🤖 AI Summary
This study addresses the limitations of traditional Ulos textile patterns—restricted variety and time-intensive design—which hinder the balance between cultural preservation and contemporary innovation. For the first time, the authors apply fine-tuned latent diffusion models to generate authentic Batak Ulos motifs from Indonesia, optimizing Protogen v3.4 and Stable Diffusion v1.4 on a high-quality dataset. Experimental results demonstrate that Protogen v3.4 substantially outperforms Stable Diffusion v1.4, achieving approximately a 10.5-fold reduction in FID and a two-fold increase in Inception Score. A guidance scale between 5 and 9 emerges as optimal, effectively balancing cultural fidelity with pattern diversity. This work not only enables creative regeneration while preserving cultural symbolism but also systematically elucidates how generation parameters influence the trade-off between fidelity and diversity.
📝 Abstract
Preserving and revitalising traditional textiles such as Ulos, a cultural heritage of the Batak ethnic group in North Sumatra, Indonesia, requires balancing fidelity to tradition with innovative approaches that meet contemporary design demands. Traditional Ulos weaving faces two key limitations: a narrow range of motifs and a time-intensive design process. This study presents a generative AI framework that fine-tunes two pretrained latent diffusion models: Protogen v3.4 and Stable Diffusion v1.4, on a curated, annotated dataset of high-resolution Ulos motifs to generate culturally consistent yet novel designs. Model performance is evaluated quantitatively using Frechet Inception Distance (FID), Inception Score (IS), and qualitatively through assessments by traditional weavers and members of the public. Protogen v3.4 consistently outperforms Stable Diffusion v1.4, achieving substantially lower FID (~10.5x) and higher IS (2.0x), indicating superior visual fidelity, diversity, and closer alignment with the real Ulos motif distribution. We further examine the effects of strength and guidance scale on generation quality across both models. Lower strength values consistently yield higher fidelity (lower FID), while higher strength values increase generative diversity at the cost of realism, revealing a clear fidelity-diversity tradeoff for both models. Across all tested configurations, a guidance scale of 5-9 provides the most effective balance between fidelity and diversity, stabilising FID, KID, and IS, and is recommended as the operating range for high-quality, diverse Ulos motif generation. These findings demonstrate that carefully fine-tuned generative AI can support the creative renewal of intangible cultural heritage while preserving its stylistic and symbolic integrity.