CONCEPTUAL DESIGN OF REALISTIC FASHION MODELS THROUGH DIGITAL TRANSFORMATION OF GRAPHIC SKETCHES
DOI:
https://doi.org/10.35546/kntu2078-4481.2026.3.10Keywords:
conceptual design, digital transformation, graphic sketch, fashion model, source of creativity, bioform, photorealism, neural network synthesisAbstract
The article examines the innovative process of transforming a creative concept in fashion design from the study of natural morphology to the creation of highly realistic digital objects. The relevance of the research is determined by the need to expand the toolkit of conceptual design in the context of the digital transformation of the fashion industry, where the traditional graphic sketch becomes the basis for the generative synthesis of complex bionic forms. The methodology is based on the use of the “semantic translation” method and prompt engineering, which made it possible to transform abstract conceptual descriptors into specific textural and volumetric-spatial parameters of models using the algorithms of the Look.ai platform. These algorithms ensure the adaptation of complex biomorphic structures to the plasticity of the human body and provide a realistic garment fit.
The research results demonstrate the capability of AI technologies to ensure highly accurate reproduction of complex 3D textures while strictly preserving the author’s silhouette line. It has been proven that the Generate Look mode enables the completion of the conceptual design process through the creation of a holistic artistic context, extrapolating the semantic core of the collection to the entire visual environment.
The scientific novelty and practical significance of the study lie in the development of an algorithmic model of interaction between the designer and neural networks, where the digital transformation of a sketch acts as a method for verifying complex design ideas. For the first time, a method of structural-semantic coding of the creative source for generative fashion design has been proposed, based on the systematization of morphological, sensory, graphic, and emotional descriptors. Unlike existing approaches focused on the random visual intuition of AI, the proposed methodology ensures the preservation of the author’s concept and increases the controllability of the generation process. The implementation of the methodology significantly reduces the time required for searching materials and compositional solutions while ensuring high conceptual integrity and realism of the final product.
References
Zhang, J. (2022). Research on the Application of 3D Virtual Simulation Technology in Fashion Design from the Perspective of Meta Universe. Scientific and Social Research, 4, 19–23. https://doi.org/10.26689/ssr.v4i12.4550
Захаркевич, О., Кошевко, Ю., Ельнашар, Е., Швець, Г., & Селезньова, А. (2023). Впровадження візуального словника з текстилю та моди у мобільний додаток. Herald of Khmelnytskyi National University. Technical Sciences, 321(3), 320-328. https://doi.org/10.31891/2307-5732-2023-321-3-320-328
Slavinska, A., Dombrovska, O., Mytsa, V., & Koshevko, J. (2020). Method of control of the compatibility of the children's clothing design using coefficients of dimensional features gradation. Fibres and Textiles, 27, 76–86.
Slavinska, A., Zakharkevich, O., Kuleshova, S., & Syrotenko, O. (2018). Development of a technology for interactive design of garments using add-ons of a virtual mannequin. Eastern-European Journal of Enterprise Technologies, 6(1(96)), 28-39. doi: 10.15587/1729-4061.2018.148984.
Lu, Z., Guo, J., Liu, S. et al. (2025). Bidirectional feature modulation fusion for fashion design using latent diffusion models. The Visual Computer 41, 8553–8567. https://doi.org/10.1007/s00371-025-03884-y
Lee, J., Kim, J. & Lee, H. Diffusedesigner: sketch-based controllable clothing image generation. Fash Text 12, 26 (2025). https://doi.org/10.1186/s40691-025-00426-x
Черевач, В. (2023). Цифрова мода: основні чинники виникнення та соціокультурне значення. Культурно-мистецькі та освітні практики, № 42, С. 307-315. doi: https://doi.org/10.31866/2410-1311.42.2023.2938042
Домбровська О. М., Артеменко М. П. Формування модельних комбінаторних рядів асортиментної структури жіночого жакета в умовах кастомізованого виробництва // Вісник Херсонського національного технічного університету. 2024. № 1 (88). С. 168–173. https://doi.org/10.35546/kntu2078-4481.2024.1.22
Yezhova, O., Wu, S., Pashkevych, K., Kolosnichenko, M., Ostapenko, N., & Struminska, T. (2024). Exploring design and technological aspects of digital fashion: A systematic review of recent innovations. International Journal of Fashion Design, Technology and Education. https://doi.org/10.1080/17543266.2024.2378032
Пашкевич, К. Л., Воробчук , М. С., & Шинкар , А. Ю. (2023). Імерсивні технології як інноваційний інструмент проєкції в дизайні. Арт та дизайн, (2), 96–104. https://doi.org/10.30857/2617-0272.2023.2.9
Run Wei. (2024). New Trends in Fashion Design: Digital Fashion Leads the Change. International Journal of Education and Humanities, 17(2), 232–237. https://doi.org/10.54097/99g93757
Shevchuk K. (2024). Digital transformations in clothing design at the beginning of the 21st century / K. Shevchuk // Bulletin of Lviv National Academy of Arts, № 52, 119-128. https://doi.org/10.37131/2524-0943-2024-52-12
Redström, J., Skog, T., & Hallnäs, L. (2000). Informative art: Using amplified artworks as information displays. Proceedings of DARE 2000 on Designing augmented reality environments, р. 103–114.
Doordan, D. (2021). Neri Oxman: Material ecology. Design Issues, 37(1), 91-92. https://doi.org/10.1162/desi_r_00626
Zhang, T., Xie, X., Du, X., & Xie, H. (2025). Sketch-guided scene image generation with diffusion model. Computers & Graphics, 129, Article 104226. https://doi.org/10.1016/j.cag.2025.104226
Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV51070.2023.00355
Liu, B., Zhu, Y., Song, K., & Elgammal, A. (2021). Self-supervised sketch-to-image synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2073–2081. https://doi.org/10.1609/aaai.v35i3.16304
Zhao, L., Chen, Y., Du, G., & Wu, X. (2025). Semantic and sketch-guided diffusion model for fine-grained restoration of damaged ancient paintings. Electronics, 14(21), Article 4187. https://doi.org/10.3390/electronics14214187
Guo, J., Zhang, J., Wu, F., Lu, H., Wang, Q., Yang, W., Lim, E. G., & Lu, D. (2025). HiGarment: Cross-modal harmony based diffusion model for flat sketch to realistic garment image. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2025). https://doi.org/10.48550/arXiv.2505.23186
Ngai, E., Lee, M. C. M., & Kei, B. C. W. (2025). A generative artificial intelligence (GenAI) system for fashion design: A case study. IEEE Transactions on Engineering Management, р. 1–15. https://doi.org/10.1109/TEM.2025.3554248
Навольська Л. В., Колосніченко О. В., Струмінська Т. В., Луцкер Т. В., Ременєва Т. В. Дослідження актуальності візуалізації процесу проєктування одягу з використанням новітніх цифрових технологій // Індустрія моди (2), С. 52–62. https://doi.org/10.30857/2706-5898.2025.2.3
Яковлєв, М. І., Бердинських, С. О., Колосніченко, О. В., & Пашкевич, К. Л. (2023). Обєктивні та емоційні властивості сучасної візуалізації в дизайн-проєктуванні. Арт і дизайн, (1), 83–95. https://doi.org/10.30857/2617-0272.2023.1.8
Селезньова А. (2024). Розробка концепт-арту характерного персонажа засобами комп’ютерної графіки // Вісник КНУКіМ. Серія «Мистецтвознавство». 51, 152-163. https://doi.org/10.31866/2410-1176.51.2024.318370
