{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T14:19:38Z","timestamp":1774361978174,"version":"3.50.1"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643684888","type":"print"},{"value":"9781643684895","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,2,7]]},"abstract":"<jats:p>Thanks to the massive data training and large base models, content generation based on artificial intelligence technology is booming. Text-to-image (T2I) systems have powerful semantic understanding and aesthetic perception capabilities, creating significant impacts on improving design efficiency and transforming design ecology. Although large-scale AI models already possess efficient multidimensional combination creation abilities, meeting most daily conceptual design requirements, there are still shortcomings when dealing with professional niche concepts, especially non-Western cultural elements. This paper takes Chinese Jingchu patterns as an example and points out the limitations of existing English-based T2I systems in describing sparse concepts and expressing non-Western cultures. Although re-adding large amounts of data and finetuning may solve some problems, the training skills and computing power required are generally not feasible for most designers. Therefore, this study aims to explore the application strategies of non-finetuned T2I systems in the design of Chinese Jingchu pattern cultural and creative products. We designed three methods: image caption-assisted text-to-image, multi-modal prompt, and text-to-image and image blending, and analyzed their characteristics in terms of Texture Fidelity, Product Accuracy, Image Aesthetics, Product Diversity, and Texture Diversity through user evaluation. Finally, we summarize the applicable scenarios and usage suggestions of the three methods.<\/jats:p>","DOI":"10.3233\/faia231487","type":"book-chapter","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T14:29:41Z","timestamp":1707488981000},"source":"Crossref","is-referenced-by-count":1,"title":["Designing Cultural and Creative Products of Chinese Jingchu Patterns Based on Non-Finetuned Text-to-Image Systems"],"prefix":"10.3233","author":[{"given":"Yijin","family":"Wang","sequence":"first","affiliation":[{"name":"China University of Geosciences School of Arts and Communication"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Design Studies and Intelligence Engineering"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA231487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T14:29:42Z","timestamp":1707488982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA231487"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,7]]},"ISBN":["9781643684888","9781643684895"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia231487","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,7]]}}}