Controllable-Continuous Color Editing in Diffusion Model via Color Mapping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yuqi, Chang, Dongliang, Fang, Yuanchen, SonG, Yi-Zhe, Ma, Zhanyu, Guo, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908544222101504
author Yang, Yuqi
Chang, Dongliang
Fang, Yuanchen
SonG, Yi-Zhe
Ma, Zhanyu
Guo, Jun
author_facet Yang, Yuqi
Chang, Dongliang
Fang, Yuanchen
SonG, Yi-Zhe
Ma, Zhanyu
Guo, Jun
contents In recent years, text-driven image editing has made significant progress. However, due to the inherent ambiguity and discreteness of natural language, color editing still faces challenges such as insufficient precision and difficulty in achieving continuous control. Although linearly interpolating the embedding vectors of different textual descriptions can guide the model to generate a sequence of images with varying colors, this approach lacks precise control over the range of color changes in the output images. Moreover, the relationship between the interpolation coefficient and the resulting image color is unknown and uncontrollable. To address these issues, we introduce a color mapping module that explicitly models the correspondence between the text embedding space and image RGB values. This module predicts the corresponding embedding vector based on a given RGB value, enabling precise color control of the generated images while maintaining semantic consistency. Users can specify a target RGB range to generate images with continuous color variations within the desired range, thereby achieving finer-grained, continuous, and controllable color editing. Experimental results demonstrate that our method performs well in terms of color continuity and controllability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13756
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Controllable-Continuous Color Editing in Diffusion Model via Color Mapping
Yang, Yuqi
Chang, Dongliang
Fang, Yuanchen
SonG, Yi-Zhe
Ma, Zhanyu
Guo, Jun
Computer Vision and Pattern Recognition
In recent years, text-driven image editing has made significant progress. However, due to the inherent ambiguity and discreteness of natural language, color editing still faces challenges such as insufficient precision and difficulty in achieving continuous control. Although linearly interpolating the embedding vectors of different textual descriptions can guide the model to generate a sequence of images with varying colors, this approach lacks precise control over the range of color changes in the output images. Moreover, the relationship between the interpolation coefficient and the resulting image color is unknown and uncontrollable. To address these issues, we introduce a color mapping module that explicitly models the correspondence between the text embedding space and image RGB values. This module predicts the corresponding embedding vector based on a given RGB value, enabling precise color control of the generated images while maintaining semantic consistency. Users can specify a target RGB range to generate images with continuous color variations within the desired range, thereby achieving finer-grained, continuous, and controllable color editing. Experimental results demonstrate that our method performs well in terms of color continuity and controllability.
title Controllable-Continuous Color Editing in Diffusion Model via Color Mapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.13756