Could ChatGPT Imagine: Content Control for Artistic Painting Generation Via Large Language Models

doi:10.1007/s10846-023-01956-6

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Could ChatGPT Imagine: Content Control for Artistic Painting Generation Via Large Language Models
	Lu, Yue 3; Guo, Chao 2; Dou, Yong 1; Dai, Xingyuan 2; Wang, Fei-Yue 2
刊名	JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
	2023-10-01
卷号	109 期号:2 页码:15
关键词	Intelligent systems Human-machine interactions Artistic painting generation Large language model ChatGPT Linguistic intelligence
ISSN号	0921-0296
DOI	10.1007/s10846-023-01956-6
通讯作者	Wang, Fei-Yue(feiyue.wang@ia.ac.cn)
英文摘要	Intelligent systems and human-machine interactions have consistently provided convenience in both work and daily life. Artificial Intelligence Generated Content (AIGC) can assist humans in artistic creation by generating painting images based on textual descriptions. However, the quality of generated painting images depends heavily on well-designed prompts, which are labor-intensive and time-consuming in painting creation. Large Language Models (LLMs) like ChatGPT have shown impressive performance in linguistic tasks such as question answering and logical inference, demonstrating strong linguistic intelligence. This paper proposes an assistant painting creation approach to provide precise content control for painting generation by combining LLMs with text-to-image generative models and evaluates the performance of the proposed approach on painting content generation and painting element arrangement. The experimental results show that our approach can provide clear guidance on rich painting content and reasonable arrangements of painting elements, demonstrating its ability of text-based painting scene imagination. In painting generation tasks, LLMs like ChatGPT can help the text-to-image models with precise control over the painting content and improve the overall painting results.
资助项目	This work is supported in part by Skywork Intelligence Culture amp; Technology LTD. ; Skywork Intelligence Culture amp; Technology LTD.
WOS关键词	PARALLEL ; METAVERSES
WOS研究方向	Computer Science ; Robotics
语种	英语
出版者	SPRINGER
WOS记录号	WOS:001083626300001
资助机构	This work is supported in part by Skywork Intelligence Culture amp; Technology LTD. ; Skywork Intelligence Culture amp; Technology LTD.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/52993]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Fei-Yue
作者单位	1.Macao Univ Sci & Technol, Macao Inst Syst Engn, Macau 999078, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 3.Shandong Univ, Sch Control Sci & Engn, Jinan 250061, Peoples R China
推荐引用方式 GB/T 7714	Lu, Yue,Guo, Chao,Dou, Yong,et al. Could ChatGPT Imagine: Content Control for Artistic Painting Generation Via Large Language Models[J]. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS,2023,109(2):15.
APA	Lu, Yue,Guo, Chao,Dou, Yong,Dai, Xingyuan,&Wang, Fei-Yue.(2023).Could ChatGPT Imagine: Content Control for Artistic Painting Generation Via Large Language Models.JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS,109(2),15.
MLA	Lu, Yue,et al."Could ChatGPT Imagine: Content Control for Artistic Painting Generation Via Large Language Models".JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 109.2(2023):15.