Work

Application of dunhuang caisson patterns in cultural and creative product design based on artificial intelligence generated content technology

Year: 2026

Type: article

Abstract: In recent years, the rapid development of Artificial Intelligence Generated Content (AIGC) has opened new technological pathways for the digital preservation creative reinvention of traditional patterns. This study focuses on the Dunhuang caisson pattern, exploring its creative reproduction under AIGC assistance and its application in cultural and creative product design. First, the analytic hierarchy process (AHP) is employed to construct an evaluation system for Dunhuang caisson patterns, ranking key motifs such as the lotus and flower by their relative importance. Based on these results, representative patterns are collected and preprocessed from published books, academic literature, and open-source datasets to build a data set. Subsequently, three mainstream image generation models (Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), and Flux) were fine-tuned using Low-Rank Adaptation (LoRA) based on the Dunhuang caisson dataset. The fine-tuned models are evaluated in terms of pattern generation quality and cultural symbol representation. Finally, four representative cultural and creative products (mugs, carpets, tote bags, and cushions) are designed using the generated patterns. The mug design was further examined through Importance–Performance Analysis (IPA), thereby validating the practical feasibility and expressive effectiveness of the generated outputs. This study not only enhances the automated generation quality of Dunhuang caisson patterns but also provides a transferable technical framework for the digital preservation and innovative utilization of traditional patterns in product design.

Source: Engineering Applications of Artificial Intelligence

DOI: 10.1016/j.engappai.2026.114816