Mapping Solar Radiation to Architectural Surface Textures: A Generative Workflow Using Stable Diffusion and ControlNet

Open Access Article Peer-Reviewed

Share this article:

Mapping Solar Radiation to Architectural Surface Textures: A Generative Workflow Using Stable Diffusion and ControlNet

Haoyi Chen ¹ , Ao Huang ² , Yiqun Wang ^{3 ,*}

1 . School of Architecture and Art Design，Inner Mongolia University of Science & Technology
2 . Academy of Arts & Design, Tsinghua University
3 . Laboratory of Landscape Development (LAND), School of Architecture, Civil and Environmental Engineering (ENAC), École Polytechnique Fédérale de Lausanne (EPFL), Switzerland

* Authors to whom correspondence should be addressed.

Published in Coastal Human Settlements ( Volume 2, Issue 2 )

Received: 15 October 2025 Accepted: 28 December 2025 Published: 22 January 2026

Download PDF

Cite This Article

Abstract

Current computational design methodologies face a distinct dichotomy: parametric tools offer quantitative precision but lack morphological complexity, while generative AI models excel in aesthetic synthesis yet struggle with spatial fidelity. To address this gap, this study proposes a Conditioned Morphogenesis workflow that integrates a multimodal diffusion model, Stable Diffusion, with a spatial control network, ControlNet, to translate solar radiation heatmaps into functional architectural surface textures. Tree bark morphology is employed as a stress test for self-shading performance, and a Human-in-the-Loop methodology is used to calibrate the interaction between data granularity and generative parameters. Quantitative evaluation using Shannon Entropy, Gray-Level Co-occurrence Matrix (GLCM) Contrast, and Pearson correlation reveals a non-linear optimization relationship, indicating that a grid resolution of 0.6 m achieves optimal morphological stability, with the lowest entropy value of 4.89 bits while effectively balancing texture definition and artifact suppression. Furthermore, a multidimensional performance matrix identifies an optimal convergence state in which moderate data correlation (Pearson r = 0.31) coincides with maximum architectural depth (GLCM Contrast = 236.3), thereby avoiding the rigidity associated with over-controlled data mapping. This framework establishes a validated approach for data-driven texture generation and reframes the architect’s role from direct form-making to parameter curation within generative design systems.

Published in	Coastal Human Settlements (Volume 2, Issue 2)
DOI	10.65736/chs02021
Page(s)	15
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s). Published by Open Access Press

Keywords

Generative AI; Conditioned Morphogenesis; Stable Diffusion; ControlNet; Solar Radiation Mapping

Cite This Article

APA Style

Chen, H. H. , Huang, A. A. , Wang, Y. Y. (2024). Mapping Solar Radiation to Architectural Surface Textures: A Generative Workflow Using Stable Diffusion and ControlNet. Coastal Human Settlements, 2, (2), 1. https://doi.org/10.65736/chs02021

Copy

ACS Style

Chen, H. ; Huang, A. ; Wang, Y. Mapping Solar Radiation to Architectural Surface Textures: A Generative Workflow Using Stable Diffusion and ControlNet. Mach. Learn. Res. (2024), 2, (2), 1. doi: https://doi.org/10.65736/chs02021

Copy

AMA Style

Chen , Huang , Wang . Mapping Solar Radiation to Architectural Surface Textures: A Generative Workflow Using Stable Diffusion and ControlNet. Mach Learn Res. (2024);2(2):1. doi: https://doi.org/10.65736/chs02021

Copy

References

1. Menges, A. Material computation: Higher integration in morphogenetic design. Archit. Des. 2012, 82(2), 14–21. https://doi.org/10.1002/ad.1374
2. Zhang, L.; Rao, A.; Agrawala, M. Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2–6 October 2023; pp. 3836–3847. https://doi.org/10.1109/ICCV51070.2023.00355
3. Oxman, R. Performance-based design: Current practices and research issues. Int. J. Archit. Comput. 2008, 6(1), 1–17. https://doi.org/10.1260/147807708784640090
4. Carpo, M. The Second Digital Turn: Design Beyond Intelligence; MIT Press: Cambridge, MA, USA, 2017.
5. Chaillou, S. ArchiGAN: A generative stack for apartment building design. NVIDIA Technical Blog, 17 July 2019. Available online: https://developer.nvidia.com/blog/archigan-generative-stack-apartment-building-design/ (accessed on 12 De-cember 2025).
6. Saxena, D.; Cao, J. Generative adversarial networks (GANs): Challenges, solutions, and future directions. ACM Comput. Surv. 2021, 54(3), 1–42. https://doi.org/10.1145/3446374
7. del Campo, M. Ontology of diffusion models: Tools, language and architecture design. In Diffusions in Architecture: Artificial Intelligence and Image Generators; del Campo, M., Ed.; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2024; pp. 44–54. https://doi.org/10.1002/9781394191802
8. Zhang, L.; Rao, A.; Agrawala, M. Adding conditional control to text-to-image diffusion models. Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV) 2023, 3836–3847. https://doi.org/10.1109/ICCV51070.2023.00355
9. Badarnah, L. Form follows environment: Biomimetic approaches to building envelope design for environmental adapta-tion. Buildings 2017, 7(2), 40. https://doi.org/10.3390/buildings7020040
10. Al-Obaidi, K.M.; Ismail, M.A.; Hussein, H.; Rahman, A.M.A. Biomimetic building skins: An adaptive approach. Renew. Sustain. Energy Rev. 2017, 79, 1472–1491. https://doi.org/10.1016/j.rser.2017.05.028
11. Leach, N. Architecture in the Age of Artificial Intelligence: An Introduction to AI for Architects; Bloomsbury Visual Arts: London, UK, 2022. https://doi.org/10.5040/9781350165557
12. Shannon, C.E. A mathematical theory of communication. Bell Syst. Tech. J. 1948, 27(3), 379–423. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
13. Haralick, R.M.; Shanmugam, K.; Dinstein, I. Textural features for image classification. IEEE Trans. Syst. Man Cybern. 1973, SMC-3(6), 610–621. https://doi.org/10.1109/TSMC.1973.4309314