A study called ‘How Complex Systems Engage in Fashion Design Creation: Using Artificial Intelligence,’ which was published in the magazine Thinking skills and creativity, aims to explore the practical applicability of AI models for implementing creative fashion design and working with human designers.
The research notes that the use of artificial intelligence in the fashion industry has grown significantly in recent years. For example, it is already being used to personalize fashion recommendations for customers, optimize supply chain management, automate processes and improve sustainability to reduce waste.
However, creative processes in fashion design are still driven by people with little research on how to use AI for fashion design, and the designers themselves are often not involved in the research itself.
Assistant professor and lead author of the study, Yoon Kyung Lee, wanted to find out if there could be effective collaboration between humans and artificial intelligence for the purpose of creative design, and explained, “At a time when artificial intelligence is so deeply embedded in our lives, this study is instead it began by considering what humans can do better than artificial intelligence.”
The study began by generating new textile designs using deep convolution generative adversarial networks (DC-GANs) and cycling GANs. The results of those models were then compared to similar designs made by design students.
The comparison revealed that the designs created by both were similar, but the biggest difference was the uniqueness and originality seen in the human designs, which came from the person’s experiences.
However, using artificial intelligence in repetitive tasks could improve designers’ efficiency and free up their time to focus on very difficult creative work.
The research also suggests that AI-generated designs could be used as a learning tool for people who have no expertise in fashion but want to explore their creativity as AI could help them create their own designs.
Following the study’s findings, Professor Lee is now proposing a human-artificial intelligence collaboration network that integrates GANs with human creativity to produce designs.
Professor Lee also defined and studied the various elements of a complex system involved in human-artificial intelligence collaborative design and established a human-artificial intelligence model in which a designer collaborates with an artificial intelligence to create a new design idea.
The model allows the designer to share his creative process and ideas with others, and the system can be interconnected and evolve to improve his design.
Professor Lee believes the fashion industry can use this to anticipate changes in the fashion industry and offer recommendations and co-creation services. Setting x-goals, variables and constraints is part of a designer’s job in a human-AI collaborative design environment, so she suggests their work should go beyond the visual aspect and instead cover different disciplines.
She concludes: “In the future, everyone will be able to be a creator or designer with the help of AI models. Until now, only professional fashion designers could design and display clothes. But in the future, it will be possible for everyone to design the clothes they want and show their creativity.”