人工智能驱动的数字图像艺术创作：方法与案例分析

doi:10.11959/j.issn.2096-6652.202333

摘要/Abstract

摘要：

近年来，人工智能技术的快速发展为数字图像创作领域提供了新的工具。使用AI工具进行数字图像创作逐渐成为一种常见的创作方式。在此背景下，通过访谈、调查与案例分析的方法，分析了人工智能驱动的数字图像艺术创作方法与案例。调查结果显示，大多数受访者认为AI工具对其创作过程产生了显著的影响，尤其是AI图像直出的方法被广泛运用于数字图像艺术创作中。通过对案例进行详细剖析，揭示了基于AI的数字图像艺术创作的典型范式，并将之归纳为“AI艺术创作工作流”。其包括AI图像直出法、AI辅助绘图法和ControlNet精确绘图法。这些方法可以有效地替代数字图像创作中的重复环节并提高出图效率，辅助数字图像的绘制和突破常规出图思路，实现精确可控的数字图像艺术内容表达。

关键词: 人工智能艺术, 数字图像, 生成艺术, AI绘画, 绘画生成

Abstract:

In recent years, the rapid advancement of artificial intelligence technology has introduced novel tools for the realm of digital image creation.The use of AI tools for digital image creation has gradually become a common practice.In this context, this paper analyzed the methods and cases of AI-driven digital image art creation through interviews, surveys, and case analyses.The survey revealed that the majority of respondents believed that AI tools had a significant impact on their creative process, especially the widespread use of direct output from artificial intelligence methods in digital image art creation.By analyzing the cases in detail, this paper revealed the typical paradigms of AI-based digital image art creation and summarized them as the “AI art creation workflow”, which included AI direct output, AI assisted drawing, and ControlNet precision drawing.These methods can effectively replace repetitive steps in digital image creation and improve image output efficiency, assist in digital image drawing and break through the conventional drawing ideas, and achieve precise and controllable expression of digital image art content.

Key words: artificial intelligence art, digital image, generative art, AI painting, painting generation

中图分类号:

TP39

王常圣. 人工智能驱动的数字图像艺术创作：方法与案例分析[J]. 智能科学与技术学报, 2023, 5(3): 406-414.

Changsheng WANG. AI-driven digital image art creation: methods and case analysis[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(3): 406-414.

