{"title":"From prompting to attribute-based interaction: a taxonomy-driven framework for fashion image generation","authors":"Lidiia Khleborodova, Eung Tae Kim","doi":"10.1186/s40691-026-00477-8","DOIUrl":"10.1186/s40691-026-00477-8","url":null,"abstract":"<div><p>Translating abstract design intent into text-based prompts presents a practical barrier in generative AI–mediated design, particularly for novice users who lack stable design vocabulary. This study proposes a structured interaction framework that replaces free-form prompting with attribute-based design variable selection, implemented as a web-based fashion image generation system. The system organizes six core fashion design attributes into a taxonomy-driven variable space and converts user selections into prompts through a rule-based translation pipeline. To examine the proposed framework, the study combined exploratory image-generation analysis with a user study. The evaluation investigated whether structured prompt construction could preserve attribute-level interpretability across diffusion-based image generation conditions and how users perceived the interaction structure during fashion ideation tasks. The results suggest that the proposed interaction framework supports relatively stable attribute reflection and enables users to explore design variations through more structured and interpretable interaction processes. The study contributes to human–AI interaction design by demonstrating how domain-specific structure can be embedded into generative AI interaction architectures to reduce reliance on prompt-writing skills and support more transparent relationships between user input and generated output.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2026-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00477-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148323582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A VLM-based framework for evaluating garment consistency in AI-generated images based on DeLong’s theory","authors":"Hyeryeon Park, Bohyun Choi, Yerim Choi","doi":"10.1186/s40691-026-00475-w","DOIUrl":"10.1186/s40691-026-00475-w","url":null,"abstract":"<div><p>The rapid proliferation of AI-generated images in the fashion industry has created a need for systematic evaluation methods to assess garment consistency between original and AI-generated images. Conventional quantitative metrics often fail to capture fine-grained garment attributes, while human evaluation, though accurate, is costly and difficult to scale. This study proposes an automated evaluation method leveraging Vision–Language Models (VLMs) to assess garment consistency in AI-generated images. To enable systematic evaluation, we developed a garment-specific evaluation framework by operationalizing DeLong’s visual definers into 20 attributes, which were embedded into the prompt to guide the VLMs. To validate the proposed method, experiments were conducted using a real-world dataset of original fashion images paired with AI-generated ghost mannequin photography. While traditional quantitative metrics failed to effectively capture garment consistency, the proposed method demonstrated substantial alignment with human evaluation on overall garment consistency. Compared to human evaluation, the proposed method successfully identified inconsistencies across the defined attributes; however, at the attribute level, it showed higher sensitivity to color and texture but lower sensitivity to shape and line dimensions. These findings suggest that VLM-based evaluation can effectively complement existing evaluation methods by providing scalable and theoretically grounded insights.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00475-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148236955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"3D female breasts aging patterns integrating age and BMI for ergonomic fashion design","authors":"Xingzhi Shi, Zixu Cai, Jie Zhang, Yadie Yang","doi":"10.1186/s40691-026-00474-x","DOIUrl":"10.1186/s40691-026-00474-x","url":null,"abstract":"<div><p>Understanding how breast morphology changes with age and body mass index (BMI) is essential for developing ergonomically designed breast-related fashion products that ensure better fit and comfort. However, creating accurate 3D aging models is challenging due to the scarcity of comprehensive data, particularly for specific populations like Chinese women. This paper presents a novel framework for modeling 3D aging patterns in Chinese female breasts by integrating both age and BMI as key variables. We constructed a 3D statistical shape model (SSM) from scans of 305 Chinese women (aged 20–70 years, BMI 16.1–36.9 kg/m<sup>2</sup>) to capture core geometric variations. Moving beyond traditional linear methods, we employed a Gaussian kernel-based locally weighted partial least squares regression (LW-PLSR) to model the complex, nonlinear relationships between demographic and anthropometric factors and breast shape. To our knowledge, this is the first study to generate a 3D breast aging model that explicitly incorporates BMI alongside age for any population. The resulting model accurately captures changes in breast morphology and provides objective, data-driven tools for the fashion and textiles industries. It also offers practical geometric insights to inspire designers, manufacturers, and researchers to advance inclusive fashion design for women across a comprehensive range of ages and body sizes, thereby improving apparel comfort, fit, and functionality.