Integrating Generative AI into Art Therapy: A Technical Showcase

TL;DR

This work addresses the gap at the intersection of generative AI and art therapy by proposing a privacy-preserving, on-device pipeline that augments therapeutic creativity without supplanting clinicians. It features a three-model workflow (edge detection via PiDiNet, a sketch-to-image adapter conditioned by prompts, and inpainting with binary masks) that refines and adapts patient drawings based on textual descriptions, all locally on GPUs. The authors demonstrate proof-of-concept with three illustrative examples, providing qualitative assessments and timing (5–10 seconds per image on an RTX A6000) and discuss ethical, privacy, and efficacy considerations. The study highlights the potential to enhance accessibility and expressiveness in art therapy while outlining concrete future research directions, including virtual platforms, integration with other therapies, and neurocognitive applications; code and implementations are publicly available at the referenced GitHub repository.

Abstract

This paper explores the integration of generative AI into the field of art therapy. Leveraging proven text-to-image models, we introduce a novel technical design to complement art therapy. The resulting AI-based tools shall enable patients to refine and customize their creative work, opening up new avenues of expression and accessibility. Using three illustrative examples, we demonstrate potential outputs of our solution and evaluate them qualitatively. Furthermore, we discuss the current limitations and ethical considerations associated with this integration and provide an outlook into future research efforts. Our implementations are publicly available at https://github.com/BFH-AMI/sds24.

Figures (2)

• Figure 1: Inclusion of generative AI in the art therapy process.
• Figure 2: Example outputs of the employed generative AI models