Abstract
AI holds transformative potential, and researchers have explored it from various perspectives in hopes of improving design efficiency and quality. its current applications are often limited to automating repetitive tasks, rather than being treated as collaborative partners for designers of co-creating inspiration and value. This oversight has triggered a critical gap: the lack of a new cognitive framework for design practice to reconcile human creativity with design efficiency assisted by AI. This study adopts a workflow and task-oriented perspective to examine how designers currently engage with AI technologies. Drawing on formative research, we identified designers’ practical needs and usage patterns, and from these insights, we developed a three-phase design framework: "Demand Exploration - Generative Creation - Optimized Evaluation". Based on this framework, we designed an intelligent design system, "FASHIONODE", which deconstructs traditional workflows into modular components and introduces on-demand recombination, enabling designers to generate more creative and adaptive design solutions. Through a user study involving 20 designers, we validated the effectiveness of FASHIONODE across multiple dimensions (Exploration, Intent Expression, Matching, Visualization, Satisfaction, Application and Utility). In addition, analysis of semi-structured interviews revealed that FASHIONODE encouraged designers to reflect on their evolving roles and provided a viable case reference for rethinking design workflows in the context of emerging technologies.
Keywords
Generation ai; Design process; Human-ai collaboration; Designer
DOI
https://doi.org/10.21606/iasdr.2025.920
Citation
Ma, R.,and Xiao, Y.(2025) FASHIONODE: Reinventing the Design Practice Framework for Intelligent Fashion Design through Node-based Modules, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.920
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Track 4 - Human-Centered AI
FASHIONODE: Reinventing the Design Practice Framework for Intelligent Fashion Design through Node-based Modules
AI holds transformative potential, and researchers have explored it from various perspectives in hopes of improving design efficiency and quality. its current applications are often limited to automating repetitive tasks, rather than being treated as collaborative partners for designers of co-creating inspiration and value. This oversight has triggered a critical gap: the lack of a new cognitive framework for design practice to reconcile human creativity with design efficiency assisted by AI. This study adopts a workflow and task-oriented perspective to examine how designers currently engage with AI technologies. Drawing on formative research, we identified designers’ practical needs and usage patterns, and from these insights, we developed a three-phase design framework: "Demand Exploration - Generative Creation - Optimized Evaluation". Based on this framework, we designed an intelligent design system, "FASHIONODE", which deconstructs traditional workflows into modular components and introduces on-demand recombination, enabling designers to generate more creative and adaptive design solutions. Through a user study involving 20 designers, we validated the effectiveness of FASHIONODE across multiple dimensions (Exploration, Intent Expression, Matching, Visualization, Satisfaction, Application and Utility). In addition, analysis of semi-structured interviews revealed that FASHIONODE encouraged designers to reflect on their evolving roles and provided a viable case reference for rethinking design workflows in the context of emerging technologies.