本研究旨在探討人工智慧(AI)作為新興建築設計媒介的應用方法，並通過提出AI建築設計流程，深入分析AI工具在建築設計過程中的價值、優勢及所面臨的挑戰。
研究首先提出一個基於網狀結構的AI建築設計流程架構，打破傳統線性設計模式的限制。隨後針對Stable Diffusion和ControlNet等AI工具進行了參數試驗，並整理出適用於建築設計的參數策略表，為後續研究提供參考依據。
在參數試驗的基礎上，研究進一步發展AI建築設計流程的組成及具體建構細節。根據不同設計階段的技術特性與應用場景，將流程劃分為「探索流」、「實現流」、「手繪流」、「實踐流」、「渲染流」和「跳脫流」，並通過流程演示具體展現其效益與應用價值。
接著本研究進行流程測試，透過受試者測試數據的分析與行為觀察，歸納出AI建築設計流程的優勢與不足。在此基礎上，通過綜合應用實作進一步驗證並優化AI建築設計流程的核心成果，最終對結果進行綜合評估。
結果顯示，AI設計流程相較於傳統設計方法具有多項優勢。首先，AI工具大幅降低了設計溝通的門檻，透過簡單的提示詞或圖像輸入，使設計概念得以迅速具象化，即使非建築專業背景者也能參與設計討論。其次，AI工具的高效生成能力促使使用者能靈活切換設計切入點，提升設計探索的效率與多樣性。此外，AI設計流程在設計思想跳脫與創新啟發方面展現出顯著價值，幫助設計者突破既有框架，激發前所未有的創意潛能。
然而本研究亦指出AI建築設計流程面臨的三大瓶頸：首先，AI工具在建築圖學專業性上的不足，特別是在平面圖及剖面圖生成過程中的誤差；其次，現有AI模型在地域文化及在地化風格的表達能力仍顯不足，難以滿足特定場域的設計需求；最後，AI工具對抽象空間概念的理解與轉化能力有限，導致在應對抽象設計指令時出現碰壁現象。
最後，本研究認為隨著AI設計流程的應用與持續發展，未來以AI為主的設計方法可能不再強調設計過程中的脈絡發展，而是轉向單純的目的導向思維模式。同時，AI設計流程將根據使用者的設計偏好進行高度客製化，使其更加符合使用者的個別需求與思維模式。這樣的客製化流程不僅具象化出使用者的思維特徵，還能促進個性化創作，開創出更具創新性和多樣化的設計成果。

Artificial intelligence (AI) is increasingly applied in architectural design, offering new methods and opportunities. An AI-driven workflow is proposed to overcome the limitations of traditional linear processes, supported by parameter tests with tools like Stable Diffusion and ControlNet. These tests establish strategies for effectively applying AI to architectural projects.
The workflow is divided into six streams—Exploration, Realization, Sketching, Implementation, Rendering, and Divergence—tailored to different design stages. Results show that AI significantly reduces communication barriers, accelerates idea visualization, and enhances design efficiency and diversity. Additionally, AI tools promote creative breakthroughs by enabling designers to transcend conventional frameworks.
However, challenges persist. AI tools often lack precision in architectural drawings, struggle with localized style representation, and have limited ability to interpret abstract spatial concepts. Looking ahead, AI design workflows are expected to evolve into goal-oriented, highly customized processes that align with individual user preferences. This personalization has the potential to foster innovation and generate more diverse and unique architectural outcomes.

Agkathidis, A. (2024). AI-Assisted Architectural Design: Generative Form-Finding Methods by Using Artificial Intelligence.
Aish, R., & Bredella, N. (2017). The evolution of architectural computing: from Building Modelling to Design Computation. Arq: Architectural Research Quarterly, 21(1), 65-73.
Akti, M. (2024). The Use and Development of Artificial Intelligence in Architectural Design Processes. Black Sea Journal of Engineering and Science, 7(6), 1347-1360.
Almaz, A. F., El-Agouz, E. A. E.-a., Abdelfatah, M. T., & Mohamed, I. R. (2024). The Future Role of Artificial Intelligence (AI) Design's Integration into Architectural and Interior Design Education is to Improve Efficiency, Sustainability, and Creativity. Sustainability, and Creativity, 3(12), 1749-1772.
