利用扩散模型结合多张风格图像进行风格化
Leveraging Diffusion Models for Stylization using Multiple Style Images
AI总结：
本文提出利用多张风格图像并结合图像提示适配器与注意力特征统计对齐，在去噪 UNet 的交叉注意力和自注意力层进行干预，以提升风格匹配质量并防止内容泄漏，在风格化任务上取得最先进结果。
摘要：
近年来，潜在扩散模型的进展推动了图像风格迁移的显著进步。然而，若干关键问题仍然存在。例如，现有方法在准确匹配风格方面仍存在困难，通常受限于可使用的风格图像数量，并且往往以不期望的方式将内容与风格纠缠在一起。为解决这些问题，我们提出利用多张风格图像，以更好地表示风格特征并防止风格图像中的内容泄漏。我们设计了一种方法，在去噪过程中同时利用图像提示适配器和特征的统计对齐。通过这种方式，我们的方法能够在去噪 UNet 的交叉注意力层和自注意力层进行干预。对于统计对齐，我们采用聚类方法，从风格样本中提取的大量注意力值中提炼出一小组具有代表性的注意力特征。如实验部分所示，所提出的方法在风格化任务上取得了最先进的结果。
英文摘要：
Recent advances in latent diffusion models have enabled exciting progress in image style transfer. However, several key issues remain. For example, existing methods still struggle to accurately match styles. They are often limited in the number of style images that can be used. Furthermore, they tend to entangle content and style in undesired ways. To address this, we propose leveraging multiple style images which helps better represent style features and prevent content leaking from the style images. We design a method that leverages both image prompt adapters and statistical alignment of the features during the denoising process. With this, our approach is designed such that it can intervene both at the cross-attention and the self-attention layers of the denoising UNet. For the statistical alignment, we employ clustering to distill a small representative set of attention features from the large number of attention values extracted from the style samples. As demonstrated in our experimental section, the resulting method achieves state-of-the-art results for stylization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
