A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer

Abstract The integration of text-to-image generation capabilities within GPT-4 allows for the convenient creation of various graphics. However, the proficiency of GPT-4 in crafting challenging scientific visuals remains largely unexplored. In this study, we conduct systematic experiments by employin...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingsi Gao, Yubo Shi, Ruoyu Wang, Jianfeng Zhou
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-00300-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334995627278336
author Jingsi Gao
Yubo Shi
Ruoyu Wang
Jianfeng Zhou
author_facet Jingsi Gao
Yubo Shi
Ruoyu Wang
Jianfeng Zhou
author_sort Jingsi Gao
collection DOAJ
description Abstract The integration of text-to-image generation capabilities within GPT-4 allows for the convenient creation of various graphics. However, the proficiency of GPT-4 in crafting challenging scientific visuals remains largely unexplored. In this study, we conduct systematic experiments by employing multiple prompt engineering techniques with various supplementary materials to generate complex scientific illustrations for environmental studies. The locally enhanced electric field treatment for water disinfection is used as an example to illustrate the universal reflection of GPT-4 in graphic creation. From the experiments, we summarize that the existing prompt methods struggle in accuracy, modifiability, and reproducibility for scientific image generation. Based on the findings and insights drawn from the extensive experimental results, we develop GPT4Designer, a framework intended to generate scientific images without tedious prompt modifications. Specifically, a simple but surprisingly effective “envision-first” strategy by combining detailed prompting and guided envisioning is developed in the GPT4Designer framework. This strategy yields images with consistent styles aligned with the initial envisioning, significantly improving modifiability. Besides, by refining the conceptualization phase, we achieve much better control over the output, resulting in both high accuracy and reproducibility. This advancement is not only crucial for environmental scientists seeking to quickly produce engaging and accurate visuals (e.g., with only one step), but also demonstrates the existence “chain-of-thought” in image generation, which can inspire more works on the creative application of text-to-image generation models or tools.
format Article
id doaj-art-4f699366f6864cae939ed8fb4596c3f5
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4f699366f6864cae939ed8fb4596c3f52025-08-20T03:45:26ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-00300-2A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4DesignerJingsi Gao0Yubo Shi1Ruoyu Wang2Jianfeng Zhou3School of Material and Environmental Engineering, Shenzhen Polytechnic UniversityNanjing UniversitySchool of Electrical and Computer Engineering (ECE), Georgia Institute of TechnologySchool of Material and Environmental Engineering, Shenzhen Polytechnic UniversityAbstract The integration of text-to-image generation capabilities within GPT-4 allows for the convenient creation of various graphics. However, the proficiency of GPT-4 in crafting challenging scientific visuals remains largely unexplored. In this study, we conduct systematic experiments by employing multiple prompt engineering techniques with various supplementary materials to generate complex scientific illustrations for environmental studies. The locally enhanced electric field treatment for water disinfection is used as an example to illustrate the universal reflection of GPT-4 in graphic creation. From the experiments, we summarize that the existing prompt methods struggle in accuracy, modifiability, and reproducibility for scientific image generation. Based on the findings and insights drawn from the extensive experimental results, we develop GPT4Designer, a framework intended to generate scientific images without tedious prompt modifications. Specifically, a simple but surprisingly effective “envision-first” strategy by combining detailed prompting and guided envisioning is developed in the GPT4Designer framework. This strategy yields images with consistent styles aligned with the initial envisioning, significantly improving modifiability. Besides, by refining the conceptualization phase, we achieve much better control over the output, resulting in both high accuracy and reproducibility. This advancement is not only crucial for environmental scientists seeking to quickly produce engaging and accurate visuals (e.g., with only one step), but also demonstrates the existence “chain-of-thought” in image generation, which can inspire more works on the creative application of text-to-image generation models or tools.https://doi.org/10.1038/s41598-025-00300-2
spellingShingle Jingsi Gao
Yubo Shi
Ruoyu Wang
Jianfeng Zhou
A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer
Scientific Reports
title A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer
title_full A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer
title_fullStr A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer
title_full_unstemmed A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer
title_short A methodology for designing accurate, modifiable and reproducible scientific graphics in environmental studies using GPT4Designer
title_sort methodology for designing accurate modifiable and reproducible scientific graphics in environmental studies using gpt4designer
url https://doi.org/10.1038/s41598-025-00300-2
work_keys_str_mv AT jingsigao amethodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT yuboshi amethodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT ruoyuwang amethodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT jianfengzhou amethodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT jingsigao methodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT yuboshi methodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT ruoyuwang methodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer
AT jianfengzhou methodologyfordesigningaccuratemodifiableandreproduciblescientificgraphicsinenvironmentalstudiesusinggpt4designer