GENERATIVE TECHNOLOGIES AS A TOOL FOR FORMING THE VISUAL LANGUAGE OF CONTEMPORARY GRAPHIC DESIGN
DOI:
https://doi.org/10.32782/uad.2026.3.28Keywords:
generative technologies, generative artificial intelligence, graphic design, visual language, diffusion models, GAN, neural style transfer, typography, authorship, ethicsAbstract
The above article investigates how generative technologies will likely evolve the visual language of modern graphic design. This study attempts to establish how generative systems (from procedural and parametric to Generative AI) will influence various aspects of the design process including; the creation of forms, arrangement of components, color use, typography, textures, authorship, ethics and workflow. The methodology used by this article includes analysis of the primary technical source material documenting these new technologies, a comparative examination of the official documentation/policies of the platforms supporting these technologies and art historical/ compositional/stylistic readings of both Ukrainian and foreign studies concerning the visual language, digital design and reference to AI and image generation. This article also presents arguments against viewing generative technology as an independent creative agent. Instead it views generative technology as a "project space" where the designer sets boundaries for variability, creates criteria for selecting output, edits output, refines output through editorial processes and legitimates the outcome. The results of this study demonstrate that generative technologies have the largest effect on morphological characteristics of images created, seriality of compositional elements within those images, density of textures within those images and speed at which designers can explore concepts. However, other areas related to graphic design are either less impacted by generative technologies or only partially addressed including precision in typography, structural layout, issues of copyright, and the lack of transparency regarding generative decision making. One key aspect of this article is its focus on comparative analyses of several generative technologies including Midjourney and the DALL-E family, along with the current OpenAI image stack (Stable Diffusion/SDXL), ControlNet, InstructPix2Pix. Additionally, the article reviews several academic based generative design tools including LayoutDM, MetaDesigner and some newer human centered AI typography design frameworks. A central aspect of this articles scholarly contribution is establishing relationships between specific technical capabilities associated with generative systems and specific dimensional aspects of graphic designs visual language. Furthermore, the article provides practical methodological guidance for designers working with generative technology
References
Вискварка Я. Сутність та становлення візуальної мови графічного дизайну в Україні. Наукові записки Тернопільського національного педагогічного університету імені В. Гнатюка. Серія : Мистецтвознавство. 2018. № 2. URL: https://journals.uran.ua/index.php/2411-3271/article/view/173726 .
Goodfellow I.J., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y. Generative Adversarial Nets. 2014. URL: https://arxiv.org/abs/1406.2661.
Sohl-Dickstein J., Weiss E.A., Maheswaranathan N., Ganguli S. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. 2015. URL: https://arxiv.org/abs/1503.03585.
Gatys L. A., Ecker A. S., Bethge M. A Neural Algorithm of Artistic Style. 2015. URL: https://arxiv.org/abs/1508.06576.
Ho J., Jain A., Abbeel P. Denoising Diffusion Probabilistic Models. 2020. URL: https://arxiv.org/abs/2006.11239.
Rombach R., Blattmann A., Lorenz D., Esser P., Ommer B. High-Resolution Image Synthesis with Latent Diffusion Models. 2022. URL: https://arxiv.org/abs/2112.10752.
Ramesh A., Dhariwal P., Nichol A., Chu C., Chen M. Hierarchical Text-Conditional Image Generation with CLIP Latents. 2022. URL: https://arxiv.org/abs/2204.06125.
Zhang L., Rao A., Agrawala M. Adding Conditional Control to Text-to-Image Diffusion Models. 2023. URL:https://arxiv.org/abs/2302.05543.
Brooks T., Holynski A., Efros A. A. InstructPix2Pix: Learning to Follow Image Editing Instructions. 2023. URL: https://openaccess.thecvf.com/content/CVPR2023/papers/Brooks_InstructPix2Pix_Learning_To_Follow_Image_Editing_Instructions_CVPR_2023_paper.pdf.
Chai S., Zhuang L., Yan F. LayoutDM: Transformer-Based Diffusion Model for Layout Generation. 2023. URL: https://openaccess.thecvf.com/content/CVPR2023/papers/Chai_LayoutDM_Transformer-Based_Diffusion_
Model_for_Layout_Generation_CVPR_2023_paper.pdf.
Vinker Y. Generative Visual Communication in the Era of Vision-Language Models. 2024. URL: https://arxiv.org/abs/2411.18727.
He J.-Y. та ін. MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis. 2024. URL: https://arxiv.org/abs/2406.19859.
Dong Y., Gao M. AI-Driven Typography: A Human-Centered Framework for Generative Font Design Using Large Language Models. Information. 2026. Vol. 17, No. 2. Art. 150. DOI: 10.3390/info17020150.
Капелька А. О. Використання штучного інтелекту під час створення графічних проєктів у сучасному дизайні. Український мистецтвознавчий дискурс. 2025. № 6. С. 104–110. DOI: 10.32782/uad.2025.6.12.
Каменецька Ю., Артеменко Р., Коваль А. AI-референси як інструмент формування візуального стилю у цифровому дизайні. Інформаційні технології та суспільство. 2025. Вип. 4 (19). С. 68–73. DOI: 10.32689/maup.it.2025.4.11
Гладун О. Український плакат: етапи розвитку візуально-пластичної мови. Збірник наукових праць «Сучасне мистецтво». 2018. № 14. С. 115–122. DOI: 10.31500/2309-8813.13.2018.152212
Сбітнєва Н., Ганоцька О. Візуальна мова сучасного графічного дизайну України. Актуальні питання гуманітарних наук. 2024. Вип. 80. Т. 2. С. 87–94. DOI: 10.24919/2308-4863/80-2-12
Liu Wei, Kolisnyk O. Parametric modeling as an innovative approach in graphic design = Параметричне моделювання як інноваційний підхід у графічному дизайні. Art and Design. 2024. № 1 (25). С. 34–45. DOI:10.30857/2617-0272.2024.1.3
UNESCO. Recommendation on the Ethics of Artificial Intelligence. URL: https://www.unesco.org/en/artificial-intelligence/recommendation-ethics .
European Commission. AI Act. URL: https://digital-strategy.ec.europa.eu/en/policies/regulatoryframework-ai.
AI Act Service Desk. FAQ; Code of Practice on marking and labelling AI-generated content. URLs: https://ai-act-service-desk.ec.europa.eu/en/faq; https://ai-act-service-desk.ec.europa.eu/en/resources.
Midjourney. Comparing Midjourney Plans. URL: https://docs.midjourney.com/hc/en-us/articles/27870484040333-Comparing-Midjourney-Plans.
Midjourney. Terms of Service. URL: https://docs.midjourney.com/hc/en-us/articles/32083055291277-Termsof-Service.
OpenAI. Europe Terms of Use. URL: https://openai.com/policies/terms-of-use/.
OpenAI. GPT Image 1.5 Model. URL: https://developers.openai.com/api/docs/models/gpt-image-1.5.
OpenAI. DALL·E 3 Model. URL: https://developers.openai.com/api/docs/models/dall-e-3.
OpenAI. Image generation guide; All models. URLs: https://developers.openai.com/api/docs/guides/imagegeneration.
Stability AI. Stability AI License. URL: https://stability.ai/license.
U.S. Copyright Office. Copyright and Artificial Intelligence, Part 2: Copyrightability. URL: https://www.copyright.gov/ai/
