Generative AI for Cultural Heritage: Shanghai Revolutionary Culture Digital Design Based on the SD–LoRA Model
Source abstract
Abstract
In recent years, the development of generative artificial intelligence, particularly diffusion models such as Stable Diffusion (SD), has provided new opportunities for the digital representation and creative dissemination of cultural heritage. This study takes Shanghai revolutionary cultural heritage as a case study and develops an application-oriented integrated workflow for generating revolutionary cultural images. By introducing Low-Rank Adaptation (LoRA) into the SD framework and combining structural control with local refinement strategies, this study enhances the style expression and structural quality of the generated images. Furthermore, an interactive creation platform is constructed to support the generation and creation of revolutionary cultural images. The evaluation results, including subjective assessment and SSIM/LPIPS metrics, indicate that the proposed workflow achieves higher style consistency and structural reliability while improving the structural integrity and detail reliability of facial regions. The proposed workflow and platform are intended to support revolutionary cultural venues in practical digital production and dissemination of heritage content while also promoting public engagement with revolutionary culture, especially among younger audiences. This study highlights the application potential of generative Artificial Intelligence (AI) in enhancing the accessibility, digitalization, and sustainable dissemination of revolutionary cultural heritage. It also provides a practical reference for interdisciplinary research in the field of cultural heritage and AI-assisted digital communication.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Generative Adversarial Networks and Image Synthesis · Aesthetic Perception and Analysis · Artificial Intelligence Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Fashion & Design, Donghua University, Shanghai 200051, China
Funding
Fundamental Research Funds for the Central Universities
References (70)
Show source-provided references
1. Smith, L. (2006). Uses of Heritage, Routledge.10.4324/9780203602263 ↗
2. Graham, B.J., and Howard, P. (2008). The Ashgate Research Companion to Heritage and Identity, Ashgate.
3. Harrison, R. (2013). Heritage: Critical Approaches, Routledge.10.1093/oxfordhb/9780199602001.013.021 ↗
4. Wang, F., Sanagustín–Fons, V., and Martínez–Quintana, V. (2025). Red Tourism and Youth Education: A Systematic Review of the Literature. Societies, 15.10.3390/soc15030069 ↗
5. From static displays to interactive AR: Evaluating the effectiveness of an AR App for Gen Z and Alpha in Museum Pusaka
6. Lian, Y., and Xie, J. (2024). The evolution of digital cultural heritage research: Identifying key trends, hotspots, and challenges through bibliometric analysis. Sustainability, 16.10.3390/su16167125 ↗
7. Research on innovative applications of AI technology in the field of cultural heritage conservation
8. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18–24). High–resolution image synthesis with latent diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01042 ↗
9. GuidePaint: Lossless image–guided diffusion model for ancient mural image restoration10.1038/s40494-025-01693-z ↗
10. Diffusion model–based image generation method for Cantonese embroidery artistic styles10.1038/s40494-026-02342-9 ↗
11. MuralAgent: Enhancing Ancient Mural Outpainting with RAG–Based Texts and Multimodal Integration10.1145/3743679 ↗
12. Research on the Construction of an AI Platform for Haipai New Year Paintings Based on the Stable Diffusion Model
13. Fine–tuning diffusion model to generate new kite designs for the revitalization and innovation of intangible cultural heritage10.1038/s41598-025-92225-z ↗
14. Can AI–generated art stimulate the sustainability of intangible cultural heritage? A quantitative research on cultural and creative products of New Year Prints generated by AI10.1016/j.heliyon.2023.e20477 ↗
15. Zheng, C.X., and Hua, J. (2025). Annual Report on Shanghai Cultural Industry Development (2025), Shanghai Far East Publishers.
16. Andrews, J.F. (1994). Painters and Politics in the People’s Republic of China, 1949–1979, University of California Press.
