AI-Driven Design: Using Generative Models for Floor Plan Automation


Authors : Khushboo Nijhawan

Volume/Issue : Volume 10 - 2025, Issue 1 - January


Google Scholar : https://tinyurl.com/3uvvyd2f

Scribd : https://tinyurl.com/ztym54th

DOI : https://doi.org/10.5281/zenodo.14651296


Abstract : The project explores the use of advanced AI technologies and generative models to automate the creation of floor plans. This initiative leverages tools such as ComfyUI and models like Stable Diffusion, LoRA, ELLA, and ControlNet to streamline the design process by translating textual prompts and boundary inputs into detailed floor layouts. This proof of concept establishes a foundation for future work, including the integration of generative outputs into CAD workflows, enhanced dataset training, and the development of user-friendly interfaces for real-time customization. The study also compares the approach with existing tools like Maket.ai and Revit Generative Design, underscoring the competitive edge of AI-driven methodologies in automating floor plan design.

References :

  1. X. Li, J. Benjamin, and X. Zhang, "From Text to Blueprint: Leveraging Text-to-Image Tools for Floor Plan Creation," arXiv preprint arXiv:2405.17236, May 2024.
  2. Y. Jeon, D. Q. Tran, and S. Park, "Skip-Connected Neural Networks with Layout Graphs for Floor Plan Auto-Generation," arXiv preprint arXiv:2309.13881, Sep. 2023.
  3. J. Ploennigs and M. Berger, "Automating Computational Design with Generative AI," arXiv preprint arXiv:2307.02511, Jul. 2023.
  4. S. Leng, Y. Zhou, M. H. Dupty, W. S. Lee, S. C. Joyce, and W. Lu, "Tell2Design: A Dataset for Language-Guided Floor Plan Generation," arXiv preprint arXiv:2311.15941, Nov. 2023.
  5. Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, "Electron spectroscopy studies on magneto-optical media and plastic substrate interface," IEEE Transl. J. Magn. Japan, vol. 2, pp. 740-741, Aug. 1987 [Digests 9th Annual Conf. Magnetics Japan, p. 301, 1982].
  6. M. T. Brown, Deep Learning for Image Synthesis: Applications in Architecture and Design, 1st ed., vol. 1. New York: Springer, 2020, pp. 34-45.
  7. P. Wang, H. Liu, and J. Zhao, "Fine-tuning diffusion models for generative architectural tasks," in Advances in Generative Design, vol. II, T. Scott and L. Perez, Eds. London: Taylor & Francis, 2023, pp. 78-95.
  8. K. Zhang, "Generative AI applications in real estate: Automated design and annotation," unpublished.
  9. R. Kumar and N. Patel, "Integrating LoRA and ControlNet for enhanced image-to-floor-plan conversion," Arch. Design J., in press.
  10. L. Martinez, Generative AI and Design Automation: Concepts and Applications, 1st ed. Cambridge, MA: MIT Press, 2022, pp. 89-120.

The project explores the use of advanced AI technologies and generative models to automate the creation of floor plans. This initiative leverages tools such as ComfyUI and models like Stable Diffusion, LoRA, ELLA, and ControlNet to streamline the design process by translating textual prompts and boundary inputs into detailed floor layouts. This proof of concept establishes a foundation for future work, including the integration of generative outputs into CAD workflows, enhanced dataset training, and the development of user-friendly interfaces for real-time customization. The study also compares the approach with existing tools like Maket.ai and Revit Generative Design, underscoring the competitive edge of AI-driven methodologies in automating floor plan design.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe