Journals / Journal of Computational Design / 2026 / Cilt: 7 Sayı: 2

Implementing a Generative AI Model in the Architectural Concept Development: Context-based Research

Mimari Konsept Geliştirme Aşamasında Bir Yapay Zekâ Modelinin Uygulanması: Bağlam Temelli Araştırma

Zeyd Elabbasi(ALTINBAŞ ÜNİVERSİTESİ)0009-0007-5150-5331
Çağda Özbaki(ALTINBAŞ ÜNİVERSİTESİ)0000-0001-8796-9567
Pages
217–236
Publication Date
2026-09-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Gathering the data about these outputs and analyzing the overall experiment.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In the context of the continual evolution of advanced architectural design tools, driven by computational and artificial intelligence technologies, the practice of design can now benefit from contextually-driven and iterative design workflows.
📊
Key Findings & Data:This paper explores juxtaposing node-based computational design and AI tools in a dependent workflow process using Grasshopper3D and ComfyUI, within the framework of an experimental architectural concept development process, through a qualitative Research-through-Design methodology (RtD).
💡
Conclusion & Impact:Gathering the data about these outputs and analyzing the overall experiment.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:: Mimari tasarım bağlamı · Yapay zekâ · Kavramsal tasarım

Abstract

In the context of the continual evolution of advanced architectural design tools, driven by computational and artificial intelligence technologies, the practice of design can now benefit from contextually-driven and iterative design workflows. Thus, computational and AI tools have huge potential to enhance the conceptual design processes in architecture, due to their advanced workflow qualities. Node-based interfaces of these tools serve as a catalyst, enabling workflows that are adaptable to different requirements and needs of the design processes. This paper explores juxtaposing node-based computational design and AI tools in a dependent workflow process using Grasshopper3D and ComfyUI, within the framework of an experimental architectural concept development process, through a qualitative Research-through-Design methodology (RtD). Through a series of controlled experiments, multiple architectural design schemes are generated and categorized into four distinct visual identities: blob, biophilic, vernacular, and modern. These categories serve as a comparative framework to evaluate the adaptability and responsiveness of the integrated workflow across different design intentions. The process emphasizes iteration and variation, but with contextual responsiveness, testing a more streamlined refinement process of design schemes. The findings demonstrate that integrating node-based computational scripting with AI-driven workflows enhances the capacity for rapid iteration, supports the generation of diverse and contextually relevant architectural concepts, and enables more fluid transitions between abstract and representational stages of design. This research contributes to the advancement of architectural design methodologies by implementing a hybrid workflow model that bridges computational logic and generative AI capabilities, showcasing new potentials for concept development in contemporary architectural practice. Node-based interfaces of these tools act as a catalyst to allow more custom and interconnected workflows. Moreover, it is important to test new design potentials that these tools contribute to when used in parallel for the conceptual design process. This thesis explores juxtaposing node-based computational design and AI tools in a dependent workflow process using Grasshopper3D and ComfyUI, within the framework of an experimental architectural concept development process, through a qualitative Research-through-Design methodology(RtD). By experimenting with their workflows, the aim is to formulate different design schemes that are contextually relevant but also achieved iteratively. Visualizing abstract forms to test architectural forms relevant to four styles, which are blob, biophilic, vernacular, and modern architectural styles. Gathering the data about these outputs and analyzing the overall experiment. Ultimately, this thesis achieves iterative, data-informed design schemes with detailed architectural features. Aiding contextually relevant but also architecturally detailed design schemes during the conceptual phase of the architectural design process.