17. Guo, R., and Xu, Y. (2025). Spatial Differentiation and Driving Mechanisms of Revolutionary Cultural Tourism Resources in Xinjiang. Sustainability, 17.10.3390/su17219484 ↗
18. Basic types and evolutionary characteristics of the socialist built heritage in China, 1949–1978: Bibliometrics analysis of the People’s Daily10.1186/s40494-024-01136-1 ↗
19. Chen, M., Zhao, B., Zhao, H., Jiang, Q., Zhou, Q., and Tong, H. (2023). Character–defining elements comparison and heritage regeneration for the former command posts of the Jinan campaign—A case of Chinese rural revolutionary heritage. Buildings, 13.10.3390/buildings13081923 ↗
20. Spark aspirations: The role of mental imagery and place memories in virtual communist heritage10.1016/j.jhtm.2024.12.011 ↗
21. Red tourism in China: Emotional experiences, national identity and behavioural intentions10.1108/TR-09-2022-0440 ↗
22. Zhou, H., Zhang, Q., Jiang, Y., and Wang, F. (2023). Can red tourism lead to spiritual transformation? Evidence from tourists visiting the Red Army Long March Xiangjiang Battle Memorial Park. PLoS ONE, 18.10.1371/journal.pone.0280920 ↗
23. Yi, J., Tian, Y., and Zhao, Y. (2024). Novel approach to protect red revolutionary heritage based on artificial intelligence algorithm and image–processing technology. Buildings, 14.10.3390/buildings14093011 ↗
24. Nichol, A.Q., and Dhariwal, P. (2021, January 18–24). Improved denoising diffusion probabilistic models. Proceedings of the International Conference on Machine Learning (ICML), Online.
25. Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., and Van Gool, L. (2022, January 18–24). Repaint: Inpainting using denoising diffusion probabilistic models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01117 ↗
26. Multimodal intelligent reconstruction–driven digital regeneration of cultural heritage in Qing Dynasty tea plantation landscapes10.1038/s40494-025-02183-y ↗
27. Revolutionary posters and cultural signs10.2307/3012520 ↗
28. Cultural politics and iconography: An introduction
29. Denoising diffusion probabilistic models
30. Diffusion models beat GANs on image synthesis
31. Photorealistic text–to–image diffusion models with deep language understanding
32. Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., and Lee, Y.J. (2023, January 18–22). Gligen: Open–set grounded text–to–image generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.02156 ↗
33. Conditional diffusion model with spatial–frequency refinement for sartooptical image translation10.1109/TGRS.2024.3491826 ↗
34. Boundary information–guided adversarial diffusion model for efficient unsupervised synthetic CT generation10.1002/mp.17723 ↗
35. Self–guidance: Boosting flow and diffusion generation on their own10.1109/TPAMI.2025.3611831 ↗
36. Exploring the capability of text–to–image diffusion models with structural edge guidance for multispectral satellite image inpainting10.1109/LGRS.2024.3370212 ↗
37. Single image defocus deblurring via multimodal–guided diffusion and depth–aware fusion10.1016/j.patcog.2025.112133 ↗
38. Inter–view Dual–domain Guided Stable Diffusion for Real–World Stereo Image Super–Resolution10.1016/j.eswa.2025.129201 ↗
39. Global–local image perceptual score (glips): Evaluating photorealistic quality of ai–generated images10.1109/THMS.2025.3527397 ↗
40. Fast Sampling of Score–Based Models with Cyclical Diffusion Sampling10.1109/ACCESS.2024.3365146 ↗
41. Zero–shot reference image segmentation based on fine–tuning of the large image–text model CLIP
42. Designer–Style Clothing Generation Method Based on LoRA Model Fine–Tuning Stable Diffusion
43. Zhang, L., Rao, A., and Agrawala, M. (2023, January 1–6). Adding conditional control to text–to–image diffusion models. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.00355 ↗
44. Wang, X., Li, Y., Zhang, H., and Shan, Y. (2021, January 20–25). Towards real–world blind face restoration with generative facial prior. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00905 ↗
45. Zhou, S., Chan, K., Li, C., and Loy, C.C. (December, January 28). Towards robust blind face restoration with codebook lookup transformer. Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA.
46. Pascual, R., Maiza, A., Sesma–Sara, M., Paternain, D., and Galar, M. (July, January 30). Enhancing dreambooth with lora for generating unlimited characters with stable diffusion. Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan.10.1109/IJCNN60899.2024.10651300 ↗
47. Ryu, H., Lim, S., and Shim, H. (October, January 29). Memory–efficient fine–tuning for quantized diffusion model. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy.
