EUVIMEDEUVIMED entdecken
Crossref

Leveraging Artificial Intelligence and Machine Learning for Artistic Creativity

M. A. Kumar, Saurabh Soni Lamba, Utsha Sarker, Lalit Vaishnav, Archy Biswas

International Journal of Innovative Science and Research Technology · 11.03.2026 · 207

DOI: 10.38124/ijisrt/26mar309 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 11.03.2026. Verfasst von M. A. Kumar und 4 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of artificial intelligence (AI) has changed the practice of art forever and enables machines to become an active participant in the creative process in the fields of visual art, musical composition and literary composition. The emergence of large-scale generative models has led to an increase in both research and practice interest in AI-driven creativity, and the questions that it raises about authorship, originality and human-AI collaboration [15], [17]. This paper surveys the recent progress of AI-powered artistic systems, ranging from visual generation to style transfer, generating music to the creation of text. We discuss basic model families, namely the Generative Adversarial Networks (GANs), transformer based large language models and diffusion models, their technical foundation and their creative affordance [1], [6], [20]. By bringing together developments of controllable diffusion structures for image stylisation [3], [4], human-AI co-creation systems [11], [14], and empirical analyses of the creativity of large language models [18], we offer a common view on computational creativity. Our principal contributions are three-fold. First of all, we propose a taxonomy of AI - creative systems based on the generative mechanism, degree of human involvement and domain specificity. Second, we report out a comparative analysis of GAN -, transformer - , diffusion - based approaches, in terms of controllability, interpretability, scalability and creative diversity. Third, we highlight some key challenges, such as evaluation metrics for creativity, ethical issues, bias propagation, IP (intellectual property) issues, and the questions of co-[ creativity], and propose some directions of future research towards the problem of responsible and human centred AI-driven artistic innovation. [12], [17].

Zitieren

APA

Kumar, M. A., Lamba, S. S., Sarker, U., Vaishnav, L., & Biswas, A. (2026). Leveraging Artificial Intelligence and Machine Learning for Artistic Creativity. International Journal of Innovative Science and Research Technology, 207. https://doi.org/10.38124/ijisrt/26mar309

Vancouver

Kumar MA, Lamba SS, Sarker U, Vaishnav L, Biswas A. Leveraging Artificial Intelligence and Machine Learning for Artistic Creativity. International Journal of Innovative Science and Research Technology. 2026:207. doi:10.38124/ijisrt/26mar309

BibTeX
@article{Kumar2026,
  author = {Kumar, M. A. and Lamba, Saurabh Soni and Sarker, Utsha and Vaishnav, Lalit and Biswas, Archy},
  title = {Leveraging Artificial Intelligence and Machine Learning for Artistic Creativity},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  pages = {207},
  doi = {10.38124/ijisrt/26mar309}
}
Kostenlos starten →