This article explores the impact of Artificial Intelligence (AI) on the architectural discipline, focusing on generative models and their controllability. While generative models have revolutionized the design process by freeing designers from specific tasks and allowing them to focus on desired results, the reliance on randomness frequently hinders controllability and meaningful experimentation. To address this challenge, the article proposes the construction of an encyclopedic architectural dataset, encompassing various architectural projects and combining images with text for multimodal applications and two methodologies, multi-class StyleGAN and multimodal StyleGAN+CLIP to enhance controllability. Utilizing specific conditions, multi-class StyleGAN enables designers to navigate latent space and identify hidden patterns, while StyleGAN+CLIP integrates text to achieve specific controllability and generate diverse architectural features. Through experimentation, the research showcases the potential of generative models to create structured designs that incorporate existing architectural styles.
del CampoMManningerSCarlsonA. A question of style. In: Yuan PF, Xie M, Leach N, et al. (eds)Architectural intelligence. Singapore, Springer. 2020, pp. 171–188. doi:10.1007/978-981-15-6568-7_11.
2.
FortyA. Words and buildings: a vocabulary of modern architecture. London: London Thames and Hudson, 2016.
3.
XuZTaoDZhangY, et al.Architectural style classification using multinomial latent logistic regression. Computer Vision – ECCV2014; 2014: 600–615.
4.
GuneyYI. Type and typology in architectural discourse. Journal of Balikesir University FBE2007; 9: 3–18.
5.
TatarkiewiczW. Objectivity and subjectivity in the history of aesthetics. Philosophy and Phenomenological Research1963; 24: 157–173. Available from: http://www.jstor.org/stable/2104458.
6.
ClaudyMCAquinoKGrasoM. Artificial intelligence can’t be charmed: the effects of impartiality on laypeople’s algorithmic preferences. Front Psychol2022; 13: 898027.
KarrasTLaineSAilaT. A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 4401–4410.
11.
BermanoAHGalRAlalufY, et al.State-of-the-art in the architecture, methods and applications of StyleGAN. Computer Graphics Forum2022; 41: 591–611.
12.
PatashnikOWuZShechtmanE, et al.StyleCLIP: Text-driven manipulation of StyleGAN imagery2021. p. 2085–2094. arXiv:2103.17249.
13.
AlexanderCIshikawaSSilversteinM. A pattern language : towns, buildings, construction. New York: Oxford Universities Press, 1977.
14.
StinyG. Introduction to shape and shape grammars. Environ Plann Plann Des1980; 7(3): 343–351.
15.
NeumannJVBurksAW. Theory of self-reproducing automata. Champaign: University of Illinois Press, 1966.
16.
ReynoldsCW. Flocks, herds and schools: A distributed behavioral model. Proceedings of the 14th annual conference on Computer graphics and interactive techniques - SIGGRAPH ’87. New York: ACM Press, 1987; Available from: https://dl.acm.org/citation.cfm?id=37406
17.
SteinfeldK. GAN Loci. In: ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA)]. Austin, Texas: The University of Texas at Austin School of Architecture, 2019, pp. 392–403.
18.
Vivanco LarrainTValenciaAYuanPF. Spatial findings on chilean architecture stylegan ai graphics. In: Proceedings of the 26th CAADRIA conference. Hong Kong: The Chinese University of Hong Kong and Online, 2021.
19.
ChenJStouffsRBiljeckiF. Hierarchical (multi-label) architectural image recognition and classification. In: Proceedings of the 26th International Conference of the Association for Computer-Aided Architectural Design Research in Asia. Hong Kong: CAADRIA, 2021, pp. 161–170.
20.
GuidaG. Multimodal Architecture: Applications of Language in a Machine Learning Aided Design Process. In: Koh I, Reinhardt D, Makki M, et al., (eds). HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference. Ahmedabad, 18-24 March 2023, 2023, pp. 561–570.
21.
HoggenmuellerMLupettiMLvanGK. Creative AI for HRI design explorations. Stockholm, Sweden: Association for Computing Machinery, 2023, p. 40. Available from: DOI: 10.1145/3568294.3580035.
22.
DoblerKHübscherFWestphalJ, et al.Art creation with multi-conditional StyleGANs. In: Raedt LD (ed)International joint conferences on artificial intelligence organization. 2022, pp. 4903–4909. doi:10.24963/ijcai.2022/684.
23.
RadfordAMetzLChintalaS. Unsupervised representation learning with deep convolutional generative adversarial networks. In:Proceedings of the International Conference on Learning Representations. 2016.
24.
KarrasTAilaTLaineS, et al.Progressive growing of GANs for improved quality, stability, and variation. CoRR [Internet]. 2017; abs/1710.10196.
25.
KarrasTAittalaMHellstenJ, et al.Training generative adversarial networks with limited data. Prayagraj, Uttar Pradesh: CoRR, 2020. Available from: https://arxiv.org/abs/2006.06676.
26.
BachlMFerreiraDC. City-GAN: learning architectural styles using a custom Conditional GAN architecture, 2020. Available from: https://arxiv.org/abs/1907.05280.
27.
RadfordAHallacyCRameshA, et al.Learning transferable visual models from natural language supervision. Prayagraj, Uttar Pradesh: CoRR, 2021. Available from: https://arxiv.org/abs/2103.00020.
28.
GalRPatashnikOMaronH, et al.StyleGAN-NADA: CLIP-guided domain adaptation of image generators. ACM Trans Graph2022; 41: 1–13.
TylečekRŠáraR. Spatial pattern templates for recognition of objects with regular structure. In: Weickert J, Hein M, Schiele, B (eds)Pattern recognition. GCPR 2013. Lecture notes in computer science. 2013. Berlin, Heidelberg: Springer, Vol 8142. doi:10.1007/978-3-642-40602-7_39.
32.
RameshADhariwalPNicholA, et al.Hierarchical text-conditional image generation with CLIP latents. arXiv e-prints, 2022. Available from: https://arxiv.org/abs/2204.06125.
33.
RombachRBlattmannALorenzD, et al.High-resolution image synthesis with latent diffusion models. Prayagraj, Uttar Pradesh: CoRR, 2021. Available from: https://arxiv.org/abs/2112.10752.
34.
CrowsonKBidermanSKornisD, et al.VQGAN-CLIP: open domain image generation and editing with natural language guidance, 2022. Available from: https://arxiv.org/abs/2204.08583.
35.
RichardsonEAlalufYPatashnikO, et al.Encoding in style: a StyleGAN encoder for image-to-image translation, 2021.
36.
KimDLloydLeeSKimH. Elemental Sabotage: Diffusing Functional Morphologies. In Koh I, Reinhardt D, Makki M, et al., (eds). HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference. Ahmedabad, 18-24 March 2023, 2023, pp. 29–38.
37.
BrownTBMannBRyderN, et al.Language models are few-shot learners. arXiv e-prints. 2020; 14165.
