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 :
- 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.
- 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.
- J. Ploennigs and M. Berger, "Automating Computational Design with Generative AI," arXiv preprint arXiv:2307.02511, Jul. 2023.
- 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.
- 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].
- M. T. Brown, Deep Learning for Image Synthesis: Applications in Architecture and Design, 1st ed., vol. 1. New York: Springer, 2020, pp. 34-45.
- 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.
- K. Zhang, "Generative AI applications in real estate: Automated design and annotation," unpublished.
- R. Kumar and N. Patel, "Integrating LoRA and ControlNet for enhanced image-to-floor-plan conversion," Arch. Design J., in press.
- 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.