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00474-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148172575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Genetic-programming prediction of solar-radiation reflectance in cotton woven fabrics for UV–Vis-NIR protection","authors":"Polona Dobnik Dubrovski, Tadeja Penko, Miran Brezocnik","doi":"10.1186/s40691-026-00476-9","DOIUrl":"10.1186/s40691-026-00476-9","url":null,"abstract":"<div><p>This study presented a genetic programming (GP) model for predicting solar-radiation reflectance of cotton woven fabrics as protective materials. The influence of three structural parameters, namely, yarn fineness (14, 25, 36 tex), weave type (plain, twill, satin), and relative fabric density (55–85%), was examined on reflectance across the ultraviolet–visible-infrared spectrum within the wavelength range of 210–1200 nm. Experimental measurements were performed on precisely engineered raw cotton woven fabrics with tightly controlled structural parameters, enabling the isolation of the effect of fabric structure. Analysis of variance confirmed that fabric structure had a considerable effect on solar-radiation reflectance across different spectral regions. Three distinct spectral regions in the interaction between solar-radiation reflectance and woven fabrics were identified, each with unique reflectance behaviours and varying dependence on fabric structural parameters. The GP-evolved model achieved high accuracy, with an average deviation of 2.3% from the experimental data and coefficients of determination of 0.985 for the training set and 0.986 for the test set, demonstrating strong robustness and reliability. This study highlighted the model's potential for designing fabrics with enhanced solar-radiation protection. The results contributed to advancing computational fabric modelling and developing functional fabrics with optimised thermal, visible, and ultraviolet performance, reducing the need for extensive experimental testing.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00476-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148172537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Nondestructive quantitative model for predicting the residual tensile strength of silk textile cultural heritage based on machine learning","authors":"Seonghee Pak, Byoungho Ellie Jin, Changsang Yun","doi":"10.1186/s40691-026-00472-z","DOIUrl":"10.1186/s40691-026-00472-z","url":null,"abstract":"<div><p>Silk is susceptible to deterioration induced by light, heat, and moisture, which leads to reduced structural stability and progressive strength loss. However, because destructive analysis is fundamentally unsuitable for silk textile cultural heritage, residual tensile strength is typically inferred through subjective evaluation. This study aims to quantitatively analyze deterioration behavior and examine the feasibility of nondestructive prediction of the residual tensile strength of silk textile cultural heritage by employing indicators that exhibit significant correlations with tensile strength reduction. As indicators of tensile strength, protein secondary structure, pH, moisture regain, yellow index, and K/S value were measured in artificially aged silk textiles. Results showed that tensile strength was not significantly influenced by differences in deterioration environments but correlated with crystallinity and protein secondary structure composition. Although linear regression demonstrated limited explanatory power (R<sup>2</sup> = 0.576), XGBoost demonstrated improved predictive performance (R<sup>2</sup> = 0.654–0.751) by capturing complex multivariate interactions, suggesting the potential for nondestructive estimation of residual tensile strength in textile cultural heritage. The prediction model using crystallinity, protein secondary structure contents, pH, yellow index, and K/S value showed the highest predictive accuracy. Further, with the accumulation of data encompassing textiles with diverse properties and the refinement of relevant indicators, the development of a machine learning–based nondestructive precision prediction model is anticipated. Such an approach can overcome the limitations of subjective assessment and contribute to systematic conservation management through the quantitative prediction of residual tensile strength in textile cultural heritage.