48. Ma, H., and Zheng, H. (2023, January 24–25). Text Semantics to Image Generation: A method of building facades design base on Stable Diffusion model. Proceedings of the International Conference on Computational Design and Robotic Fabrication, Shanghai, China.10.1007/978-981-99-8405-3_3 ↗
49. Bai, B., Xie, H., and Miyata, K. (2024, January 14–15). Fine–Tuning Pipeline for Hand Image Generation Using Diffusion Model. Proceedings of the 2024 Nicograph International (NicoInt), Hachioji, Japan.10.1109/NICOInt62634.2024.00020 ↗
50. Wu, J., Han, B., Zhang, Y., Huang, C., Qiu, S., Feng, W., Liu, Z., and Zou, C. (2025). Enhancing bolt object detection via AIGC–driven data augmentation for automated construction inspection. Buildings, 15.10.3390/buildings15050819 ↗
51. TDASD: Generating medically significant fine–grained lung adenocarcinoma nodule CT images based on stable diffusion models with limited sample size10.1016/j.cmpb.2024.108103 ↗
52. Lyu, Z., Li, Z., and Wu, Z. (2023, January 24–25). Research on image–to–image generation and optimization methods based on diffusion model compared with traditional methods: Taking façade as the optimization object. Proceedings of the International Conference on Computational Design and Robotic Fabrication, Shanghai, China.10.1007/978-981-99-8405-3_4 ↗
53. Liu, Y., Ji, S., and Whang, M. (2025). Emotion–Driven Architectural Image Generation and EEG–Based Evaluation: Divergent Subjective and Physiological Responses to AI–Modified Design Elements. Buildings, 16.10.3390/buildings16010036 ↗
54. Bao, Q., Zhao, J., Liu, Z., and Liang, N. (2025). AI–assisted inheritance of Qinghua porcelain cultural genes and sustainable design using low–rank adaptation and stable diffusion. Electronics, 14.10.3390/electronics14040725 ↗
55. Lu, Y., Wu, J., Wang, M., Fu, J., Xie, W., Wang, P., and Zhao, P. (2025). Design transformation pathways for AI–generated images in Chinese traditional architecture. Electronics, 14.10.3390/electronics14020282 ↗
56. Liu, J., and Huang, Y. (2026). LoRA–Fine–Tuned Latent Diffusion for High–Fidelity Digitization of Classic Mongolian Patterns. Appl. Sci., 16.10.3390/app16010011 ↗
57. Artificial intelligence generation model of Dai brocade patterns based on DreamBooth
58. Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014, January 8–13). How transferable are features in deep neural networks?. Proceedings of the 27th Conference on Neural Information Processing Systems (NeurIPS 2014), Montreal, QC, Canada.
59. Kornblith, S., Shlens, J., and Le, Q.V. (2019, January 15–20). Do better imagenet models transfer better?. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00277 ↗
60. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
61. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–23). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
62. Artistic style transfer with internal–external learning and contrastive learning
63. Singh, J., Gould, S., and Zheng, L. (2023, January 17–24). High–fidelity guided image synthesis with latent diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00581 ↗
64. Advancing persistent character generation: Comparative analysis of fine–tuning techniques for diffusion models10.3390/ai5040088 ↗
65. Chen, Z., Zhang, N., Xu, C., Xu, Z., Han, S., and Jiang, L. (2025). Typological Transcoding Through LoRA and Diffusion Models: A Methodological Framework for Stylistic Emulation of Eclectic Facades in Krakow. Buildings, 15.10.20944/preprints202505.2497.v1 ↗
66. SAD: Style–aware diffusion adaptation for few–shot style transfer image generation10.26599/CVM.2025.9450494 ↗
67. Controllable image synthesis methods, applications and challenges: A comprehensive survey10.1007/s10462-024-10987-w ↗
68. Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., and Li, X. (2023, January 17–24). Layoutdiffusion: Controllable diffusion model for layout–to–image generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.02154 ↗
69. Learning face image super–resolution through facial semantic attribute transformation and self–attentive structure enhancement10.1109/TMM.2020.2984092 ↗
70. Yang, T., Ren, P., Xie, X., and Zhang, L. (2024, January 16–22). Gan prior embedded network for blind face restoration in the wild. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.