Palette Aligned Image Diffusion
Computer Graphics Forum · 30.03.2026
DOI: 10.1111/cgf.70384 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 30.03.2026. Verfasst von E. Aharoni und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Israel Science Foundation.
Abstract (Originalsprache)
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 human evaluation, and show that it consistently outperforms existing approaches in achieving both strong palette adherence and high image quality.
Förderung
- Israel Science Foundation
Zitieren
APA
Aharoni, E., Porat, N., Lischinski, D., & Shamir, A. (2026). Palette Aligned Image Diffusion. Computer Graphics Forum. https://doi.org/10.1111/cgf.70384
Vancouver
Aharoni E, Porat N, Lischinski D, Shamir A. Palette Aligned Image Diffusion. Computer Graphics Forum. 2026. doi:10.1111/cgf.70384
BibTeX
@article{Aharoni2026,
author = {Aharoni, E. and Porat, N. and Lischinski, D. and Shamir, A.},
title = {Palette Aligned Image Diffusion},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70384}
}
EUVIMED