Product Family Formal Design Based on Brand DNA Extraction by AIGC Technology

Contemporary brands increasingly emphasize the unification of design elements to enhance brand image consistency. With the advancement of artificial intelligence, AIGC (Artificial Intelligence Generated Content) technology has been widely applied in the modern design industry. Although existing studies acknowledge the capability of AIGC technology in capturing and preserving brand characteristics, current research has two limitations. Most models rely on machine annotation, and little research addresses how design DNA transfers across different product categories within the same brand using this technology. This study proposes an AIGC-assisted approach for brand product family formal design, aiming to improve the design efficiency and innovation of brand products while maintaining brand consistency across multiple product categories. Through multi-dimensional analysis, design matrix analysis, and fuzzy evaluation methods, this research refines the design DNA of brand product families, providing a theoretical foundation for the subsequent AIGC model training and application. Additionally, based on the Stable Diffusion platform, this study conducts a comparative analysis of LoRA models trained with manual annotations versus CLIP-based machine annotations in inheriting design DNA of brand product families. Research findings suggest that AIGC technology effectively enhances the inheritance of brand attributes across product categories. While both annotation methods demonstrate effectiveness in preserving brand design coherence within ControlNet constraints, the manually labeled LoRA model outperforms its machine-labeled counterpart in representing design elements. This research establishes an innovative approach to brand product design, demonstrating AIGC technology’s practical value in maintaining brand consistency while fostering design innovation.