As, I., & Basu, P. (2021). The Routledge companion to artificial intelligence in architecture. Routledge Abingdon, UK.
Bölek, B., Tutal, O., & Özbaşaran, H. (2023). A systematic review on artificial intelligence applications in architecture. Journal of Design for Resilience in Architecture and Planning, 4(1), 91-104.
Baduge, S. K., Thilakarathna, S., Perera, J. S., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A., & Mendis, P. (2022). Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction, 141, 104440.
Banh, L., & Strobel, G. (2023). Generative artificial intelligence. Electronic Markets, 33(1), 63.
Beyan, E. V. P., & Rossy, A. G. C. (2023). A review of AI image generator: influences, challenges, and future prospects for architectural field. Journal of Artificial Intelligence in Architecture, 2(1), 53-65.
Branda, E. E. (1998). Drawing interfaces: building geometric models with hand-drawn sketches Massachusetts Institute of Technology].
Caldas, L. (2008). Generation of energy-efficient architecture solutions applying GENE_ARCH: An evolution-based generative design system. Advanced Engineering Informatics, 22(1), 59-70.
Croitoru, F.-A., Hondru, V., Ionescu, R. T., & Shah, M. (2023). Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 10850-10869.
Dall’Asta, J. C., & Di Marco, G. (2023). AI Machine Learning in Creative Architectural Design Processes. xArch–creativity in the age of digital reproduction symposium,
Denerel, S. B., & Birişçi, T. (2017). Drawing Tools Used from Past to Present in the Architectural Design Process. Journal of International Environmental Application and Science, 12(3), 230-237.
El Samad, M., Nasserddine, G., & Kheir, A. (2023). Introduction to Artificial Intelligence. In Artificial Intelligence and Knowledge Processing (pp. 1-14). CRC Press.
Gammal, Y. (2024). The “Cognitive” Architectural Design Process and Its Problem with Recent Artificial Intelligence Applications. Engineering and Applied Sciences, 9, 83-105. https://doi.org/10.11648/j.eas.20240905.11
Goldschmidt, G. (1994). On visual design thinking: the vis kids of architecture. Design studies, 15(2), 158-174.
Grobman, Y. J., Yezioro, A., & Capeluto, I. G. (2010). Non-linear architectural design process. International Journal of Architectural Computing, 8(1), 41-53.
Harapan, A., Indriani, D., Rizkiya, N., & Azbi, R. (2021). Artificial Intelligence in Architectural Design. International Journal of Design (INJUDES), 1, 1-6.
Hegazy, M., & Saleh, A. (2023). Evolution of AI role in architectural design: between parametric exploration and machine hallucination. MSA Engineering Journal, 2(2), 262-288.
Hu, X., Zheng, H., & Lai, D. (2024). Performance Prediction of AI-generated Architectural Layout Design: Using Daylight Performance of Residential Floorplans as an Example.
Ibrahim, R., & Rahimian, F. P. (2010). Comparison of CAD and manual sketching tools for teaching architectural design. Automation in Construction, 19(8), 978-987.
Idi, D. B., & Khaidzir, K. A. B. M. (2015). Concept of creativity and innovation in architectural design process. International Journal of Innovation, Management and Technology, 6(1), 16.
James, T. G., Guetterman, T. C., & Molina-Azorin, J. F. (2024). Increasing transparency on the use of artificial intelligence and automated tools in mixed methods studies. In (Vol. 18, pp. 425-429): SAGE Publications Sage CA: Los Angeles, CA.
Ji, L. H. (2022). [Retracted] Application and Optimization of Artificial Intelligence Technology in Architectural Design. Wireless Communications and Mobile Computing, 2022(1), 5170068.
Kallioras, N. A., & Lagaros, N. D. (2020). DzAIℕ: Deep learning based generative design. Procedia Manufacturing, 44, 591-598.
Kristianova, K., Joklova, V., & Meciar, I. (2018). Physical models in architectural education and the use of new technologies. ICERI2018 Proceedings,
Li, C., Zhang, T., Du, X., Zhang, Y., & Xie, H. (2024). Generative AI models for different steps in architectural design: A literature review. Frontiers of Architectural Research.
Lund, J. J., & Sinton, D. S. (2007). Critical and creative visual thinking. Understanding place: GIS mapping across the curriculum, 1-18.
