目的 探究一种基于生成式人工智能技术拓展耀州青瓷传统牡丹纹饰的工作流程和设计方式。方法 以耀州青瓷传统牡丹纹饰为研究对象,通过搭建多模型组合流程,对其进行数据整理、标签锚定和训练优化。使用生成式人工智能技术来获得特定风格牡丹纹饰的智能生成方法,从而拓宽传统耀州青瓷牡丹纹饰样本数量,为设计师再创造提供海量素材。结果 采用LoRA模型训练方式,仅需少量样本即可将耀州青瓷传统牡丹纹饰特征在Stable Diffusion中重现。结论 在数智高速发展的背景下,该方式不仅符合新时代发展和满足独立知识产权的需要,而且为中国其他历史名窑的数字化传承提供了良好的可借鉴思路和方法。
Abstract
Exploring a Workflow and Design Approach for Expanding Traditional Peony Patterns in Yaozhou Celadon Using Generative Artificial Intelligence.This study focuses on the traditional peony patterns found in Yaozhou celadon as the research object. By establishing a multi-model combination process, we aim to organize the data, anchor labels, train and optimize the models, and leverage generative artificial intelligence techniques to develop an intelligent method for generating peony patterns with a specific style. This endeavor seeks to broaden the sample base of traditional peony patterns in Yaozhou celadon, providing designers with a vast array of materials for re-creation. The experimental results demonstrate that by adopting the LoRA model training method, the characteristic features of traditional peony patterns in Yaozhou celadon can be reproduced in Stable Diffusion with only a small number of samples. In the context of rapid development of digital intelligence, this approach not only meets the needs of the new era and independent intellectual property rights, but also provides a good reference and method for the digital inheritance of other historical kilns in China.
关键词
生成式人工智能 /
耀州青瓷传统牡丹纹饰 /
LoRA模型 /
Stable Diffusion
Key words
Artificial Intelligence Generated Content (AIGC) /
Traditional Peony Patterns in Yaozhou Celadon /
Low- Rank Adaptation of Large Language Models (LoRA) /
Stable Diffusion
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 高黎, 王思茜. 耀州窑刻划花装饰综述[J]. 中国陶瓷, 2021, 57(10): 101-109.
GAO L, WANG S Q.Summary of Carved Flower Decoration in Yaozhou Kiln[J]. China Ceramics, 2021, 57(10): 101-109.
[2] 陈鋆纯, 彭坚, 郭寅曼, 等. 基于花瑶挑花纹样风格化图像的辅助设计研究[J]. 包装工程, 2022, 43(14): 246-253.
CHEN J C, PENG J C, GUO Y M, et al.Computer-aided Design Based on Stylized Images of Huayao Cross- stitch Patterns[J]. Packaging Engineering, 2022, 43(14): 246-253.
[3] 乔锦浩, 肖懿, 崔誉丹, 等. 特定风格剪纸艺术的智能生成[J]. 包装工程, 2021, 42(14): 74-80.
QIAO J H, XIAO Y, CUI Y D, et al.Intelligent Generation for Specific Style of Paper-Cutting Art[J]. Packaging Engineering, 2021, 42(14): 74-80.
[4] BELHI A, BOURAS S, FOU F.Digitization and Preservation of Cultural Heritage: The CEPROQHA Approach[C]//Proceedings of the 2017 11th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), Malabe: SKIMA, 2017: 1-7.
[5] 侯云鹏, 彭涵, 刘育晖. 基于LoRA模型的非遗数字化传承:以楚漆器为例[J]. 设计艺术研究, 2024, 14(1): 14-18.
HOU Y P, PENG H, LIU Y H.Digital Inheritance of Intangible Cultural Heritage Based on the LoRA Model: a Case Study of Chu Lacquerware[J]. Desgin Research, 2024, 14(1): 14-18.
[6] 于鹏, 张毅. 从特征辨识到图像生成: 基于AIGC范式的苗族服饰设计[J]. 丝绸, 2024, 61(3): 1-10.
YU P, ZHANG Y.From Feature Recognition to Image Generation: Miao Ethnic Costume Design Based on the AIGC Paradigm[J]. Journal of Silk, 2024, 61(3): 1-10.
[7] 舒畇溦, 孟凯宁, 孙宁. 彝族传统纹样的数字化传承与重塑设计研究[J]. 吉林艺术学院学报, 2023(4): 11-17.
SHU Y W, MENG K N, SUN N.Research on Digital Inheritance and Redesign of Yi Ethnic Traditional Patterns[J]. Journal of Jilin University of Arts, 2023(4): 11-17.
[8] ZHANG H.Combined Development of Artificial Intelligence and Art Design[C]//2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP). Xi'an: ICSP, 2021: 1023-1026.
[9] 冯金牛, 周强, 张瑞瑞, 等. 基于卷积神经网络的中国古陶瓷智能断代研究[J]. 陶瓷学报, 2022, 43(1): 145-152.
FENG J N, ZHOU Q, ZHANG R R, et al.Intelligent Dating of Chinese Ancient Ceramics Based on Convolutional Neural Network[J]. Journal of Ceramics, 2022, 43(1): 145-152.
[10] 崔因, 杨建明, 李芳, 等. 磁州窑装饰纹样智能辅助设计研究[J].包装工程, 2023, 44(16): 1-9.
CUI Y, YANG J M, LI F, et al.AI-assisted Design for Decorative Pattern of Cizhou Kiln[J]. Packaging Engineering, 2023, 44(16): 1-9
[11] HAN X R, LIU Y Y, ZHANG H W, et al.Pattern Derivative Design of Black Copper Infused with Silver Using AI-based Pattern Generation and Image Style Transfer Algorithm[C]//2023 International Conference on Artificial Intelligence and Automation Control (AIAC). Xiamen: AIAC, 2023: 177-181.
[12] 覃京燕, 贾冉. 人工智能在非物质文化遗产中的创新设计研究: 以景泰蓝为例[J]. 包装工程, 2020, 41(06): 1-6.
QIN J Y, JIA R.Innovative Designof Artificial Intelligence in Intangible Cultural Heritage: Take Cloisonné as an Example[J]. Packaging Engineering, 2020, 41(6): 1-6.
[13] 张海龙, 黄文锋, 路翔, 等. 知识增强大模型在信息系统故障分析中的应用研究[J].现代计算机, 2024, 30(6): 87-93.
ZHANG H L, HUANG W F, LU X, et al.Research on the Application of Knowledge-Enhanced Large Models in Information System Fault Analysis[J]. Modern Computer, 2024,30(6): 87-93.
[14] 曾建勇, 沈晓萍. 基于Stable Diffusion的虚拟人形象预设计的应用与研究[J]. 现代信息科技, 2024, 8(3): 169-175.
ZENG J Y, SHEN X P.Application and Research on Virtual Human Image Pre-design Based on Stable Diffusion[J]. Modern Information Technology, 2024, 8(3): 169-175
[15] 孙贾康. 宋代耀州窑牡丹纹饰研究[J]. 陶瓷, 2023(12): 50-52.
SUN J K.Study on Peony Oranmentation of YaoZhou Kiln in Song Dynasty[J]. Ceramics, 2023(12): 50-52.
基金
陕西省哲学社会科学研究专项项目（2025YB0246）; 陕西省自然科学基础研究计划面上项目（2025JC-YBMS-605）; 西安理工大学教育教学改革研究重点项目（xjy2412）; 陕西省艺术科学规划项目（SYG2024010）; 陕西省社会科学基金项目（2023J005）; 教育部人文社会科学研究一般项目（20YJC760074）
PDF(15375 KB)
渝公网安备 50010702501717号