Exploring the Hidden Layers of Image Synthesis through Material-Driven Design Workshops with Fashion and Textile Practitioners

Abstract

Creative work with generative image models is typically mediated through prompts, often requiring designers to translate visual and material intentions into words. Such translation can have a constraining effect on creative tasks in visual domains such as fashion and textile design. To understand how designers make sense of the material of AI based on its interpretable properties, we let users interact with the technology by manipulating the neurons that lie in its hidden layers. In two material-driven design workshops, we introduced fashion and textile practitioners to the technical material properties of a model trained to generate fashion imagery. We found that the interaction leads to new forms of material experiences by offering a gateway into AI's otherwise implicit functioning and discuss the how thinking hidden layers might support intuitive rather than interpretative control when designing with AI, leading to more active material experiences.