Lv, Z. (2023). Generative artificial intelligence in the metaverse era. Cognitive Robotics, 3, 208-217.
Mancini, M., & Menconero, S. (2023). AI-aided Design? Text-to-image Processes for Architectural Design/AI-aidedDesign? Processi text-to-image per il disegno di architettura. 13, 57-70. https://doi.org/10.26375/disegno.13.2023.8
Mukkavaara, J., & Sandberg, M. (2020). Architectural design exploration using generative design: framework development and case study of a residential block. Buildings, 10(11), 201.
Pannu, A. (2015). Artificial intelligence and its application in different areas. Artificial Intelligence, 4(10), 79-84.
Pena, M. L. C., Carballal, A., Rodríguez-Fernández, N., Santos, I., & Romero, J. (2021). Artificial intelligence applied to conceptual design. A review of its use in architecture. Automation in Construction, 124, 103550.
Rando, J., Paleka, D., Lindner, D., Heim, L., & Tramèr, F. (2022). Red-teaming the stable diffusion safety filter. arXiv preprint arXiv:2210.04610.
Rane, N. (2023). Role of ChatGPT and similar generative artificial intelligence (AI) in construction industry. Available at SSRN 4598258.
Rane, N., Choudhary, S., & Rane, J. (2023). Integrating Building Information Modelling (BIM) with ChatGPT, Bard, and similar generative artificial intelligence in the architecture, engineering, and construction industry: applications, a novel framework, challenges, and future scope. Bard, and similar generative artificial intelligence in the architecture, engineering, and construction industry: applications, a novel framework, challenges, and future scope (November 22, 2023).
Riccobono, A. (2014). Architectural design in the digital era. Identifying computer influences and new expressive trends in current architecture.
Rubayet, M., Mouri, J., Ahmmed, M., Ishtiak, M., & Shuvo, A. Artificial Intelligence Design Advancements: The Role of AI in Architectural Design.
Sönmez, N. O. (2018). A review of the use of examples for automating architectural design tasks. Computer-Aided Design, 96, 13-30.
Sajja, P. S., & Sajja, P. S. (2021). Introduction to artificial intelligence. Illustrated Computational Intelligence: Examples and Applications, 1-25.
Sebestyen, A., Özdenizci, O., Legenstein, R., & Hirschberg, U. (2023). Generating conceptual architectural 3d geometries with denoising diffusion models. Digital Design Reconsidered-Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023)-Volume,
Shi, M., Seo, J., Cha, S. H., Xiao, B., & Chi, H.-L. (2024). Generative AI-powered architectural exterior conceptual design based on the design intent. Journal of Computational Design and Engineering, 11(5), 125-142.
Strong, A. (2016). Applications of artificial intelligence & associated technologies. Science [ETEBMS-2016], 5(6), 64-67.
Wen, M., Liang, D., Ye, H., & Tu, H. (2024). Architectural facade design with style and structural features using stable diffusion model. Journal of Intelligent Construction, 2(4).
Weytjens, L., Verdonck, E., & Verbeeck, G. (2009). Classification and use of design tools: The roles of tools in the architectural design process.
Wiggins, G. E. (1989). Methodology in architectural design Massachusetts Institute of Technology].
Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., & Yang, M.-H. (2023). Diffusion models: A comprehensive survey of methods and applications. ACM Computing Surveys, 56(4), 1-39.
Zhang, J., Huang, Y., Li, Z., Li, Y., Yu, Z., & Li, M. (2024). Development of a method for commercial style transfer of historical architectural façades based on stable diffusion models. Journal of Imaging, 10(7), 165.
林冠伶. (2022). 衍生式設計輔助BIM設計流程之研究 國立成功大學]. 臺灣博碩士論文知識加值系統. 台南市. https://hdl.handle.net/11296/zs38r3
陳秀嬪. (2023). 人工智慧在建築業主要發展軌跡及未來展望 國立臺北科技大學]. 臺灣博碩士論文知識加值系統. 台北市. https://hdl.handle.net/11296/298d3k
龔智群. (2023). 人工智慧輔助BIM建築設計流程 國立成功大學]. 臺灣博碩士論文知識加值系統. 台南市. https://hdl.handle.net/11296/326d8q