Research on Stylized Image Generation of Local Chronicles Ancient Books Based on LoRA Fine-tuning

Authors

  • Huabiao Li School of Engineers, Zhejiang University, Hangzhou 310000, Zhejiang Province; Data Management and Analysis Center, National Museum of China, Beijing 100000
  • Tianhang Liu School of Electronic Information (School of Artificial Intelligence), Northwest University, Xi’an 710000, Shaanxi Province
  • Bin Wang School of Electronic Information (School of Artificial Intelligence), Northwest University, Xi’an 710000, Shaanxi Province

Abstract

To improve the visualization and dissemination efficiency of the content of local chronicles ancient books, this paper explores an artificial intelligence painting generation scheme based on the Low-Rank Adaptation (LoRA) fine-tuning technology, aiming to assist the public to better understand and appreciate the ancient book content by generating intuitive and easy-to-understand illustrations. First, a selected dataset containing a small number of paintings in the style of local chronicles ancient books is constructed and refined annotation is carried out. Then, a pre-trained text-image generation model is used as the basic framework, and the LoRA technology is used to carry out targeted fine-tuning to improve the model’s understanding ability of specific domain texts and the quality of image generation. Finally, the trained LoRA model is combined with the basic model for image generation inference. The experimental results show that this method can reproduce a specific ancient book painting style with high fidelity and accurately translate the text semantics, providing an efficient and low-cost technical path for the digital interpretation and dissemination of cultural heritage.

References

Deng, Xiaoxiao. "Enhancing Neural Network Performance on Tabular Data via Knowledge Distillation and RankGauss Transformation." 2025 6th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE). IEEE, 2025.

Zi, Yun, and Xiaoxiao Deng. "Joint modeling of medical images and clinical text for early diabetes risk detection." Journal of Computer Technology and Software 4.7 (2025).

Ziren, Z. (2026). Dynamic Optimization and Multi-Regional Performance Validation of Automotive Sales Strategies in the United States. Academic Journal of Natural Science, 3(1), 1-7.

Peng, Qucheng, Hongfei Xue, Pu Wang, and Chen Chen. "Lifelong Domain Adaptive 3D Human Pose Estimation." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 10, pp. 8358-8366. 2026.

Zheng, Ce, et al. "Diffmesh: A motion-aware diffusion framework for human mesh recovery from videos." 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 2025.

Tang, Yingheng, et al. "Design and Optimization of Shallow-Angle Grating Coupler for Vertical Emission from Indium Phosphide Devices." (2020).

Sun, Lingxin. "AI-Assisted UI Design: Enhancing Efficiency and Creativity through Generative Tools." Journal of Computer Technology and Applied Mathematics 3.1 (2026): 19-27.

Yang, X., Xue, H., Hu, Q., & Zhang, Y. (2025, October). Design of a full-cycle intelligent risk control system for pre-loan, mid-loan, and post-loan lending: AI-driven closed-loop management of online credit security. In Proceedings of the 2025 2nd International Conference on Digital Economy and Computer Science (pp. 1022-1027).

Shen, Zepeng, et al. "Research on Application of Whale Optimization Algorithm in Financial Payment Fraud Detection." 2025 4th International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID). IEEE, 2025.

Yang, X., & Zhang, Y. (2026). Edge-Enabled Real-Time Fraud Detection for Network Lending Terminals under Low-Latency Constraints. Journal of Computer Technology and Applied Mathematics, 3(1), 55-62.

Zhou, Z. (2025, November). Digital precision distribution strategy for social media content on private domain platforms in the automotive industry: a collaborative filtering model based on user behavior. In Proceedings of the 2025 International Conference on Digital Society and Intelligent Computing (pp. 516-521).

Wensi, L. (2026). AI-Enabled Data Visualization Marketing for Automated Production Lines: Building Customer Trust and Improving Lead-to-Order Conversion. Academic Journal of Natural Science, 3(1), 8-13.

Yang, Z., Zhang, W., Lin, X., Zhang, Y., & Li, S. (2023, April). HGMatch: A Match-by-Hyperedge Approach for Subgraph Matching on Hypergraphs. In 2023 IEEE 39th International Conference on Data Engineering (ICDE) (pp. 2063-2076). IEEE.

Ukey, N., Zhang, G., Yang, Z., Li, B., Li, W., & Zhang, W. (2023). Efficient continuous kNN join over dynamic high-dimensional data. World Wide Web, 26(6), 3759-3794.

Lian, J., & Chen, T. (2024). Research on Complex Data Mining Analysis and Pattern Recognition Based on Deep Learning. Journal of Computing and Electronic Information Management, 12(3), 37-41.

Downloads

Published

2026-05-20

How to Cite

Li, H., Liu, T., & Wang, B. (2026). Research on Stylized Image Generation of Local Chronicles Ancient Books Based on LoRA Fine-tuning. International Journal of Advance in Applied Science Research, 5(4), 45–50. Retrieved from https://h-tsp.com/index.php/ijaasr/article/view/289

Issue

Vol. 5 No. 4 (2026)

Section

Articles

License

Copyright (c) 2026 Huabiao Li, Tianhang Liu, Bin Wang

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.