Traditional and Modern Architectural Design Generation for Kıyıköy in Türkiye Utilizing the DALL-E Artificial Intelligence Model

Year 2025, Volume: 6 Issue: 1, 33 - 46, 30.06.2025

Samet Memiş , Hatice Çiğdem Zağra , Sibel Özden Omuzlu

https://doi.org/10.54559/amesia.1730023

Abstract

This study utilizes the DALL-E artificial-intelligence (AI) model to generate both traditional and modern architectural visuals that follow the Kıyıköy Conservation Master Plan for the historic coastal town of Kıyıköy, Türkiye. The process has two stages. First, key features of traditional architecture—such as morphology, materials, and design types—are extracted from the plan and used as text prompts; DALL-E then creates visual representations of heritage structures. Next, the prompts are adjusted to incorporate contemporary design goals while respecting constraints on height, façade materials, setbacks, roof shapes, and window-door ratios. A five-point compliance framework, based directly on the conservation plan, is used to evaluate each output: (1) building height and number of stories, (2) lot width and distance to neighbors, (3) roof type, (4) façade materials, and (5) window-door ratios and openness. Figure 4b meets all standards, while Figures 4a, 4c, and 4d meet four criteria, falling short only in fenestration proportions. The results demonstrate that DALL-E, guided by regulation-aware prompts, can quickly generate concepts that adhere to conservation rules, emphasizing its usefulness for heritage-sensitive, rule-based design projects. Incorporating zoning and morphological constraints directly into prompts provides a new, reproducible approach for integrating generative AI into preservation-focused architectural workflows.

Keywords

Traditional architectural design , modern architectural design , artificial intelligence , DALL-E , Kıyıköy

Thanks

We thank Kıyıköy Municipality for providing the notes of the conservation master plan of Cumhuriyet Street in Kıyıköy, Türkiye.

