Abstract
This study builds on previous research to assess whether text-to-image technology can correctly generate images of residential floor plans. Three tools are tested: Midjourney, Stable Diffusion and Dall-E. The process involved: (1) using reference images to generate text descriptions, (2) crafting prompts from these descriptions and testing them on the three AI systems, (3) merging text requests with reference images, and (4) using hand-drawn sketches to create technical architectural drawings.
In general, the tools showed potential but were deemed not yet suitable for producing architectural designs due to a lack of syntactic and functional logic. Midjourney emerged as the most effective, consistently generating 2D planimetric images and producing quality results when combining textual descriptions with reference images. On the other hand, Dall-E underperformed in responding to text requests and deviated significantly from delivering the desired images, although it excelled at describing images via ChatGPT, a task at which Midjourney faltered. Stable Diffusion was noted for striking a balance, offering quality close to Midjourney and better text descriptions through Artbot. It also showed promise with its unique ability to create images from hand-drawn sketches, a feature not available in the other tools.
The improvements shown by those tools within a short time suggest that they will continue to advance and might soon generate accurate architectural drawings from text descriptions and rough sketches, constituting an important help tool for architects.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
CLIP Interrogator is a prompt engineering tool that combines CLIP, from OpenAI, and BLIP, from Salesforce, to generate optimized texts that match a given image. Its author is pharmapsychotic and it is available on Github. It can be tested online from various websites. For this work, Huggingface (https://huggingface.co/spaces/pharmapsychotic/CLIP-Interrogator) and Replicate (https://replicate.com /pharmapsychotic/clip-interrogator) were used.
- 2.
Interrogate is an application within Artbot, a Stable Horde web client created by Dave Schumaker. It can be used online from https://tinybots.net/artbot/interrogate. Stable Horde is an open source platform that uses idle GPU power, voluntarily provided by the user community, to be freely used for AI art generation.
References
Baduge, S.K., et al.: Artificial intelligence and smart vision for building and construction 4.0: machine and deep learning methods and applications. Autom. Constr. 141, 104440 (2022)
Chaillou, S.: AI+ Architecture: Towards a New Approach. Harvard University, p. 188 (2019)
Nauata, N., Chang, K.H., Cheng, C.Y., Mori, G., Furukawa, Y.: House-GAN: relational generative adversarial networks for graph-constrained house layout generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, Part I, vol. 12346, pp. 162–177. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_10
Merino-Gómez, E., Reviriego, P., Moral, F.: Arquitecturas inconclusas: una perspectiva desde la Inteligencia Artificial. EGA 28(48), 254–267 (2023)
Jaruga-Rozdolska, A.: Artificial intelligence as part of future practices in the architect’s work: MidJourney generative tool as part of a process of creating an architectural form. Architectus 3(71), 95–104 (2022)
Yildirim, E.: Text-to-image generation AI in architecture. In: Kozlu, H.H. (ed.) Art and Architecture: Theory, Practice and Experience, vol. 97. Livre de Lyon, Lyon (2022)
Gajjar, C.P.: Re_Imaged: reimaging architecture through artificially intelligent generated images. Doctoral dissertation, Virginia Tech (2023)
Molina-Siles, P., Ribera, M.G.: Inteligencia artificial y creatividad para la generación de imágenes arquitectónicas a partir de descripciones textuales en Midjourney. Emulando a Louis I. Kahn. EGA Expresión Gráfica Arquitectónica 28(49), 238–251 (2023)
Paananen, V., Oppenlaender, J., Visuri, A.: Using text-to-image generation for architectural design ideation. arXiv preprint arXiv:2304.10182 (2023)
Ploennigs, J., Berger, M.: AI art in architecture. AI Civ. Eng. 2(8) (2023)
Fernández-Morales, A.: Explorando las posibilidades de Midjourney para la generación de plantas de distribución. In: Horizontes Gráficos. Proceedings of the XX Congreso Internacional de Expresión Gráfica Arquitectónica (2024, in press)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fernández-Morales, A. (2024). The Possibilities of Text-to-Image Tools for the Generation of Floor Plans. In: Hermida González, L., Xavier, J.P., Amado Lorenzo, A., Fernández-Álvarez, Á.J. (eds) Graphic Horizons. EGA 2024. Springer Series in Design and Innovation , vol 43. Springer, Cham. https://doi.org/10.1007/978-3-031-57575-4_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-57575-4_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-57574-7
Online ISBN: 978-3-031-57575-4
eBook Packages: EngineeringEngineering (R0)