Penerapan Metode Stable Diffusion Dengan Fine Tuning Untuk Pola Endek Bali

  • Ni Luh Wiwik Sri Rahayu Ginantra Institut Bisnis dan Teknologi Indonesia https://orcid.org/0000-0003-3731-5981
  • Theresia Hendrawati Institut Bisnis dan Teknologi Indonesia
  • Dewa Ayu Putri Wulandari Institut Bisnis dan Teknologi Indonesia
Keywords: Endek Bali, Stable Diffusion, Fine Tuning

Abstract

Endek Bali fabric is a cultural heritage of Bali renowned for its traditional decorative motifs, including floral, fauna, patra, and diamond patterns. Although rich in cultural value, artisans often face challenges in creating new designs that align with market trends while preserving cultural authenticity. Artificial Intelligence (AI) technology, particularly text-to-image generation models, offers a solution to this issue by streamlining the design process and enabling the exploration of new motifs. The Stable Diffusion model, introduced by Stability.AI in 2022 and open source, can be utilized to generate Endek Bali patterns through Fine Tuning techniques. Fine Tuning allows the model to be adapted to specific domains, enhancing its performance in generating textile patterns based on textual descriptions. This study aims to apply the Stable Diffusion model and Fine Tuning techniques to create new patterns and motifs. By using this model, it is hoped that innovative designs can be produced while maintaining the authenticity and local cultural values of Bali. The research demonstrates that the Fine-Tuned Stable Diffusion model is effective in creating Endek Bali patterns with high accuracy, as evaluated by Clip Similarity, with the highest scores achieved for Floral Patterns (92.43), followed by Decorative (free-form motifs) Floral (88.77), Decorative (free-form motifs) Geometric (87.94), and Decorative (free-form motifs) (85.79). These findings indicate the model’s flexibility and effectiveness in producing intricate textile designs, enabling designers and artisans to generate complex and innovative patterns solely from textual descriptions while preserving Bali’s cultural values.

Downloads

Download data is not yet available.

References

G. Ayu, M. Dewi, W. Ardika, and N. Sunarta, “KREASI IKAT ENDEK SEBAGAI PRODUK PENUNJANG PARIWISATA BALI,” 2019.

D. W. Kariodimedjo, B. C. Rotua, and M. J. Jordi, “Pelindungan Dan Pemajuan Pengetahuan Tradisional Dan Ekspresi Budaya Tradisional Indonesia : Penggunaan Tenun Endek Bali Oleh Christian Dior,” Jurnal IUS Kajian Hukum dan Keadilan, vol. 10, no. 1, pp. 78–97, Apr. 2022, doi: 10.29303/ius.v10i1.1002.

N. M. Ariani, “PENGEMBANGAN KAIN ENDEK SEBAGAI PRODUK PENUNJANG PARIWISATA BUDAYA DI BALI,” Jurnal Ilmiah Hospitality Management, vol. 9, no. 2, pp. 146–159, Jun. 2019, doi: 10.22334/jihm.v9i2.154.

N. Dewi Pebryani, P. Manik Prihatini, and T. C. Istri Ratna, “PENGUATAN DAN PEMAJUAN PEMBELAJARAN MOTIF TENUN ENDEK BALI.”

N. K. Widyawati, “PERKEMBANGAN MOTIF KAIN TENUN ENDEK BERBASIS BUDAYA BALI PADA PERTENUNAN IKAT WISNU MURTI DI DESA KERAMAS, BLAHBATUH, GIANYAR,” Oct. 2023.

E. Suryokta, W. Taruklimbong, and H. Sihotang, “Peluang dan Tantangan Penggunaan AI (Artificial Intelligence) dalam Pembelajaran Kimia.”

M. Muhaemin, “Analisis Pemanfaatan Artificial Intelligence (AI) sebagai Referensi dalam Desain Komunikasi Visual,” Jurnal SASAK : Desain Visual dan Komunikasi, vol. 5, no. 1, pp. 71–80, Jun. 2023, doi: 10.30812/sasak.v5i1.2966.

E. Yıldırım, “Text-to-Image Artificial Intelligence in a Basic Design Studio: Spatialization From Novel,” 2022. [Online]. Available: https://www.researchgate.net/publication/366920915

T. Zhang, Z. Wang, J. Huang, M. M. Tasnim, and W. Shi, “A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions,” Aug. 2023, [Online]. Available: http://arxiv.org/abs/2308.13142

O. Ovadia, M. Brief, M. Mishaeli, and O. Elisha, “Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs,” Dec. 2023, [Online]. Available: http://arxiv.org/abs/2312.05934

H. Faruk Karagoz, G. Baykal, I. Arikan Eksi, and G. Unal, “International Textile & Fashion Congress Innovative textiles and fashion trends tackling global challenges Textile Pattern Generation Using Diffusion Models.”

S. M, G. S, M. Reni, M. M, and R. M. S, “IMAGE GENERATION WITH STABLE DIFFUSION AI,” IJARCCE, vol. 12, no. 5, Apr. 2023, doi: 10.17148/ijarcce.2023.125106.

A. Borji, “Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2,” Oct. 2022, [Online]. Available: http://arxiv.org/abs/2210.00586

H. Ma and H. Zheng, “Text Semantics to Image Generation: A Method of Building Facades Design Base on Stable Diffusion Model,” in Computational Design and Robotic Fabrication, vol. Part F2072, Springer, 2024, pp. 24–34. doi: 10.1007/978-981-99-8405-3_3.

A. M. Simarmata, A. Zizwan Putra, and A. Mahmud Husein, “Penerapan Metode Computer Vision Dalam Klasifikasi Buah Jeruk Menggunakan Teknik Image Pre-Processing,” vol. 3, no. 2, doi: 10.47709/dsi.v3i2.4010.

A. Colmenero-Fernandez, “Exploring historical conceptualization of AI Stable Diffusion Model with prompt engineering techniques,” 2023, doi: 10.22541/au.167907565.50467808/v1.

N. Dehouche and K. Dehouche, “What’s in a Text-to-Image Prompt? The Potential of Stable Diffusion in Visual Arts Education.”

Z. Han, C. Gao, J. Liu, J. Zhang, and S. Q. Zhang, “Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey,” Mar. 2024, [Online]. Available: http://arxiv.org/abs/2403.14608

Amanatullah, “Fine-Tuning the Model: What, Why, and How,” https://medium.com/@amanatulla1606/fine-tuning-the-model-what-why-and-how-e7fa52bc8ddf.

R. Al Rasyid, D. Handayani, and U. Ningsih, “Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata,” Jurnal Teknologi Informasi dan Komunikasi), vol. 8, no. 1, p. 2024, 2024, doi: 10.35870/jti.

Published
2024-11-05
How to Cite
Ginantra, N. L. W. S. R., Hendrawati, T., & Wulandari, D. A. P. (2024). Penerapan Metode Stable Diffusion Dengan Fine Tuning Untuk Pola Endek Bali . TEMATIK, 11(2), 141 - 147. https://doi.org/10.38204/tematik.v11i2.2069