UNVEILING THE ACCURACY OF AI TEXT TO IMAGE TOOLS VS. HUMAN EXPERTISE IN INTERIOR SPACE DESIGN (A year long journey tracking and evaluating AI text to image tools revolution 2023-2024)

Document Type : Specialized scientific research papers

Author

Assistant professor -Faculty of Arts and design -Msa university -Cairo -Egypt.

10.47436/jaars.2024.279622.1189

Abstract

In an ever-evolving world, Artificial Intelligence tools are rapidly emerging as game-changer in all fields (Interior space design included) in a way that cannot be ignored any more .The time has come to start facing the truth and start evaluating those tools’ accuracy from subject matter expert’s point of view and find ways to utilize it the right way by exploring how to get the best results, and by this answering so many questions, can those tools replace interior designers totally?. Can they really generate very accurate (expert level) results? What is the most reliable tool that can be used as an assistant? The study focus on evaluating the free available text to image tools only (excluding popular mid journey) following the experimental, analysis and comparative method that lead to some important findings. Most important is the perfect prompt writing strategy, Microsoft Bing being the absolute best, technical reasons behind this and much more…

Keywords

Main Subjects

References

Alhabeeb, S. K., & Al-Shargabi, A. A. (2023). Text-to-Image Synthesis with Generative Models: Methods, Datasets, Performance Metrics, Challenges, and Future Direction. IEEE Access. Advance online publication. DOI: 10.1109/ACCESS.2024.3365043
Cao, P., Zhou, F., Song, Q., & Yang, L. (2024). Controllable generation with text-to-image diffusion models: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. Retrieved from https://ar5iv.labs.arxiv.org/html/2403.04279
Chen, J., Shao, Z., & Hu, B. (2023). Generating Interior Design from Text: A New Diffusion Model-Based Method for Efficient Creative Design. Buildings, 13, 1861. https://doi.org/10.3390/buildings1307186
Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M¨ uller, Joe Penna, and Robin Rombach. Sdxl: Improving latent diffusion mod els for high-resolution image synthesis. arXiv preprint arXiv:2307.01952, 2023
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial networks [arXiv preprint arXiv:1406.2661]. Retrieved from http://papers.neurips.cc/paper/5423-generative-adversarial-nets.pdf
Ho, J., Jain, A., Abbeel, P., & Malik, J. (2020). Denoising diffusion probabilistic models. In H. Larochelle, M. Balcan, R. Fergus, S. Bachman, D. Tran, J. Hinton, & E. Xing (Eds.), Advances in Neural Information Processing Systems 33 (pp. 18242-18256). Curran Associates, Inc. https://arxiv.org/abs/2006.11239
McKinsey & Company. (2023). The state of AI in 2023: Generative AI’s breakout year. McKinsey & Company- https://www.mckinsey.com/~/media/mckinsey/business%20functions/quantumblack/our%20insights/the%20state%20of%20ai%20in%202023%20generative%20ais%20breakout%20year/the-state-of-ai-in-2023-generative-ais-breakout-year_vf.pdf
Muller, M. (2023). Generative AI and HCI at CHI 2023 [Workshop]. In CHI '23: Proceedings of the ACM CHI Conference on Human Factors in Computing Systems (pp. 1-6). Association for Computing Machinery: https://www.acm.org
Smith, J. (2024). iDesigner: A high-resolution and complex-prompt following text-to-image diffusion model for interior design. Journal of Interior Design Research, 12(3), 45-67. https://arxiv.org/abs/2312.0432
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In H. Larochelle, M. Balcan, R. Fergus, S. Bachman, D. Tran, J. Hinton, & E. Xing (Eds.), Advances in Neural Information Processing Systems 30 (pp. 3015-3025). Curran Associates, Inc.
Xu, X., Guo, J., Wang, Z., Huang, G., Essa, I., & Shi, H. (2023). Prompt-Free Diffusion: Taking “Text” out of Text-to-Image Diffusion Models (Version 2). arXiv preprint arXiv:2305.16223v2.
Zhao, L., Yuan, Z., Zhang, Y., Wu, S., & Wu, J. (2024). Learning Generative 3D Scene Layouts from a Single Image- CVPR 2024 Workshop on AI for 3D Generation (conference paper ) - (1) (PDF) Learning Generative 3D Scene Layouts from a Single Image (researchgate.net)
Journal of Arts & Architecture Research Studies
Volume 5, Issue 9 - Serial Number 9
JAARS – Volume 5 - Issue 9 - June 2024
June 2024
Pages 60-77

Files

Share

How to cite

Statistics