A Product’s Kansei Appearance Design Method Based on Conditional-Controlled AI Image Generation

Abstract

Accurately grasping users’ Kansei needs and rapidly transforming them into product design solutions are key factors in enhancing product competitiveness and sustainability. This paper proposes a product appearance design method based on Kansei engineering and AI image generation technology, integrating other approaches, with household indoor hydroponics as the research subject. First, the web crawler is used to obtain product image samples and user online reviews, and factor analysis (FA) is applied to quickly extract users’ Kansei needs. Second, product morphology is used to deconstruct and encode product appearances. Partial least squares regression (PLSR) is then employed to map and quantify the relationships between Kansei needs and design elements, yielding optimal design solutions and one-dimensional sketches. These sketches are subsequently used as controlled conditions in Stable Diffusion (SD), combined with a team-trained Lora model, to generate two-dimensional colored sketches in batches. Finally, evaluations verify that the generated design solutions are satisfactory and meet users’ Kansei needs. The results indicate that the proposed product appearance design method not only holds significant implications for the sustainable development of Kansei engineering in product design but also greatly enhances the efficiency of the design process, providing new insights into integrating new technologies and scientific research methods in the field of product design.