This book addresses the growing need for architects and designers to critically engage with artificial intelligence in visual and spatial production. It offers a systematic approach to understanding, directing, and constraining generative models.
Combining theoretical insights with technical instructions, the book explains how contemporary AI tools such as latent diffusion models can be employed effectively and responsibly. Rather than relying on AI as an automatic image generator, the book proposes a methodology grounded in control, feedback, and authorship. It introduces practical workflows using platforms - like ComfyUI, MidJourney, Grasshopper and others - to explore constrains, prompt structure, and how procedural logic can be harnessed to produce intentional, coherent results.
Intended for architects, educators, researchers, and students, this volume positions AI not as a substitute for design expertise, but as a configurable system that must be shaped by the disciplinary and ethical priorities of architecture.
This book addresses the growing need for architects and designers to critically engage with artificial intelligence in visual and spatial production. It offers a systematic approach to understanding, directing, and constraining generative models.
Preface. Acknowledgment. List of Figures. List of Tables.
1.
Introduction. PART1: THEORETICAL FOUNDATIONS.
2. Introduction to AI.
3. Core
Components of AI.
4. Architectures of Learning: From Perceptrons to
Multimodal Intelligence.
5. Latent Space: The Cognitive and Computational
Foundation of Generative AI in Architecture.
6. From Stone to Simulation: The
Evolution of Tools and Technologies in Architecture.
7. AI Tools in
Architectural Practice: From Automation to Epistemic Partnership.
8. A
Framework for Critical AI Practice: Ethics, Authorship, and the New
Architectural Agency. Part 2: CONTROLLING THE HALLUCINATIONSA PRACTICAL
GUIDE.
9. Prompt Engineering for Architects.
10. MidJourney Interfaces:
Discord vs. Web Platform.
11. MidJourney Discord Commands: Annotated
Overview.
12. Architectural Scenarios and Command Applications in Discord.
13. Prompt Engineering Components.
14. Video Generation on Midjourney.
15.
Midjourney Prompt Parameters Overview.
16. Practical Guide to Using COMFY UI
in Architecture.
17. ComfyUI for Image GenerationCheckpoints, Prompts, and
Sampling Logic.
18. Latent Conditioning and ControlNetPrecision Through
Visual Guides.
19. Architectural Animation in ComfyUIVideo Generation and
Consistency Control.
20. Image PreprocessingResizing, Scaling, and Alignment
in the Latent Pipeline.
21. From Sketch to 3DConstructing Volumetric
Architecture in ComfyUI.
22. Reference-Based IterationControlling
Consistency with IPAdapter, ReferenceOnly, and Latent Anchors.
23. Regional
Prompting and Multimodal ControlLayered Guidance in Architectural
Generation.
24. Integrating AI into Grasshopper with APIs, MCP, and Assistant
Plugins.
25. Integrating ComfyUI with GrasshopperParametric Data to
Prompt-Driven Visualization.
26. KreaAI and Googles Nano Banana.
27.
Training and Using Custom LoRA ModelsOffice-Specific Style Conditioning.
28.
Preparing AI Outputs for VR and ARToward Immersive Architectural Workflows.
29. Troubleshooting and Optimizing ComfyUI Workflows for Architectural Image
Quality.
30. Useful Shortcuts for ComfyUI. Conclusion: From Latent
Hallucinations to Architectural Epistemologies of Control. References. Index.
Mustapha El Moussaoui, an architect and urbanist, currently is an assistant professor at the Free University of Bolzano, Italy.
With a background in architecture and philosophy, Mustapha has been involved in educational courses across various countries and universities worldwide. Moreover, he has been engaged professionally in the domain with structures and competitions built and won all over the world. Mustapha's research focuses on the theoretical and practical relationship between architecture and artificial intelligence. Theoretically, his work investigates the epistemological and existential dimensions of artificial intelligence. Practically, Mustapha focuses on narrowing the hallucinatory gap between machine-generated outputs and human architectural authorship.
Lisainfo e-raamatute kohta