Abstract
The implementation of neural networks in the creative design process enables original and innovative results and increased efficiency in creating a visual art product, and therefore it is important to explore how various interactive tools can contribute to the development of the creative abilities of future design professionals. The purpose of this study was to investigate the capabilities and characteristics of Midjourney, Stable Diffusion, and DALL-E neural networks in the context of their use in teaching design students. The study used the analytical method, comparison, generalisation, and systematisation methods. The study found that the neural networks Midjourney, Stable Diffusion and DALL-E have prospects for implementation in the educational process for students of design specialities. The authors of this paper revealed the significant potential of artificial intelligence, namely neural networks, in design, namely for creating fonts, typographic elements, posters, banners, graphics, and illustrations. By comparing the capabilities of the Midjourney, Stable Diffusion, and DALL-E neural networks, it was found that each of them has a specific purpose and architecture that is effective for performing various design tasks. The findings of the study demonstrate the potential of neural networks to improve the education of students of design-related specialities. It was substantiated that the introduction of suitable methods and techniques can help expand the creative spectrum, ensure stability and control in generating images, and lead to a more effective implementation of ideas in visual realities. The results of this study can be useful as tools for developing educational approaches in the field of design and introducing modern technologies into the educational process.
Keywords
visual image; idea generation; software; modern education; artificial intelligence
References
[1] Alışık, E. (2022). “All compressed and rendered with a pathetic delicacy that astounds the eye”: Midjourney renders ambergris as Constantinople. CyberOrient, 16(2), 76-88. doi: 10.1002/cyo2.30.
[2] Borji, A. (2022). Generated faces in the wild: Quantitative comparison of stable diffusion, Midjourney and DALL-e 2. doi: 10.48550/arXiv.2210.00586.
[3] Bozhko, T., & Arefiev, V. (2023). Neural networks as a graphic design tool. Bulletin of KNUKiM. Series in Arts, 48, 125-135. doi: 10.31866/2410-1176.48.2023.282475.
[4] Byrne, U. (2023). A parochial comment on Midjourney. International Journal of Architectural Computing, 21(2), 374-379. doi: 10.1177/14780771231170271.
[5] Cetinic, E., & She, J. (2022). Understanding and creating art with AI: Review and outlook. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 18(2), article number 66. doi: 10.1145/3475799.
[6] Davydova, S.V., & Derevyanko, N.V. (2022). Ethnic design in professional training of future clothing designers. Pedagogical Sciences: Theory and Practice, 1, 129-134. doi: 10.26661/2786-5622-2022-1-19.
[7] Dehouche, N., & Dehouche, K. (2023). What’s in a text-to-image prompt? The potential of stable diffusion in visual arts education. Heliyon, 9(6), article number e16757. doi: 10.1016/j.heliyon.2023.e16757.
[8] Fortuna, P., & Modliński, A. (2021). A(I)rtist or counterfeiter? Artificial intelligence as (d)evaluating factor on the art market. The Journal of Arts Management, Law, and Society, 51(3), 188-201. doi: 10.1080/10632921.2021.1887032.
[9] Justice, L. (2019). The future of design education. Design Management Review, 30(1), 33-37. doi: 10.1111/drev.12159.
[10] Kahng, M., Thorat, N., Chau, D.H., Viégas, F.B., & Wattenberg, M. (2019). Gan lab: Understanding complex deep generative models using interactive visual experimentation. IEEE Transactions on Visualization and Computer Graphics, 25(1), 310-320. doi: 10.1109/TVCG.2018.2864500.
[11] Kolisnyk, O.V., Mykhailova, R.D., Beregovyi, O.S., Vlasiuk, V.V., & Kurovska, D.V. (2023). Midjorney Neural Network as a tool for generating design graphics. Art and Design, 1, 106-115. doi: 10.30857/2617-0272.2023.1.10.
[12] Lee, S., Hoover, B., Strobelt, H., Wang, Z.J., Peng, S., Wright, A., Li, K., Park, H., Yang, H., & Chau, D.H. (2023). Diffusion explainer: Visual explanation for text-to-image stable diffusion. doi: 10.48550/arXiv.2305.03509.
[13] Liu, M., & Hu, Y. (2023). Application potential of stable diffusion in different stages of industrial design. In H. Dehen, & S. Ntoa (Eds.), Artificial Intelligence in HCI: 4th International Conference: Proceedings (Pt 1; pp. 590-609). Cham: Springer. doi: 10.1007/978-3-031-35891-3_37.
[14] Lugova, I.A., & Panchenko, D.D. (2023). Application of artificial intelligence in architectural drawing. In T.M. Zinenko (Ed.), Collection of scientific papers based on the materials of the VI-VII All-Ukrainian scientific and practical conference of students, young scientists and scientific and pedagogical workers “Architectural drawing in the context of professional education” (pp. 199-202). Poltava: National University “Yuri Kondratyuk Poltava Polytechnic”.
[15] Marcus, G., Davis, E., & Aaronson, S. (2022). A very preliminary analysis of DALL-E 2. doi: 10.48550/arXiv.2204.13807.
[16] Marienko, M., & Kovalenko, V. (2023). Artificial intelligence and open science in education. Physical and Mathematical Education, 38(1), 48-53. doi: 10.31110/2413-1571-2023-038-1-007.
[17] Perera, A.S. (2022). DALL·E 2 vs Midjourney vs Stable Diffusion: Comparison between most popular AI art generation tools. Retrieved from https://medium.com/mlearning-ai/dall-e-2-vs-midjourney-vs-stable-diffusion-8eb9eb7d20be.
[18] Romaniuk, O., & Naidiuk, V. (2021). Using neural networks for image processing and recognition. In Abstracts of the XII International Scientific and Technical Conference “Information and computer technologies – 2021 (ICT-2021)” (pp. 72-73). Zhytomyr: Zhytomyr Polytechnic.
[19] UNESCO Education Sector. (2019). Artificial intelligence in education: Challenges and opportunities for sustainable development. Paris: United Nations Educational, Scientific and Cultural Organization.
[20] Wang, B., Liu, H., An, P., Li, Q., Li, K., Chen, L., Zhang, Q., Zhang, J., Zhang, X., & Gu, S. (2019). Artificial intelligence and education. In D. Jin (Ed.), Reconstructing our orders: Artificial intelligence and human society (pp. 129-161). Singapore: Springer. doi: 10.1007/978-981-13-2209-9_5.
[21] Yuan, X., Bi, H., & Niu, X. (2023). Computer-aided teaching system design method for information design specialty. Computer-Aided Design & Applications, 20(S4), 44-55. doi: 10.14733/cadaps.2023.S4.44-55.
[22] Zhou, K.-Q., & Nabus, H. (2023). The ethical implications of DALL-E: Opportunities and challenges. Mesopotamian Journal of Computer Science, 2023, 17-23. doi: 10.58496/MJCSC/2023/003.