Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192135,
        author = {Devadarshini P and Dr. Mary Louis L},
        title = {LoRA-Enhanced Diffusion-Based Framework for Automated Comic Book Image Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {358-366},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192135},
        abstract = {The rapid progress of generative artificial intelligence has enabled automated image synthesis from natural language descriptions. However, producing domain-specific artistic content with a consistent visual style remains a challenging task. Comic book illustration demands expressive characters, bold line art, coherent visual themes, and stylistic consistency across generated images. This paper presents a LoRA-enhanced diffusion-based framework for automated comic book image generation. It transforms textual prompts into high-quality comic-style illustrations. The proposed system is built on a latent diffusion architecture and uses Low-Rank Adaptation to efficiently specialize the model for comic-specific visual characteristics, without retraining the entire network. By introducing parameter-efficient adaptations, the framework achieves improved style control, reduced computational overhead, and enhanced consistency compared to conventional diffusion-based generation. The results indicate that integrating diffusion models with LoRA provides an effective and scalable solution for creative content generation and digital storytelling applications.},
        keywords = {Comic Book Generation, Diffusion Models, Low-Rank Adaptation, Text-to-Image Synthesis, Style Consistency, Creative AI},
        month = {February},
        }