欢迎访问《图学学报》 分享到:

图学学报 ›› 2023, Vol. 44 ›› Issue (6): 1212-1217.DOI: 10.11996/JG.j.2095-302X.2023061212

• 计算机图形学与虚拟现实 • 上一篇    下一篇

DynArt ChatGPT:一个动态非遗年画的生成平台

靳聪1(), 周满玲1, 张竣淞1,3(), 王洪亮2, 张佳一2, 王晶4, 徐明亮5   

  1. 1.中国传媒大学信息与通信工程学院,北京 100024
    2.中国传媒大学广告学院,北京 100024
    3.华北科技学院电子信息工程学院,北京 101601
    4.北京理工大学信息与电子学院,北京 100081
    5.郑州大学计算机与人工智能学院,河南 郑州 450001
  • 收稿日期:2023-06-19 接受日期:2023-09-07 出版日期:2023-12-31 发布日期:2023-12-17
  • 通讯作者: 张竣淞(1985-),男,讲师,博士。主要研究方向为智能视音频技术、矿山安全工程。E-mail:cuczjs@ncist.edu.cn
  • 作者简介:

    靳聪(1986-),女,副教授,博士。主要研究方向为强化学习、音乐人工智能和音频信号处理。E-mail:jincong0623@cuc.edu.cn

  • 基金资助:
    国家自然科学基金项目(62207029);非物质文化遗产全媒体传播设计研究项目;教育部人文社会科学研究项目-教育部人文社科规划基金项目(22YJA760079);基于AI技术的中国传统设计元素生成方法研究项目(CUC23GZ008)

DynArt ChatGPT: a platform for generating dynamic intangible cultural heritage new year paintings

JIN Cong1(), ZHOU Man-ling1, ZHANG Jun-song1,3(), WANG Hong-liang2, ZHANG Jia-yi2, WANG Jing4, XU Ming-liang5   

  1. 1. School of Information and Communication Engineering, Communication University of China, Beijing 100024, China
    2. School of Advertising, Communication University of China, Beijing 100024, China
    3. School of Electronic Information Engineering, North China Institute of Science and Technology, Beijing 101601, China
    4. School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
    5. School of Computer and Artificial Intelligence, Zhengzhou University, Zhenzhou Henan 450001, China
  • Received:2023-06-19 Accepted:2023-09-07 Online:2023-12-31 Published:2023-12-17
  • Contact: ZHANG Jun-song (1985-), lecturer, Ph.D. His main research interests cover intelligent audio-visual technology, mine safety engineering. E-mail:cuczjs@ncist.edu.cn
  • About author:

    JIN Cong (1986-), associate professor, Ph.D. Her main research interests cover reinforcement learning, music artificial intelligence and audio signal processing. E-mail:jincong0623@cuc.edu.cn

  • Supported by:
    National Natural Science Foundation of China(62207029);Research on the Design of Full Media Communication of Intangible Cultural Heritage;Ministry of Education Humanities and Social Sciences Research Project - Ministry of Education Humanities and Social Sciences Planning Fund Project(22YJA760079);Research on the Generation Method of Chinese Traditional Design Elements Based on AI Technology(CUC23GZ008)

摘要:

Chat GPT吸引了跨领域的兴趣,因其提供了一个领域的会话能力和推理能力。年画是中国非物质文化遗产的重要组成部分,在过去,年画常作为一种主要的宣传手段。作为商品生产,其有着巨大的宣传推广量与经济价值。在以科技为主导的现代社会,中国非物质文化遗产的保护与发展遭遇到了发展经济、技术更新和文化变迁的三大矛盾,产生了传承乏人、创新不易、保护不力的诸多问题。为了弘扬与发展中国传统美术,本文产生了一个设想:能否将Chat GPT的会话功能与非遗文化中的传统美术进行组合呢?基于此设想,构建了一个系统——动态非遗年画生成系统(DynaArt ChatGPT)。DynaArt ChatGPT可通过提取Chat GPT给出的样例中的关键词,然后再根据关键词生成一段与样例相关的描述,并将描述输入到Lumen5模型中,Lumen5就会根据该输入的描述生成相应的动态视频,经过实验本文认为动态画生成系统可以对一些耳熟能详的中国民间故事进行全新的演绎。

关键词: 动态画生成系统, Chat GPT, Lumen5, 陕西凤翔戏出年画, 天津杨柳青年画

Abstract:

ChatGPT has attracted cross-disciplinary interest due to its capabilities in conversation and reasoning skills. New Year paintings are a vital component of China's intangible cultural heritage, historically serving as a primary means of publicity. As a form of commodity production, it holds immense publicity and economic value. In the modern society dominated by science and technology, the preservation and development of China's intangible cultural heritage has encountered three major challenges: economic development, technological updating, and cultural changes, resulting in issues such as a lack of inheritance, difficulties in innovation, and inadequate protection. In order to promote and develop traditional Chinese arts, an idea was envisioned: could we combine the conversational capabilities of ChatGPT with traditional arts from the realm of intangible cultural heritage? Based on this idea, we constructed a system called the dynamic intangible cultural heritage New Year paintings generation system (DynaArt ChatGPT). DynaArt ChatGPT could extract the keywords from the samples provided by ChatGPT and then generate a description related to those samples based on the keywords. The description was then input into the Lumen5 model, which could generate the corresponding dynamic video according to the provided description. Experiments demonstrated that this dynamic painting generation system could offer a new interpretation of some well-known Chinese folktales.

Key words: DynaArt ChatGPT, ChatGPT, Lumen5, Shaanxi Fengxiang opera New Year paintings, Tianjin Yangliuqing New Year paintings

中图分类号: