Color Conditional Generation with Sliced Wasserstein Guidance
Authors: Alexander Lobashev, Maria Larchenko, Dmitry Guskov
🎯 Key Contributions
- Training-free approach for color-conditioned image generation using diffusion models
- Incorporates differentiable Sliced 1-Wasserstein distance during sampling process
- Achieves state-of-the-art color similarity while maintaining semantic coherence
📚 Resources
Abstract
We propose SW-Guidance, a training-free approach for image generation conditioned on the color distribution of a reference image. While it is possible to generate an image with fixed colors by first creating an image from a text prompt and then applying a color style transfer method, this approach often results in semantically meaningless colors in the generated image.
Our method solves this problem by modifying the sampling process of a diffusion model to incorporate the differentiable Sliced 1-Wasserstein distance between the color distribution of the generated image and the reference palette. Our method outperforms state-of-the-art techniques for color-conditional generation in terms of color similarity to the reference, producing images that not only match the reference colors but also maintain semantic coherence with the original text prompt.
📋 Citation
@article{lobashev2025color,
title={Color Conditional Generation with Sliced Wasserstein Guidance},
author={Lobashev, Alexander and Larchenko, Maria and Guskov, Dmitry},
journal={arXiv preprint arXiv:2503.19034},
year={2025}
}