Enhancing Traditional Batik Design with AI Techniques

This research article presents a study on the application of artificial intelligence in the generation of Bakaran batik motifs, utilizing three versions of the Stable Diffusion algorithm: Version 1.5, Version 2.0, and SDXL. The objective of this study is to explore the capabilities of these algorithms in creating diverse batik motifs, particularly those inspired by nature. The findings indicate that Version 1.5 and SDXL are the most effective models, each offering unique strengths. SDXL is noted for its innovative approach, while Version 1.5 maintains cultural authenticity in traditional designs. The study also highlights the challenges faced by the batik industry, including the loss of traditional motifs due to a decline in interest among younger generations. By integrating generative AI techniques, this research aims to bridge the gap between traditional craftsmanship and modern technological advancements, thereby enhancing productivity and preserving cultural heritage in batik design. The evaluation of the models is conducted using inception and CLIP scores to assess the quality and diversity of generated images.