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00472-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148009819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Three-dimensional virtual prototyping for designing firefighting gear: an exploration of manufacturer perceptions","authors":"Uikyung Jung, Anne Porterfield, Cassandra Kwon","doi":"10.1186/s40691-026-00469-8","DOIUrl":"10.1186/s40691-026-00469-8","url":null,"abstract":"<div><p>Guided by the Technology-Organization-Environment (TOE) framework, this study explores how firefighting gear manufacturers perceive 3D apparel visualization software and how these perceptions shape their intentions to adopt the technology. Semi-structured interviews were conducted with 12 experts from six companies producing wildland and structural turnout gear, including pattern makers, designers, technical designers, and a business manager. Content analysis revealed that manufacturers viewed 3D apparel visualization software as a useful tool for pattern optimization, visualizing air gaps, and improving communication with municipal customers. However, participants also highlighted significant technical limitations, particularly in simulating composite materials, multilayer garment structures, and substantial ease and air gap behavior in structural turnout gear. They also noted constraints related to organizational slack, including financial and human resource demands and disruptions to established workflows. Adoption decisions were further shaped by key industry characteristics, such as stringent National Fire Protection Association (NFPA) standards, unchanging garment style requirements, conservative industry norms, and varying levels of business partner readiness. The findings extend TOE research to a specialized functional clothing context by highlighting sector-specific constraints and the importance of distinguishing between current capabilities and perceived future value. Practical implications are offered for software developers, regulators, and manufacturers seeking to align digital design investments with the technological and regulatory realities of firefighting gear innovation.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00469-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147937815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Addressing hamstring muscle soreness in female NCAA athletes: design and evaluation of a user-centered compression sleeve for recovery","authors":"Sarah Megivern, Adriana Gorea","doi":"10.1186/s40691-026-00471-0","DOIUrl":"10.1186/s40691-026-00471-0","url":null,"abstract":"<div><p>Compression garments are used by athletes for post-exercise recovery and injury prevention, yet their effectiveness depends on the interaction between textile properties, garment construction, and user-specific biomechanics. Despite growing participation of women in collegiate sports, few studies have examined recovery-focused compression engineered specifically for female athletes. This pilot investigation combined user-centered design methodology with textile performance testing to develop and evaluate a hamstring compression sleeve for female NCAA athletes. Survey data from competitive athletes (N = 34) identified durability, stretch, and thermal comfort as primary design priorities. Five candidate fabrics were evaluated for thickness, mass, elongation, and air permeability, leading to selection of a spacer knit fabric that provided high extensibility with sufficient stability for localized compression. A prototype sleeve incorporating elastomeric striping aligned with hamstring musculature was produced and evaluated during four repeated sprint testing sessions with NCAA athletes (N = 8). Functional performance measures included isometric strength, jump performance, and power output, alongside perceived soreness and wearability assessments. No statistically significant differences were detected between the compression and control limbs across biomechanical performance variables. However, participants consistently reported positive perceptions related to comfort, usability, and recovery support. These findings suggest that perceived benefits of compression garments may not always be reflected into short-term performance metrics, but remain relevant to athlete experience. The study demonstrates the feasibility of integrating textile engineering, garment design, and athlete feedback within a single development process and provides a framework for future optimization of compression systems tailored to female athletic populations.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00471-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147937816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Zero-waste shirt pattern creation with size development: evaluation of appearance, comfort, and purchase intention","authors":"KyoungOk Kim, Tomoyuki Furuno, Masayuki Takatera","doi":"10.1186/s40691-026-00458-x","DOIUrl":"10.1186/s40691-026-00458-x","url":null,"abstract":"<div><p>This study introduces a novel approach for producing zero-waste dress shirts (ZWSs) through size development by proposing a method that transforms a base pattern into a rectangle, effectively reducing fabric waste while maintaining garment functionality. To minimize fabric waste, we developed ZWSs by marking a graded conventional shirt pattern within a rectangle that has a large seam allowance. Moreover, we proposed a sewing method for handling the large seam allowance. The produced ZWSs were evaluated against conventional shirts for