Abstract
This study aims to explore the feasibility and practical application of Artificial Intelligence Generated Content (AIGC) in Mandala-based art therapy, specifically assessing the comparative therapeutic effects of traditional versus AI-generated Mandala patterns on emotional regulations. It also examines differences in therapeutic outcomes across personality types. A total of 53 university students participated in the experiment. Followingapre-testthatincludedapersonalityassessment, participants were randomly assigned to either a Traditional Group or an AI Group. The Traditional Group engaged with Mandala patterns sourced from existing materials, while the AI Group colored images generated by a Stable Diffusion model fine-tuned with LoRA. The experiment consisted of three phases: resting state, anxiety induction, and coloring intervention. Throughout the process, both subjective anxiety scores and physiological indicators were recorded. The results showed that AI- generated Mandala patterns were comparable to traditional patterns in reducing anxiety, indicating that AIGC has potential in art therapy. Furthermore, the study suggests that AIGC not only expands the visual language of Mandala design but also enhances the personalization and scal ability of therapeutic interventions. These findings contribute to emerging discussions on digital Mandala therapy and the evolving role of the therapist, offering new directions for mental health intervention and design practice.
Keywords
Mandalaarttherapy; AIGC; Psychophysiologicalassessment; Personalitytypes
DOI
https://doi.org/10.21606/iasdr.2025.509
Citation
Lin, X., Gong, H., University, A., Xiao, Y., Peng, Y., University, A.,and Li, S.(2025) Design Research and Exploration of Mandala Art Therapy Intervention Based on AIGC, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.509
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Conference Track
Track 4 - Human-Centered AI
Design Research and Exploration of Mandala Art Therapy Intervention Based on AIGC
This study aims to explore the feasibility and practical application of Artificial Intelligence Generated Content (AIGC) in Mandala-based art therapy, specifically assessing the comparative therapeutic effects of traditional versus AI-generated Mandala patterns on emotional regulations. It also examines differences in therapeutic outcomes across personality types. A total of 53 university students participated in the experiment. Followingapre-testthatincludedapersonalityassessment, participants were randomly assigned to either a Traditional Group or an AI Group. The Traditional Group engaged with Mandala patterns sourced from existing materials, while the AI Group colored images generated by a Stable Diffusion model fine-tuned with LoRA. The experiment consisted of three phases: resting state, anxiety induction, and coloring intervention. Throughout the process, both subjective anxiety scores and physiological indicators were recorded. The results showed that AI- generated Mandala patterns were comparable to traditional patterns in reducing anxiety, indicating that AIGC has potential in art therapy. Furthermore, the study suggests that AIGC not only expands the visual language of Mandala design but also enhances the personalization and scal ability of therapeutic interventions. These findings contribute to emerging discussions on digital Mandala therapy and the evolving role of the therapist, offering new directions for mental health intervention and design practice.