AI图像技术介入水墨构成在川茶包装设计中的应用研究

陈胄

doi:10.19554/j.cnki.1001-3563.2026.16.047

PDF(2911 KB)

包装工程（设计栏目） ›› 2026, Vol. 47 ›› Issue (16) : 531-541. DOI: 10.19554/j.cnki.1001-3563.2026.16.047

设计研讨

AI图像技术介入水墨构成在川茶包装设计中的应用研究

陈胄

作者信息 +

Application of AI Image Technology in Ink Wash Composition for Sichuan Tea Packaging Design

CHEN Zhou

Author information +

文章历史 +

摘要

目的将AI图像技术介入水墨构成实验,将其生成的水墨图像用于水墨风格的川茶包装设计中。旨在探索人工智能在水墨构成形式、笔墨语言、艺术风格和包装设计方案、效果图等方面的能力。方法用文献分析法和实验法。在文献分析方面系统地梳理AI图像技术最新发展成果与工作原理,在实验方面使用即梦AI、ChatGPT、Midjourney模型和“包小盒”线上设计平台对水墨构成艺术语言和水墨风格川茶包装设计的成效。结论研究表明,AI图像模型能够解决肌理变化、笔墨语言、构成样式、风格融合方面的难题;并且能够按照要求完成包装盒设计、材质选择、效果图生成等设计全流程工作,通过问卷调查发现AI生成的川茶水墨风包装设计具有较高的消费者接受度和市场潜力。

Abstract

The work aims to integrate AI image technology into ink wash composition experiments, and utilize the generated ink wash imagery to create Sichuan tea packaging designs in the ink wash style, so as to explore artificial intelligence's capabilities in ink wash composition forms, brushwork language, artistic styles, packaging design solutions, and visualization. For methodologies, comprise literature analysis and experimental approaches were employed. For the literature review, the latest advancements and operational principles of AI image technology were systematically examined. For the experimental phase, Jiemeng AI, ChatGPT, Midjourney models, and the "Pacdora" online design platform were used to evaluate the effectiveness of applying ink wash composition techniques and ink wash-style design to Sichuan tea packaging. The research demonstrates that AI image models can resolve challenges in texture variation, brushwork language, compositional patterns, and stylistic fusion. Furthermore, they can complete the entire design workflow, including packaging box design, material selection, and rendering generation, according to specifications. Questionnaire surveys reveal that AI-generated ink-wash style packaging designs for Sichuan tea possess high consumer acceptance and market potential.

导出引用1

陈胄. AI图像技术介入水墨构成在川茶包装设计中的应用研究[J]. 包装工程. 2026, 47(16): 531-541 https://doi.org/10.19554/j.cnki.1001-3563.2026.16.047

CHEN Zhou. Application of AI Image Technology in Ink Wash Composition for Sichuan Tea Packaging Design[J]. Packaging Engineering. 2026, 47(16): 531-541 https://doi.org/10.19554/j.cnki.1001-3563.2026.16.047

中图分类号： TP242.6

参考文献

[1] 张彦远. 历代名画记[M]. 南京: 江苏美术出版社, 2007.
ZHANG Y Y.Famous Paintings of Past Dynasties[M]. Nanjing: Jiangsu Fine Arts Publishing House, 2007.
[2] 卢沉. 水墨构成[J]. 美术研究, 1998(1): 40-44.
LU C.Ink Composition[J]. Art Research, 1998, (1): 40-44.
[3] 何志明, 潘运告. 唐五代画论[M]. 长沙: 湖南美术出版社, 1997.
HE Z M, PAN Y G.On Painting in Tang and Five Dynasties[M]. Changsha: Hunan Fine Arts Publishing House, 1997.
[4] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al.Generative Adversarial Networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[5] SOHL-DICKSTEIN J, WEISS E A, MAHESWARANATHAN N, et al. Deep Unsupervised Learning Using Nonequilibrium Thermodynamics[EB/OL]. (2015-03-11) [2026-01-10]. https://arxiv.org/abs/1503.03585, arXiv: 1503.03585.
[6] HO J, JAIN A, ABBEEL P.Denoising Diffusion Probabilistic Models[J]. Advances in Neural Information Processing Systems, 2020, 33: 6840-6851.
[7] PEEBLES W, XIE S N.Scalable Diffusion Models with Transformers[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France. IEEE, 2024: 4172-4182.
[8] RUMELHART D E, HINTON G E, WILLIAMS R J.Learning Representations by Back-Propagating Errors[J]. Nature, 1986, 323(6088): 533-536.
[9] 张泽宇, 王铁君, 郭晓然, 等. AI绘画研究综述[J]. 计算机科学与探索, 2024, 18(6): 1404-1420.
ZHANG Z Y,WANG T J, GUO X R, et al.Review of AI Painting Research[J]. Journal of Computer Research and Development, 2024, 18(6): 1404-1420.
[10] RAMESH A, PAVLOV M, GOH G, et al.Zero-Shot Text-to-Image Generation[C]//Proceedings of the 38th International Conference on Machine Learning. Online: PMLR, 2021: 8821-8831.
[11] VASWANI A, SHAZEER N, PARMAR N, et al.Attention Is All You Need[C]//Advances in Neural Information Processing Systems 30. Long Beach: Curran Associates Inc., 2017: 5998-6008.
[12] RADFORD A, KIM J W, HALLACY C, et al.Learning Transferable Visual Models from Natural Language Supervision[C]//Proceedings of the 38th International Conference on Machine Learning. Online: PMLR, 2021: 8748-8763.
[13] CROWSON K, BIDERMAN S, KORNIS D, et al.VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance[M]//Computer Vision -ECCV 2022. Cham: Springer Nature Switzerland, 2022: 88-105.
[14] NICHOL A, DHARIWAL P, RAMESH A, et al.GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models[C]//International Conference on Machine Learning., 2021