appearance, comfort, satisfaction, and purchase intention. In addition, we investigated the difference between consumer evaluations before and after explaining zero-waste fashion design. Although the ZWSs were slightly more wrinkled than the conventional shirts, their overall appearance was comparable. At the same time, the method successfully achieved zero waste. In terms of comfort, ZWSs required more ease allowance around curved areas like the neck and armholes owing to the stiffness of the seam allowance. This could be addressed using thin fabric. Although the ZWSs initially scored lower in comfort and satisfaction, their overall satisfaction and purchase intention improved when participants were informed about their zero-waste design. This highlights the importance of consumer awareness of sustainable practices in increasing the acceptance and appeal of zero-waste fashion design.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00458-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147937963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"AI-driven wearable smart textiles: a review of research trends and frontiers","authors":"Yunjun Wan","doi":"10.1186/s40691-026-00470-1","DOIUrl":"10.1186/s40691-026-00470-1","url":null,"abstract":"<div><p>The integration of Artificial Intelligence (AI) with wearable smart textiles is transforming passive fabrics into active systems capable of sensing, responding, and adapting to environmental and user-specific stimuli. Despite growing interest, a comprehensive quantitative analysis of this interdisciplinary field remains lacking. This study conducts a bibliometric and visual analysis of publications from 2000 to 2025 from the Web of Science (WoS) Core Collection, utilizing Visualization of Similarities viewer (VOSviewer), CiteSpace, and Bibliometrix to examine publication trends, collaboration networks, thematic evolution, and intellectual structures. Results indicate rapid growth in publications, with China, the United States, and South Korea leading a highly collaborative international network. The field exhibits strong interdisciplinary connections among materials science, nanotechnology, electronic engineering, and AI-based data analytics. Key research themes include fiber-based nanogenerators, while emerging trends focus on AI-sensor integration, sustainable materials, and multifunctional applications. This study constructs a knowledge framework and identifies future directions such as AI algorithm miniaturization, self-powered sensing, eco-friendly material industrialization, and deeper scenario-based applications. These findings address the gap in macro-level analysis and offer strategic guidance to advance research and innovation in AI-enhanced wearable smart textiles.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00470-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147829616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Beyond production: a review of use-phase environmental impacts in apparel life cycle assessment (LCA)","authors":"Kyungha Baik, Suhyun Lee","doi":"10.1186/s40691-026-00468-9","DOIUrl":"10.1186/s40691-026-00468-9","url":null,"abstract":"<div><p>Clothing involves a complex production process and long-term usage, during which garments undergo repeated maintenance. Consequently, the use-phase plays a critical role in assessing the overall environmental impacts of apparel. While life cycle assessment (LCA) is widely applied in the fashion and textile industry, many studies prioritize cradle-to-gate stages. This review highlights two key aspects. First, it establishes the importance of the use-phase within the entire life cycle. Second, it delves into a detailed analysis of the use-phase, examining major elements affecting environmental burdens, including garment lifespan, washing frequency, drying method, and regional differences. The use-phase often accounts for the second-highest environmental impact after production, and in certain cases, represents the most significant contributor. Extending garment lifespan is a highly effective strategy for mitigating overall impacts by avoiding the need for new production. Washing frequency and the choice between machine and air drying are also confirmed as important factors. Regional differences, which include consumer behavior and the carbon intensity of electricity grids, lead to substantial differences in use-phase impacts. In summary, this review highlights the central role of the use-phase in apparel LCA and emphasizes its key factors. While extensive LCA studies have focused on washing and drying processes, other common practices such as ironing and dry cleaning have received limited academic attention. This oversight constitutes a notable gap in the current literature, suggesting a need for further research to achieve a comprehensive understanding of the environmental impacts of apparel.</p></div>","PeriodicalId":555,"journal":{"name":"Fashion and Textiles","volume":"13 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s40691-026-00468-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147642697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}