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.
Key words
AI image technology /
ink wash composition /
Sichuan tea packaging design
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[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
PDF(2911 KB)
渝公网安备 50010702501717号