The purpose of the article is in finding out the level of influence of Artificial Intelligence on the graphic design on the example of operationalization of neural networks, which made generative graphics possible, allowed for a high variability of parameters, as well as adjusting the color scheme, contrast, and geometric proportions of the objects being created. Research methods. The empirical method, the method of analysis and synthesis, as well as qualitative research methods were used, which, in particular, include the study of scientific, popular and web sources on the use of generative networks and AI in graphic design; the features and functional parameters of individual neural networks in the context of the topic of the article were analyzed. In addition, along with a review of the latest research on the topic, the relationship between experimental and scientific research in graphic design today and the development of generative design as a promising technology with a wide range of applications and a method for designing functional structures of graphic design, UI/UX design, animation, etc. is clarified. Scientific novelty. The article presents for the first time a comprehensive approach to the problem of applying AI and generative neural networks in graphic design, and considers, in particular, the potential, advantages, and disadvantages of specific neural networks, such as DALL-E, DALL-E 2, Stable Diffusion, MidJourney, and Craiyon, when generating compositional and graphic solutions. Conclusions. It was found out that generative neural networks are one of the most popular types of AI in the design industry in the first quarter of the twenty-first century. Neural networks such as DALL-E, DALL-E 2, Stable Diffusion, MidJourney, and Craiyon, or professional programs such as InDesign or Illustrator, have definitely become indispensable for many graphic designers today, who use them to reproduce, transform, and synthesize images, manipulate elements according to the needs of users, improve and edit variations of generated images, as well as adjust geometric proportions, color and contrast of objects, and use a high variability of parameters.
Read full abstract