Özet

Hesaplamalı tasarım ve yapay zekâ teknolojilerinin gelişimiyle birlikte, bugünkü mimari tasarım süreci artık daha çeşitli yöntemlerle yürütülebilmektedir. Mimari tasarım daha tekrarlayan ve hızla gelişen bir yapıya büründü, özellikle kavramsal tasarım aşaması için bu kaliteleri kullanmak çok önemlidir. Bu bağlamda, hesaplamalı ve yapay zekâ araçları, sahip oldukları yinelemeli iş akışları sayesinde kavramsal tasarım süreçlerini geliştirme açısından büyük bir potansiyele sahiptir. Ayrıca, bu araçların birlikte ve paralel kullanımının, mimari tasarım sürecine kazandırdığı yeni tasarım olanaklarının test edilmesi de önem arz etmektedir. Bu çalışmada, Grasshopper3D ve ComfyUI programları kullanılarak düğüm tabanlı hesaplamalı tasarım ile yapay zekâ modelinin bir arada çalıştığı bağımlı bir iş akışı süreci incelenmektedir. Araştırma, Tasarımla Araştırma (Research-through-Design– RtD) yöntemi çerçevesinde deneysel bir kavramsal tasarım geliştirme süreci olarak yürütülmüştür. Çalışmanın amacı, farklı iş akışlarını deneyerek hem bağlama duyarlı hem de yinelemeli yöntemlerle elde edilen çeşitli tasarım şemaları ortaya koymaktır. Bu kapsamda, dört farklı mimari üsluba (blob, biyofilik, yerel ve modern) uygun soyut formlar üretilmiş, bu formlar üzerinden veriler toplanmış ve süreç bütüncül olarak analiz edilmiştir. Elde edilen bulgular, ayrıntılı mimari özellikler barındıran, veriye dayalı ve yinelemeli tasarım çıktılarının kavramsal tasarım aşamasında nasıl geliştirilebileceğini göstermektedir. Sonuç olarak, çalışma mimari tasarım sürecine hem bağlamsal açıdan duyarlı hem de ayrıntılı çözümler sunan yeni bir metodolojik katkı sağlamaktadır.

🔖

Cite This Article

Elabbasi, Z., Özbaki, Ç. (2026). Implementing a Generative AI Model in the Architectural Concept Development: Context-based Research. Journal of Computational Design, Cilt: 7 Sayı: 2, 217–236. https://doi.org/10.53710/jcode.1776839

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (16)

  1. Agkathidis, A. (2015). Generative design: Form-finding techniques in architecture. Laurence King Publishing.
  2. Alexander, C., Ishikawa, S., & Silverstein, M. (1977). A pattern language. Oxford University Press.
  3. Burry, M. (2011). Scripting cultures. John Wiley & Sons.
  4. Carpo, M. (2013). The digital turn in architecture. John Wiley & Sons.
  5. Carpo, M. (2017). The second digital turn: Design beyond intelligence. The MIT Press.
  6. Chaillou, S. (2022). Artificial intelligence and architecture: From research to practice. Birkhäuser.
  7. Ching, F. D. K. (2015). Architecture: Form, space, and order (4th ed.). Wiley.
  8. Cross, N. (2006). Designerly ways of knowing. Springer.
  9. Garnier, T. (1990). Une cité industrielle. Rizzoli.
  10. Han, S., & Kim, J. (2024). CLIP-VQDiffusion: Language-free training of text-to-image generation using CLIP and vector-quantized diffusion model. arXiv. https://doi.org/10.48550/arXiv.2403.1494
  11. Heidegger, M. (1977). The question concerning technology and other essays. Garland Publishing.
  12. Leach, N. (2022). Architecture in the age of artificial intelligence. Bloomsbury Publishing.
  13. Le Corbusier. (2007). Towards a new architecture (F. Etchells, Trans.). Dover Publications. (Original work published 1923).
  14. Menges, A., & Ahlquist, S. (2011). Computational design thinking. John Wiley & Sons.
  15. Wang, W., Sun, Q., Zhang, F., Tang, Y., Liu, J., & Wang, X. (2024). Diffusion feedback helps CLIP see better. arXiv. https://doi.org/10.48550/arXiv.2407.20171
  16. Wesego, D., & Rooshenas, A. (2024). Revising multimodal VAEs with diffusion decoders. arXiv. https://doi.org/10.48550/arXiv.2408.16883