Research on Generative Design Methods for Yan'an Cloth Pile Paintings Based on Fine-tuned Diffusion Models
Abstract
Yanchuan cloth patch painting, a Shaanxi intangible cultural heritage, serves as a significant material carrier for the inheritance of Yellow River culture. However, its inheritance faces the risk of generational gaps and innovation dilemmas due to the experience-dependent creation model. This study focuses on the application of generative artificial intelligence technology in the inheritance of intangible cultural heritage, proposing a diffusion model fine-tuning method for constructing a professional dataset. This method includes collecting 1380 samples of Yanchuan cloth patch paintings, electronically preprocessing them, and constructing the Yanchuan Cloth Patch Painting Dataset (CYCPP) through manual annotation. The CYCPP dataset is used to fine-tune the diffusion model. Image generation experiments are conducted using the fine-tuned diffusion model. The CYCPP model is solidified after mixed evaluation, and the CYCPP model is used for image generation of Yanchuan cloth patch paintings. Experiments show that the generative design method optimizes the hand-painting process, and the new method can support the creation of Yanchuan cloth patch paintings. This study provides an effective technical method for breaking the predicament of "loss of skills due to the death of people" in intangible cultural heritage.
Read the paper
Related studies
- Learning from First-Generation Qualitative Approaches in the IS Discipline: An Evolutionary View and Some Implications for Authors and Evaluators (PART 1/2)
- Commentary on the clinical and preclinical dosage limits of interstitially administered magnetic fluids for therapeutic hyperthermia based on current practice and efficacy models
- Prosthesis: New Technological Opportunities and Innovative Biomedical Devices
- The history and future of neural modeling for cochlear implants
- Ryanodine receptors: waking up from refractoriness
- Novel Transgenic Rabbit Model Sheds Light on the Puzzling Role of Matrix Metalloproteinase-12 in Atherosclerosis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.