 4, 2024, : 3360 - 3368
  • [34] Holistic Evaluation of Text-to-Image Models
    Lee, Tony
    Yasunaga, Michihiro
    Meng, Chenlin
    Mai, Yifan
    Park, Joon Sung
    Gupta, Agrim
    Zhang, Yunzhi
    Narayanan, Deepak
    Teufel, Hannah Benita
    Bellagente, Marco
    Kang, Minguk
    Park, Taesung
    Leskovec, Jure
    Zhu, Jun-Yan
    Li Fei-Fei
    Wu, Jiajun
    Ermon, Stefano
    Liang, Percy
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [35] Adversarial text-to-image synthesis: A review
    Frolov, Stanislav
    Hinz, Tobias
    Raue, Federico
    Hees, Joern
    Dengel, Andreas
    [J]. NEURAL NETWORKS, 2021, 144 : 187 - 209
  • [36] Optimizing Prompts for Text-to-Image Generation
    Hao, Yaru
    Chi, Zewen
    Dong, Li
    Wei, Furu
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [37] TIGEr: Text-to-Image Grounding for Image Caption Evaluation
    Jiang, Ming
    Huang, Qiuyuan
    Zhang, Lei
    Wang, Xin
    Zhang, Pengchuan
    Gan, Zhe
    Diesner, Jana
    Gao, Jianfeng
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 2141 - 2152
  • [38] Exploring the use of AI text-to-image generation to downregulate negative emotions in an expressive writing application
    Azuaje, Gamar
    Liew, Kongmeng
    Buening, Rebecca
    She, Wan Jou
    Siriaraya, Panote
    Wakamiya, Shoko
    Aramaki, Eiji
    [J]. ROYAL SOCIETY OPEN SCIENCE, 2023, 10 (01):
  • [39] Development and Classification of Image Dataset for Text-to-Image Generation
    Kumar, Munish
    Mittal, Meenakshi
    Singh, Satwinder
    [J]. Journal of The Institution of Engineers (India): Series B, 2024, 105 (04) : 787 - 796
  • [40] 3DALL-E: Integrating Text-to-Image AI in 3D DesignWorkflows
    Liu, Vivian
    Vermeulen, Jo
    Fitzmaurice, George
    Matejka, Justin
    [J]. DESIGNING INTERACTIVE SYSTEMS CONFERENCE, DIS 2023, 2023, : 1955 - 1977