图/表 13

表1

表2

表3

表4

图1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 27

[1]	CAO Y , LI S , LIU Y ,et al. A comprehensive survey of AI-generated content (AIGC):a history of generative AI from GAN to ChatGPT[EB]. arXiv preprint, 2023,arXiv:2303.04226.
[2]	ROMBACH R , BLATTMANN A , LORENZ D ,et al. High-resolution image synthesis with latent diffusion models[C]// Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2022: 10674-10685.
[3]	CHANG M , DRUGA S , FIANNACA A J ,et al. The prompt artists[C]// Proceedings of the 15th Conference on Creativity and Cognition. New York:ACM, 2023: 75-87.
[4]	武强, 季雪庭, 吕琳媛 . 元宇宙中的人工智能技术与应用[J]. 智能科学与技术学报, 2022,4(3): 324-334.
	WU Q , JI X T , LYU L Y . Artificial intelligence technology and applications in the metaverse[J]. Journal of Intelligent Science and Technology, 2022,4(3): 324-334.
[5]	RUNCO M A , JAEGER G J . The standard definition of creativity[J]. Creativity Research Journal, 2012,24(1): 92-96.
[6]	CROWSON K , BIDERMAN S , KORNIS D ,et al. VQGAN-CLIP:open domain image generation and editing with natural language guidance[EB]. arXiv preprint, 2022,arXiv:2204.08583.
[7]	CETINIC E , SHE J . Understanding and creating art with AI:review and outlook[J]. ACM Transactions on Multimedia Computing,Communications,and Applications (TOMM), 2022,18(2): 1-22.
[8]	HONG J W , CURRAN N M . Artificial intelligence,artists,and art:attitudes toward artwork produced by humans vs.artificial intelligence[J]. ACM Transactions on Multimedia Computing,Communications,and Applications, 2019,15(2): 1-16.
[9]	DENG Y . Application of artificial intelligence in art design[C]// Proceedings of 2021 International Conference on Computer Technology and Media Convergence Design (CTMCD). Piscataway:IEEE Press, 2021: 200-203.
[10]	SUN Y K , LYU Y R , LIN P H ,et al. Comparison of cognitive differences of artworks between artist and artistic style transfer[J]. Applied Sciences, 2022,12(11): 5525.
[11]	LI L . The impact of artificial intelligence painting on contemporary art from disco diffusion’s painting creation experiment[C]// Proceedings of 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML). Piscataway:IEEE Press, 2022: 52-56.
[12]	TAE H S , KIM S Y . Exploratory review on the convergence of artificial intelligence and art[J]. Official Journal of the Korean Society of Dance Science, 2019,36(2): 27-42.
[13]	MALINA R F , MCCORDUCK P , COHEN H . Aaron’s code:meta-art,artificial intelligence and the work of Harold Cohen[J]. Leonardo, 1991,24(5): 628-629.
[14]	LE Q V . Building high-level features using large scale unsupervised learning[C]// Proceedings of 2013 IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway:IEEE Press, 2013: 8595-8598.
[15]	MIIKKULAINEN R , LIANG J , MEYERSON E ,et al. Evolving deep neural networks[M]// Artificial Intelligence in the Age of Neural Networks and Brain Computing. Amsterdam: Elsevier, 2019: 293-312.
[16]	WANG K F , GOU C , DUAN Y J ,et al. Generative adversarial networks:introduction and outlook[J]. IEEE/CAA Journal of Automatica Sinica, 2017,4(4): 588-598.
[17]	LI X R , LI H , WANG C Y ,et al. Visual-attention GAN for interior sketch colourisation[J]. IET Image Processing, 2021,15(4): 997-1007.
[18]	ZHU J Y , PARK T , ISOLA P ,et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]// Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2017: 2242-2251.
[19]	KARRAS T , LAINE S , AILA T M . A style-based generator architecture for generative adversarial networks[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2019: 4401-4410.
[20]	BROCK A , DONAHUE J , SIMONYAN K ,et al. Large scale GAN training for high fidelity natural image synthesis[EB]. arXiv preprint, 2018,arXiv:1809.11096.
[21]	RADFORD A , KIM J W , HALLACY C ,et al. Learning transferable visual models from natural language supervision[EB]. arXiv preprint, 2021,arXiv:2103.00020.
[22]	NICHOL A , DHARIWAL P , RAMESH A ,et al. GLIDE:towards photorealistic image generation and editing with text-guided diffusion models[EB]. arXiv preprint, 2021,arXiv:2112.10741.
[23]	DHARIWAL P , NICHOL A . Diffusion models beat GANs on image synthesis[C]// Proceedings of Advances in Neural Information Processing Systems.[S.l.:s.n.], 2021: 8780-8794.
[24]	PAVLICHENKO N , USTALOV D . Best prompts for text-to-image models and how to find them[C]// Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM, 2023: 2067-2071.
[25]	CHOI S Y . A study on AI art in the post-digital age[J]. The Journal of Aesthetics ＆ Science of Art, 2022,67: 188-214.
[26]	ZHANG L , RAO A , AGRAWALA M ,et al. Adding conditional control to textto-image diffusion models[EB]. arXiv preprint, 2023,arXiv:2302.05543.
[27]	OPPENLAENDER J , LINDER R , SILVENNOINEN J ,et al. Prompting AI art:an investigation into the creative skill of prompt engineering[EB]. arXiv preprint, 2023,arXiv:2303.13534.

AI工具	使用人数	占比
Midjourney	103	55.4%
Stable Diffusion	75	40.3%
其他	8	4.3%

影响程度	回答人数	占比
非常有影响	162	84.4%
一般影响	23	12.4%
没有影响	6	3.2%

AI工作流	使用人数	占比	Midjourney使用人数	Midjourney使用人数占比	Stable Diffusion使用人数	Stable Diffusion使用人数占比
AI 图像直出法	127	68.3%	105	82.6%	22	17.4%
AI辅助绘图法	23	12.4%	4	17.4%	19	82.6%
ControlNet精确绘图法	36	19.3%	N/A	N/A	36	100%

AI工作流	优点	缺陷
AI 图像直出法	快速生成高质量图像；方法简单	需要多次生成以获得理想结果；需要较高的提示词写作水平、较好的基础模型效果并熟悉自己想要实现的图像风格
AI 辅助绘图法	拓展创作思路；灵活性高	需要较好的审美筛选生成图像；需要对AI技术有一定的理解和操作能力
ControlNet 精确绘图法	极高的美学表达上限；精确控制图像生成	较高的技术门槛；需要更多的时间来调整和优化图像效果