Palette Aligned Image Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aharoni, Elad, Porat, Noy, Lischinski, Dani, Shamir, Ariel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909765998739456
author Aharoni, Elad
Porat, Noy
Lischinski, Dani
Shamir, Ariel
author_facet Aharoni, Elad
Porat, Noy
Lischinski, Dani
Shamir, Ariel
contents We introduce the Palette-Adapter, a novel method for conditioning text-to-image diffusion models on a user-specified color palette. While palettes are a compact and intuitive tool widely used in creative workflows, they introduce significant ambiguity and instability when used for conditioning image generation. Our approach addresses this challenge by interpreting palettes as sparse histograms and introducing two scalar control parameters: histogram entropy and palette-to-histogram distance, which allow flexible control over the degree of palette adherence and color variation. We further introduce a negative histogram mechanism that allows users to suppress specific undesired hues, improving adherence to the intended palette under the standard classifier-free guidance mechanism. To ensure broad generalization across the color space, we train on a carefully curated dataset with balanced coverage of rare and common colors. Our method enables stable, semantically coherent generation across a wide range of palettes and prompts. We evaluate our method qualitatively, quantitatively, and through a user study, and show that it consistently outperforms existing approaches in achieving both strong palette adherence and high image quality.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02000
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Palette Aligned Image Diffusion
Aharoni, Elad
Porat, Noy
Lischinski, Dani
Shamir, Ariel
Computer Vision and Pattern Recognition
We introduce the Palette-Adapter, a novel method for conditioning text-to-image diffusion models on a user-specified color palette. While palettes are a compact and intuitive tool widely used in creative workflows, they introduce significant ambiguity and instability when used for conditioning image generation. Our approach addresses this challenge by interpreting palettes as sparse histograms and introducing two scalar control parameters: histogram entropy and palette-to-histogram distance, which allow flexible control over the degree of palette adherence and color variation. We further introduce a negative histogram mechanism that allows users to suppress specific undesired hues, improving adherence to the intended palette under the standard classifier-free guidance mechanism. To ensure broad generalization across the color space, we train on a carefully curated dataset with balanced coverage of rare and common colors. Our method enables stable, semantically coherent generation across a wide range of palettes and prompts. We evaluate our method qualitatively, quantitatively, and through a user study, and show that it consistently outperforms existing approaches in achieving both strong palette adherence and high image quality.
title Palette Aligned Image Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.02000