Graphic design is a pillar of visual communication, which has traditionally been reliant on a complex mix of technical expertise, creative skill and human instinct. The rapid evolution of Artificial Intelligence (AI) and generative models has opened avenues to transform the design industry, moving it towards a collaborative approach where humans and AI work in tandem [1], [2]. Many current platforms rely on static template-based structures that severely limit creativity, or generate flattened images that prevent granular editing [5], [6]. Moreover, many existing algorithms lack cultural and visual semantic backing, leading to overly generalized outputs that do not cater to regional preferences [7], [8]. To address these challenges, we present ARTURE, an AI-enhanced web-based design platform that bridges the gap between rudimentary template-based tools and professional design software. The system combines Natural Language Processing with vector-based semantic search to retrieve culturally adaptable templates mapped to the user’s prompt. The proposed architecture outputs structured, multi-layer design data rendered on an editable web canvas, enabling a fully-editable interface for text, uploaded media, and template layout [9], [10]. A human-in-the- loop approach preserves complete designer control while enhancing productivity [11], [12]. Results highlight the potential of AI as a creative companion that democratizes professional-grade graphic design.

ARTURE demonstrates that structured, editable, culturally-aware AI-generated design is achievable within a single web-based platform. By combining NLP-driven prompt interpretation, vector-based semantic template retrieval, hybrid AI inference, and Fabric.js canvas rendering, the system bridges the long-standing gap between accessible template tools and professional-grade design software. The implementation confirms that AI is most effective not as a replacement for human creativity but as a collaborative partner that handles structural composition while the designer retains full authority over every detail. The platform’s modular architecture positions it well for future expansion into 3D design, real-time collaboration, and richer cultural representation, pointing toward a more inclusive and democratized design ecosystem.

[1]U. Nagargoje, S. Naral, D. Palve, K. Lahare, and S. Ladge, “Artificial Intelligence in Modern Graphic Design: Transforming Creativity and Workflow,” IJIRT, vol. 11, no. 12, 2025. [2]S. Sharma and J. Prakash, “Generative Design: AI-Powered Creativity in Graphic Design,” IJCRT, 2024. [3]K. Fleischmann, “Generative Artificial Intelligence in Graphic Design Education: A Student Perspective,” CJLT/RCAT, vol. 50, no. 1, 2024. [4]P. O’Donovan, A. Agarwala, and A. Hertzmann, “DesignScape: Design with Interactive Layout Suggestions,” in Proc. ACM CHI, 2015. [5]J. Li, J. Yang, A. Hertzmann, J. Zhang, and T. Xu, “Attribute-Conditioned Layout GAN for Automatic Graphic Design,” IEEE Trans. Vis. Comput. Graphics, 2020. [6]Y. Huang, T. Lv, L. Cui, Y. Lu, and F. Wei, “LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking,” in Proc. ACM Multimedia, 2022. [7]M. Hui, Z. Zhang, X. Zhang, W. Xie, Y. Wang, and Y. Lu, “Unifying Layout Generation with a Decoupled Diffusion Model,” in Proc. IEEE/CVF CVPR, 2023. [8]Z. Tang, C. Wu, J. Li, and N. Duan, “LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models,” arXiv:2309.09506, 2023. [9]Z. Zhang et al., “CreatiPoster: Towards Editable and Controllable Multi- Layer Graphic Design Generation,” ACM Trans. Graphics, 2025. [10]O. Peckham et al., “Artificial Intelligence in Generative Design: A Structured Review of Trends and Opportunities,” Designs, vol. 9, no. 79, 2025. [11]M. Feller, Y. Xu, L. Skitka, and S. Lerman, “Mitigating Bias in Algorithmic Design: A Multifaceted Approach,” in Proc. FAT, 2023. [12]J. McCormack, T. Gifford, and P. Hutchings, “Autonomy, Authenticity, Authorship and Intention in Computer Generated Art,” Computational Creativity Research, 2019. [13]K. Wong, B. Friedman, M. Sundararajan, M. Resnick, and J. Keller, “The Trouble with Bias in Algorithmic Design Tools,” in Proc. ACM CHI, 2023. [14]M. Kretzschmar et al., “Evaluating the Role of Generative AI in Product Development and Design — A Systematic Review,” in Proc. NordDesign, 2024. P. M. Khanolkar, A. Vrolijk, and A. Olechowski, “A Case Study of the Decision Making Behind the Automation of a Composites Based Design Process,” in Proc. Design Society, 2023.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close