Authors : Dr. M. A. Kumar; Saurabh Soni Lamba; Utsha Sarker; Lalit Vaishnav; Archy Biswas

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/zwv9rh6r

Scribd : https://tinyurl.com/mstuu8ke

DOI : https://doi.org/10.38124/ijisrt/26mar309

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : 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].

Keywords : Fusional HI (Hyperfocal Intensity), AI (Artificial Intelligence), ML (Machine Learning), Generative Art, Computational Creativity, Generative Adversarial Networks (GANs), Diffusion Models, Creative Support Tools, Human - AI Co -Creation.

References :

1. L. Zhang, A. Rao, and M. Agrawala, “Adding conditional control to text-to-image diffusion models,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023, pp. 3836–3847.
2. D.-Y. Chen, H. Tennent, and C.-W. Hsu, “ArtAdapter: Text-to-image style transfer using multi level style encoder and explicit adaptation,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2024, pp. 8619–8628.
3. J. Chung, S. Hyun, and J.-P. Heo, “Style injection in diffusion: A training-free approach for adapting large-scale diffusion models for style transfer,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2024, pp. 8795–8805.
4. T. Qi et al., “DEADiff: An efficient stylization diffusion model with disentangled representations,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2024, pp. 8693–8702.
5. M. Hamazaspyan and S. Navasardyan, “Diffusion-enhanced PatchMatch: A framework for arbitrary style transfer with diffusion models,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jun. 2023, pp. 797–805, doi: 10.1109/CVPRW59228.2023.00087.
6. Z. Wang, L. Zhao, and W. Xing, “StyleDiffusion: Controllable disentangled style transfer via diffusion models,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2023, pp. 7677–7689.
7. S. Yang, H. Hwang, and J. C. Ye, “Zero-shot contrastive loss for text-guided diffusion image style transfer,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2023, pp. 22873–22882.
8. S. Li, “DiffStyler: Diffusion-based localized image style transfer,” arXiv preprint, arXiv:2403.18461, 2024.
9. J. Sun and C. Meng, “StyDiff: Creative style transfer using latent diffusion models,” Sci. Rep., vol. 15, Art. no. 33521, 2025.
10. S. Li et al., “CSFer: A deep learning model for creative style transfer,” Knowl.-Based Syst., vol. 332, Art. no. 112330, 2025.
11. Z. Liu et al., “A human-AI co-creation framework for enhancing creativity and satisfaction in AI-assisted drawing,” arXiv preprint, arXiv:2504.00980, 2025.
12. X. Hu et al., “Designing interactions with generative AI for art and creativity: A systematic review and taxonomy,” in Proc. ACM Designing Interactive Systems Conf. (DIS ’25), 2025, pp. 1126–1155, doi: 10.1145/3715336.3735843.
13. Y. Fu et al., “Exploring the collaborative co-creation process with AI: A case study in novice music production,” arXiv preprint, arXiv:2501.15276, 2025.
14. C. Moruzzi and S. Margarido, “A user-centered framework for human-AI co-creativity,” in Extended Abstracts CHI Conf. Human Factors Comput. Syst. (CHI EA ’24), May 2024, doi: 10.1145/3613905.3650929.
15. T. Chakrabarty, V. Padmakumar, F. Brahman, and S. Muresan, “Creativity support in the age of large language models: An empirical study involving emerging writers,” arXiv preprint, arXiv:2309.12570, 2024.
16. J. Rafner et al., “Agency in human-AI collaboration for image generation and creative writing: Preliminary insights from think-aloud protocols,” Creativity Research Journal, pp. 1–24, Dec. 2025, doi: 10.1080/10400419.2025.2587803.
17. K. E. Medeiros, D. H. Cropley, R. L. Marrone, and R. Reiter-Palmon, “Human-AI co-creativity: Does ChatGPT make us more creative?” J. Creative Behavior, vol. 59, no. 2, 2025, doi: 10.1002/jocb.70022.
18. L. Sun et al., “Large language models show both individual and collective creativity comparable to humans,” Thinking Skills and Creativity, vol. 57, Art. no. 101870, 2025, doi: 10.1016/j.tsc.2025.101870.
19. G. Franceschelli and M. Musolesi, “On the creativity of large language models,” arXiv preprint, arXiv:2304.00008, 2023 (rev. 2025).
20. Q. Huang et al., “Noise2Music: Text-conditioned music generation with diffusion models,” arXiv preprint, arXiv:2302.03917, 2023.