Full-Process Structural Prompts: Enhancing the Expressive Effects of GAI in Idiom Image Generation
Pages 337 - 343
Abstract
Prompt engineering enhances generative artificial intelligence (GAI)'s expressive capabilities, but its impact on idiom visualization in region language education remains unclear. This study aims to assess GAI's performance in creating idiomatic images under various prompts and to develop an optimized full-process structural prompt approach. Experiments using ZhiPu QingYan on 20 idioms and comparing simple, complex, and structural prompts' effects on image integrity, clarity, and classical aesthetics. The proposed prompts scheme efficiently generates images that align with idiomatic meanings and regional aesthetics, with further optimization possible through material text, detail, and style adjustments. This approach not only eases the burden on educators in crafting prompts for GAI-based educational resources but also opens new avenues for GAI applications in education.
References
[1]
Ge, J. On the Copyrightability of AI-Generated Content: From the Perspective of Users' Original Expressions. Intellectual Property, 1(Jan. 2024), 36-67.
[2]
Spasic, A. J. and Jankovic, D. S. Using ChatGPT Standard Prompt Engineering Techniques in Lesson Preparation: Role, Instructions and Seed-Word Prompts. In Proceedings of the 58th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST), Jun. 29-Jul. 01, 2023, Nis, SERBIA, 47-50.10.1109/icest58410.2023.10187269.
[3]
Yang, H., Wanaskar, K., Shrivastava, H., Mansahia, S., Richhariya, S. and Eirinaki, M. Prompt Recommendations for Al Art. In Proceedings of the 2023 IEEE Sixth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Sept. 25- 27, 2023, Laguna Hills, CA, 62-65.10.1109/AIKE59827.2023.00017.
[4]
Feng, Y. C. J., Wang, X. B., Wong, K. K., Wang, S. J., Lu, Y. H., Zhu, M. F., Wang, B. C. and Chen, W. PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation. IEEE T VIS COMPUT GR, 30, 1 (Jan. 2024), 295-305. 10.1109/Tvcg.2023.3327168.
[5]
Department, P. s. L. P. H. E. Idiom Stories (Chinese Edition). People's Literature Publishing House, Beijing, 2020.
[6]
Xin, W., Zhihao, J. and Dong, X. AI Prompt Engineering: Foundations, Applications, and Examples (Chinese Edition). Publishing House of Electronics Industry, Beijing, 2024.
[7]
Zi, Y. Dictionary of Chinese Calligraphy and Painting Appraisal and Collection (Chinese Edition). Xiling Seal Society Publishing House, Hangzhou, 2016.
[8]
Li, J., Li, D., Xiong, C. and Hoi, S. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In Proceedings of the 39th International Conference on Machine Learning (ICML), Vol. 162 (Jul. 17-23, 2022), Baltimore, MD.
[9]
Liu, V. V., Chilton, L. B. and Acm. Design Guidelines for Prompt Engineering Text-to-Image Generative Models. In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI), Apr. 30-May 05, 2022, New Orleans, LA, Article 384, 1–23. 10.1145/3491102.3501825.
[10]
Hanning, L., Hao, W., Xingjie, X., Menghao, Y. and Feng, Y. Prompt Writing Approach in GAI Tools Aided Architectural Design: Taking Urban Camp Center Design as an Example. In Proceedings of the 2023 National Academic Seminar on Architectural Digital Technology Teaching and Research of Architectural Schools and DADA2023 Digital Architecture Academic Seminar, Oct. 14 2023, Xiangtan, HUNAN, 424-427.
[11]
Oppenlaender, J. A taxonomy of prompt modifiers for text-to-image generation. Behaviour & Information Technology. Nov. 2023, 1–14. 10.1080/0144929x.2023.2286532.
[12]
Qiao, H., Liu, V., Chilton, L. B. and Acm. Initial Images: Using Image Prompts to Improve Subject Representation in Multimodal AI Generated Art. In Proceedings of the 14th ACM Creativity and Cognition Conference Series (C and C), Jun. 20-23, 2022, Venice, ITALY, 15-28.10.1145/3527927.3532792.
[13]
Chung, J. J. Y., Adar, E. and Acm. Artinter: AI-powered Boundary Objects for Commissioning Visual Arts. In Proceedings of the ACM Designing Interactive Systems Conference (DIS) on Rebuilding and Resilience, Jul. 10-14, 2023, Pittsburgh, PA, 1997-2018. 10.1145/3563657.3595961.
Index Terms
- Full-Process Structural Prompts: Enhancing the Expressive Effects of GAI in Idiom Image Generation
Recommendations
The Social Construction of Generative AI Prompts
CHI EA '24: Extended Abstracts of the CHI Conference on Human Factors in Computing SystemsAs text-to-image AI tools grow in capability and widespread use, research has focused on studying individualistic user prompt crafting strategies. Recognizing that technologies are socially constructed, this paper examines prompt engineering through a ...
Initial Images: Using Image Prompts to Improve Subject Representation in Multimodal AI Generated Art
C&C '22: Proceedings of the 14th Conference on Creativity and CognitionAdvances in text-to-image generative models have made it easier for people to create art by just prompting models with text. However, creating through text leaves users with limited control over the final composition or the way the subject is ...
Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models
UIST '23: Proceedings of the 36th Annual ACM Symposium on User Interface Software and TechnologyText-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts. However, crafting prompts that accurately capture the user’s creative intent remains challenging. It often involves ...
Comments
Information & Contributors
Information
Published In
June 2024
399 pages
ISBN:9798400709937
DOI:10.1145/3687488
Copyright © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 18 November 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
ICCIR 2024
ICCIR 2024: 2024 4th International Conference on Control and Intelligent Robotics
June 21 - 23, 2024
Guangzhou, China
Acceptance Rates
Overall Acceptance Rate 131 of 239 submissions, 55%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 33Total Downloads
- Downloads (Last 12 months)33
- Downloads (Last 6 weeks)5
Reflects downloads up to 05 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderFull Text
View this article in Full Text.
Full TextHTML Format
View this article in HTML Format.
HTML Format