Hostname: page-component-cb9f654ff-pvkqz Total loading time: 0 Render date: 2025-08-29T02:03:41.617Z Has data issue: false hasContentIssue false
  • English
  • Français

EXPLORING THE ROLE OF TEXT-TO-IMAGE AI IN CONCEPT GENERATION

Published online by Cambridge University Press:  19 June 2023

Ross Brisco ,
Laura Hay  and
Sam Dhami
Ross Brisco*
Affiliation:
University of Strathclyde
Laura Hay
Affiliation:
University of Strathclyde
Sam Dhami
Affiliation:
University of Strathclyde
*
Brisco, Ross, University of Strathclyde, United Kingdom, ross.brisco@strath.ac.uk

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Artificial intelligence (AI) capable of generating images from a text prompt are becoming increasingly prevalent in society and design. The general public can use their computers and mobile devices to ask a complex text-to-image AI to create an image which is in some cases indistinguishable from that which a human could create using a computer graphics package. These images are shared on social media and have been used in the creation of art projects, documents and publications. This exploratory study aimed to identify if modern text-to-image AI (Midjourney, DALL-E 2, and Disco Diffusion) could be used to replace the designer in the concept generation stage of the design process. Teams of design students were asked to evaluate AI generated concepts from 15 to a final concept. The outcomes of this research are a first of its kind for the field of engineering design, in the identification of barriers in the use of current text-to-image AI for the purpose of engineering design. The discussion suggests how this can be overcome in the short term and what knowledge the research community needs to build to overcome these barriers in the long term.

Keywords

Artificial intelligenceConceptual designtext-to-imageDesign processConcept Generation

Information

Type
Article
Information
Proceedings of the Design Society , Volume 3: ICED23 , July 2023 , pp. 1835 - 1844
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2023. Published by Cambridge University Press

References

Alymani, A., Mujica, A., Jabi, W., & Corcoran, P. (2022). Classifying Building and Ground Relationships Using Unsupervised Graph-Level Representation Learning. Design Computing and Cognition DCC’22. https://www.researchgate.net/publication/361811023Google Scholar
Ayele, W. Y., & Juell-Skielse, G. (2021). A Systematic Literature Review about Idea Mining: The Use of Machine-Driven Analytics to Generate Ideas. In Advances in Intelligent Systems and Computing (Vol. 1364, pp. 744–762). Springer, Cham. https://doi.org/10.1007/978-3-030-73103-8_53Google Scholar
Beetham, H., & Sharpe, R. (2019). Rethinking pedagogy for a digital age: principles and practices of design (3rd ed.). Routeledge. https://doi.org/https://doi.org/10.4324/9781351252805CrossRefGoogle Scholar
Berisha, B., & Lobov, A. (2021). Overview and Trends for Application of AI Methods for Product Design. IEEE International Conference on Industrial Informatics (INDIN), 2021-July. https://doi.org/10.1109/INDIN45523.2021.9557531CrossRefGoogle Scholar
Pena, Castro, Carballal, M. L., Rodríguez-Fernández, A., Santos, N., & Romero, I., J. (2021). Artificial intelligence applied to conceptual design. A review of its use in architecture. Automation in Construction, 124. https://doi.org/10.1016/J.AUTCON.2021.103550Google Scholar
Cornock, S., & Edmonds, E. (1973). The Creative Process Where the Artist Is Amplified or Superseded by the Computer. Leonardo, 6(1), 11–16.CrossRefGoogle Scholar
Deprez, L., Verstraeten, R., & Pauwels, P. (2022). Data-based Generation of Residential Floorplans Using Neural Networks. Design Computing and Cognition DCC’22.Google Scholar
Figoli, F. A., Mattioli, F., & Rampino, L. (2022). AI in the design process: training the human-AI collaboration. International Conference on Engineering and Product Design Education . https://doi.org/10.35199/EPDE.2022.61CrossRefGoogle Scholar
Gero, J. S., & Kannengiesser, U. (2014). The Function-Behaviour-Structure Ontology of Design. An Anthology of Theories and Models of Design, 263–283. https://doi.org/10.1007/978-1-4471-6338-1_13CrossRefGoogle Scholar
Karimi, P., Grace, K., Davis, N., & Maher, M. lou. (2019). Creative Sketching Apprentice: Supporting Conceptual Shifts in Sketch Ideation. In Design Computing and Cognition ’18 (pp. 721–738). Springer International Publishing. https://doi.org/10.1007/978-3-030-05363-5_39CrossRefGoogle Scholar
Koh, I. (2022). Voxel Substitutional Sampling: Generative Machine Learning for Architectural Design. Design Computing and Cognition ’22.Google Scholar
Le, M., & Jung, E. C. (2020). Analysis of intent-design relationship for artificial intelligence design agent model based on product purchasing process. Proceedings of the Design Society: DESIGN Conference, 1, 285–294. https://doi.org/10.1017/dsd.2020.146Google Scholar
Maher, M. L., & Fisher, D. H. (2012). Using AI to evaluate creative designs.Google Scholar
Poole, B., Jain, A., Barron, J. T., & Mildenhall, B. (2022). DreamFusion: Text-to-3D using 2D Diffusion. http://arxiv.org/abs/2209.14988Google Scholar
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical Text-Conditional Image Generation with CLIP Latents. ArXiv, abs/2204.06125. https://doi.org/10.48550/ARXIV.2204.06125CrossRefGoogle Scholar
Sosa, R., & Gero, J. S. (2016). Multi-dimensional creativity: a computational perspective. International Journal of Design Creativity and Innovation, 4(1), 26–50. https://doi.org/10.1080/21650349.2015.1026941CrossRefGoogle Scholar
Torkkeli, M., & Tuominen, M. (2002). The contribution of technology selection to core competencies. Int. J. Production Economics, 77(3), 271–284.CrossRefGoogle Scholar
Umeda, Y., & Tomiyama, T. (1997). Functional Reasoning in Design. IEEE Expert, 21(2). https://doi.org/10.1109/64.585103Google Scholar
Urquhart, L., Wodehouse, A., Loudon, B., & Fingland, C. (2022). The Application of Generative Algorithms in Human-Centered Product Development. Applied Sciences, 12(7). https://doi.org/10.3390/app12073682CrossRefGoogle Scholar
Wang, D., Li, J., Ge, Z., & Han, J. (2021). A computational approach to generate design with specific style. Proceedings of the Design Society International Conference on Engineering Design, ICED21, 1, 21–30. https://doi.org/10.1017/pds.2021.3CrossRefGoogle Scholar
Wu, Y., Zhou, Y., Zhou, Z., Tang, J., & Ouyang, H. (2018). An advanced CAD/CAE integration method for the generative design of face gears. Advances in Engineering Software, 126, 90–99. https://doi.org/10.1016/j.advengsoft.2018.09.009CrossRefGoogle Scholar
Yoo, S., Lee, S., Kim, S., Hwang, K. H., Park, J. H., & Kang, N. (2021). Integrating deep learning into CAD/CAE system: generative design and evaluation of 3D conceptual wheel. Structural and Multidisciplinary Optimization, 64(4), 2725–2747. https://doi.org/10.1007/s00158-021-02953-9CrossRefGoogle Scholar