References

• S. Seneviratne, D. Senanayake, S. Rasnayaka, R. Vidanaarachchi, J. Thompson, DALLE-URBAN: Capturing the urban design expertise of large text to image transformers, International Conference on Digital Image Computing: Techniques and Applications (DICTA), IEEE, Sydney, 2022, pp. 1–9.
• M. S. Watanabe, Algorithmic Design/Induction Design: Three Kinds of Flow/Three Stations (2005), https://www.makoto-architect.com/kashiwanohaCSt.html, Accessed 23 Feb 2023.
• I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets, Advances in Neural Information Processing Systems 27 (2014) 1–9.
• D. Bolojan, The Hitchhiker’s Guide to Artificial Intelligence: AI and Architectural Design (2021), www.digitalfutures.world, Accessed 23 Feb 2023.
• B. Yıldırım, D. Demirarslan, Evaluation of the benefits of artificial intelligence applications to the design process in interior architecture, Humanities Sciences 15 (2) (2020) 62–80.
• C. Uzun, M. B. Çokaloğlu, A. İnceoğlu, GAN as a generative architectural plan layout tool: A case study for training DCGAN with Palladian Plans, and evaluation of DCGAN outputs, ITU Journal of the Faculty of the Architecture 17 (2) (2020) 185–198.
• B. Sağlam, T. Çelik, Architecture and utopia: Experiments in generative design with artificial intelligence, Mimarlık, 429 (2023) 59–64.
• V. Paananen, J. Oppenlaender, A. Visuri, Using text-to-image generation for architectural design ideation, International Journal of Architectural Computing 22 (3) (2024) 458–474.
• A. Durukan, R. D. Türk, The effect of verbally transmitted data on visualisation potential in artificialintelligence perception: Traditional Turkish house example, International Journal of Social and Humanities Sciences Research, 10 (102) (2023) 3569–3580.
• M. Gür, F. K. Çorakbaş, İ. S. Atar, M. G. Çelik, İ. Maşat, C. Şahin, Communicating AI for architectural and interior design: Reinterpreting traditional Iznik tile compositions through AI software for contemporary spaces, Buildings 14 (9) (2024) 2916.
• K. Arzomand, M. Rustell, T. Kalganova, From ruins to reconstruction: Harnessing text-to-image AI for restoring historical architectures, Challenge Journal of Structural Mechanics 10 (2) (2024) 69–85.
• Y. Lu, J. Wu, M. Wang, J. Fu, W. Xie, P. Wang, P. Zhao, Design transformation pathways for AI-generated images in Chinese traditional architecture, Electronics 14 (2) (2025) 282.
• H. Xu, F. Omitaomu, S. Sabri, S. Zlatanova, X. Li, Y. Song, Leveraging generative AI for urban digital twins: a scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement, Urban Informatics 3 (1) (2024) 29.
• F. Zhou, H. Li, R. Hu, S. Wu, H. Feng, Z. Du, L. Xu, ControlCity: A Multimodal Diffusion Model Based Approach for Accurate Geospatial data Generation and Urban Morphology Analysis (2024), https://arxiv.org/abs/2409.17049v1, Accessed 22 June 2025.
• D. Jia, J. Guo, K. Han, H. Wu, C. Zhang, C. Xu, X. Chen, Geminifusion: Efficient Pixel-Wise Multimodal Fusion for Vision Transformer (2024), https://arxiv.org/abs/2406.01210v2, Accessed 22 June 2025.
• C. Thampanichwat, T. Wongvorachan, L. Sirisakdi, P. Chunhajinda, S. Bunyarittikit, R. Wongmahasiri, Mindful architecture from text-to-image AI perspectives: A case study of DALL-E, Midjourney, and Stable Diffusion, Buildings 15 (6) (2025) 972.
• Z. Kuang, J. Zhang, Y. Li, T. Fukuda, Preserving architectural heritage in urban renewal: A stable diffusion model framework for automated historical facade generation, npj Heritage Science 13 (1) (2025) 1–19.
• J. Huang, S. E. Bibri, P. Keel, Generative spatial artificial intelligence for sustainable smart cities: A pioneering large flow model for urban digital twin, Environmental Science and Ecotechnology 24 (2025) 100526.
• S. Alaçam, O. Z. Güzelci, S. Z. Bacınoğlu, H. N. Kızılyaprak, C. Uzun, E. Coşkun, İ. Karadağ, Artificial intelligence 101 for architectural education, Oneri 20 (Special Issue) (2025) 219–237.
• A. Ramesh, M. Pavlov, G. Goh, S. Gray, C. Voss, A. Radford, I. Sutskever, Zero-Shot Text-to-Image Generation (2021), https://arxiv.org/abs/2102.12092v2 Accessed 22 June 2025.
• A. Ramesh, P. Dhariwal, A. Nichol, C. Chu, M. Chen, Hierarchical Text-Conditional Image Generation with CLIP Latents (2022), https://arxiv.org/abs/2204.06125v1, Accessed 22 June 2025.
• OpenAI, DALL-E 3 system card, https://openai.com/dall-e-3, Accessed 22 June 2025.
• OpenAI, GPT-4 Technical Report (2023), https://arxiv.org/abs/2303.08774v6, Accessed 22 June 2025.
• Google Earth, https://earth.google.com/web/, Accessed 20 Jan 2023.
• H.Ç. Zağra Öz, Kıyıköy Survey, Kıyıköy Municipality, 2022, Kıyıköy, Kırklareli, Türkiye.
• Z. Wang, A. C. Bovik, H. R. Sheikh, E. P. Simoncelli, Image quality assessment: From error visibility to structural similarity, IEEE Transactions on Image Processing 13 (4) (2004) 600–612.
• J. Ko, J. Ajibefun, W. Yan, Experiments on Generative AI-Powered Parametric Modeling and BIM for Architectural Design (2023), https://arxiv.org/abs/2308.00227v1, Accessed 22 June 2025.
• V. Liu, J. Vermeulen, G. Fitzmaurice, J. Matejka, 3DALL-E: Integrating text-to-image AI in 3D design workflows, in: D. Byrne, N. Martelaro, A. Boucher, D. Chatting, S. F. Alaoui, S. Fox, I. Nicenboim, C. MacArthur (Eds.), Proceedings of the 2023 ACM Designing Interactive Systems Conference, Pittsburgh, 2023, pp. 1955–1977.