ShoeGenAI: A Creativity Support Tool Bridging Design Intention and Feasibility in Shoe Design

DOI

Product designers increasingly turn to generative AI for creating concept images, but these outputs often fall short in terms of real-world manufacturability and typically require iterative revisions to align with intended designs. Concentrating on sneaker design, we introduce ShoeGenAI, an AI tool that enhances designers' creativity while ensuring feasible outcomes and reducing the need for post-processing. A formative study involving four shoe designers uncovered key limitations in both traditional workflows and current genereative AI tools. These insights guided the development of four core features: fine-tuned models trained on domain-specific data, template-driven prompt assistance, support for hybrid part recombination, and localized editing for detail refinement. A subsequent user study with 20 designers showed that ShoeGenAI enabled clearer communication of design intent, more efficient workflows with less manual correction, and higher satisfaction with the realism and feasibility of the generated outputs. We also explore how professionals and novices differ in their use of creativity support tools, especially across tasks ranging from imitation to original creation.