ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Ding, Inoue, Naoto, Qiu, Qianru, Kikuchi, Kotaro
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918123902337024
author Xia, Ding
Inoue, Naoto
Qiu, Qianru
Kikuchi, Kotaro
author_facet Xia, Ding
Inoue, Naoto
Qiu, Qianru
Kikuchi, Kotaro
contents Colors play a crucial role in the design of vector graphic documents by enhancing visual appeal, facilitating communication, improving usability, and ensuring accessibility. In this context, color recommendation involves suggesting appropriate colors to complete or refine a design when one or more colors are missing or require alteration. Traditional methods often struggled with these challenges due to the complex nature of color design and the limited data availability. In this study, we explored the use of pretrained Large Language Models (LLMs) and their commonsense reasoning capabilities for color recommendation, raising the question: Can pretrained LLMs serve as superior designers for color recommendation tasks? To investigate this, we developed a robust, rigorously validated pipeline, ColorGPT, that was built by systematically testing multiple color representations and applying effective prompt engineering techniques. Our approach primarily targeted color palette completion by recommending colors based on a set of given colors and accompanying context. Moreover, our method can be extended to full palette generation, producing an entire color palette corresponding to a provided textual description. Experimental results demonstrated that our LLM-based pipeline outperformed existing methods in terms of color suggestion accuracy and the distribution of colors in the color palette completion task. For the full palette generation task, our approach also yielded improvements in color diversity and similarity compared to current techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08987
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation
Xia, Ding
Inoue, Naoto
Qiu, Qianru
Kikuchi, Kotaro
Computer Vision and Pattern Recognition
Human-Computer Interaction
Colors play a crucial role in the design of vector graphic documents by enhancing visual appeal, facilitating communication, improving usability, and ensuring accessibility. In this context, color recommendation involves suggesting appropriate colors to complete or refine a design when one or more colors are missing or require alteration. Traditional methods often struggled with these challenges due to the complex nature of color design and the limited data availability. In this study, we explored the use of pretrained Large Language Models (LLMs) and their commonsense reasoning capabilities for color recommendation, raising the question: Can pretrained LLMs serve as superior designers for color recommendation tasks? To investigate this, we developed a robust, rigorously validated pipeline, ColorGPT, that was built by systematically testing multiple color representations and applying effective prompt engineering techniques. Our approach primarily targeted color palette completion by recommending colors based on a set of given colors and accompanying context. Moreover, our method can be extended to full palette generation, producing an entire color palette corresponding to a provided textual description. Experimental results demonstrated that our LLM-based pipeline outperformed existing methods in terms of color suggestion accuracy and the distribution of colors in the color palette completion task. For the full palette generation task, our approach also yielded improvements in color diversity and similarity compared to current techniques.
title ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2508.08987