A Manufacturing-Oriented Diffusion Framework for Generative Product Design with Traditional Cultural Resources
DOI:
https://doi.org/10.4108/eetsis.14571Keywords:
Diffusion Model, Generative Design, Intelligent Manufacturing, Cultural Resource Transformation, LoRA Fine-tuning, Product DesignAbstract
Traditional cultural resources contain rich symbolic and visual knowledge but remain difficult to incorporate into manufacturing-oriented generative design workflows because cultural semantics, visual characteristics, and pro-duction requirements are often represented separately. This study presents a manufacturing-oriented generative de-sign framework that integrates traceable cultural-resource preparation, structured cultural and manufacturing de-scriptions, and LoRA-based adaptation of Stable Diffusion XL (SDXL). A candidate cultural-resource inventory is examined through metadata auditing, while ResNet-50 features are used to characterize visual representations and to investigate the sensitivity of image features to common augmentation operations. Cultural semantic requirements and manufacturing-oriented requirements are organized as structured generation conditions for product-concept synthesis. In addition, a design-stage assessment framework is formulated in terms of structural feasibility, process compatibility, material adaptability, and visual consistency. Comparative experiments across four generation set-tings further indicate that the proposed framework achieves better performance in cultural consistency, design adaptability, constraint satisfaction, and expert-rated manufacturing feasibility. Although the current evaluation remains at the design stage rather than physical manufacturing validation, the proposed workflow provides a repro-ducible basis for connecting traditional cultural resources with manufacturing-oriented generative product design.
References
[1] J. Wang, Y. Ma, L. Zhang, et al., “Deep learning for smart manufacturing: Methods and applications,” Journal of Manufacturing Systems, vol. 48, pp. 144–156, 2018, doi: 10.1016/j.jmsy.2018.01.003.
[2] F. Tao, J. Cheng, Q. Qi, et al., “Digital twin-driven product design, manufacturing and service with big data,” International Journal of Advanced Manufacturing Technology, vol. 94, pp. 3563–3576, 2018, doi: 10.1007/s00170-017-0233-1.
[3] E. Stylianidis and F. Remondino, Eds., 3D Recording, Documentation and Management of Cultural Heritage. Caithness, Scotland: Whittles Publishing, 2016.
[4] J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 6840–6851.
[5] R. Rombach, A. Blattmann, D. Lorenz, et al., “High-resolution image synthesis with latent diffusion models,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2022, pp. 10684–10695, doi: 10.1109/CVPR52688.2022.01042.
[6] G. La Rocca, “Knowledge based engineering: Between AI and CAD. Review of a language based technology to support engineering design,” Advanced Engineering Informatics, vol. 26, no. 2, pp. 159–179, 2012, doi: 10.1016/j.aei.2012.02.002.
[7] J. S. Gero, “Computational models of creative designing based on situated cognition,” in Proc. 4th Conf. Creativity and Cognition, 2002, pp. 3–10, doi: 10.1145/581710.581712.
[8] Gal R., Alaluf Y., Atzmon Y., Patashnik O., Bermano A. H., Chechik G., Cohen-Or D. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. arXiv preprint arXiv:2208.01618, 2022.
[9] Ruiz N., Li Y., Jampani V., Pritch Y., Rubinstein M., Aberman K. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 22500–22510.
[10] Podell D., English Z., Lacey K., Blattmann A., Dockhorn T., Müller J., Penna J., Rombach R. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv preprint arXiv:2307.01952, 2023.
[11] Ye H., Zhang J., Liu S., Han X., Yang W. IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models. arXiv preprint arXiv:2308.06721, 2023.
[12] Zhang L., Rao A., Agrawala M. Adding Conditional Control to Text-to-Image Diffusion Models. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 3836–3847.
[13] Hessel J., Holtzman A., Forbes M., Le Bras R., Choi Y. CLIPScore: A Reference-free Evaluation Metric for Image Captioning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021, pp. 7514–7528.
[14] K. He, X. Zhang, S. Ren, et al., “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
[15] Koonce B. ResNet 50[M]//Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization. Berkeley, CA: Apress, 2021: 63-72.
[16] A. Radford, J. W. Kim, C. Hallacy, et al., “Learning transferable visual models from natural language supervision,” in Proc. 38th International Conference on Machine Learning, vol. 139, 2021, pp. 8748–8763.
[17] A. Chakrabarti, Ed., Engineering Design Synthesis: Understanding, Approaches and Tools. London, U.K.: Springer, 2002, doi: 10.1007/978-1-4471-3717-7.
[18] K. Krippendorff, The Semantic Turn: A New Foundation for Design. Boca Raton, FL, USA: CRC Press, 2006, doi: 10.1201/9780203299951.
[19] E. J. Hu, Y. Shen, P. Wallis, et al., “LoRA: Low-rank adaptation of large language models,” in International Conference on Learning Representations (ICLR), 2022.
[20] E. S. Abdelall, L. Alawneh, and M. Eldakroury, “A manufacturability-based assessment and design modification support tool,” Journal of Applied Research and Technology, vol. 18, no. 6, pp. 410–424, 2020, doi: 10.22201/icat.24486736e.2020.18.6.1366.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yingru Ji, Jing Wu
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
