ZePo：具备更快采样速度的零样本人像风格化
ZePo: Zero-Shot Portrait Stylization with Faster Sampling
AI总结：
针对现有扩散模型人像风格化方法速度慢的问题，提出无需逆扩散的ZePo框架，借助潜一致性模型特征与风格增强注意力控制，仅四步采样实现高效高保真的零样本人像风格化。
摘要：
基于扩散的文本生成图像模型已极大推动了艺术内容合成领域的发展。然而，当前的人像风格化方法通常要么需要基于样本进行模型微调，要么需要采用DDIM Inversion（DDIM逆扩散）将图像还原至噪声空间，这两种方式都会大幅拖慢图像生成流程。为突破这些局限，本文提出了一种基于扩散模型的无需逆扩散的人像风格化框架，仅需四步采样即可实现内容与风格特征的融合。我们观察到，采用一致性蒸馏的Latent Consistency Models（潜一致性模型）能够从含噪图像中有效提取具有代表性的一致性特征（Consistency Features）。为融合从内容图像和风格图像中提取的一致性特征，我们提出了风格增强注意力控制技术，可在目标图像的注意力空间内精细融合内容特征与风格特征。此外，我们还提出了一种特征合并策略，用于合并一致性特征中的冗余特征，以此降低注意力控制的计算负载。大量实验已验证了本文提出的框架在提升风格化效率和保真度方面的有效性。代码可访问https://github.com/liujin112/ZePo 获取。
英文摘要：
Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples or the employment of DDIM Inversion to revert images to noise space, both of which substantially decelerate the image generation process. To overcome these limitations, this paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We observed that Latent Consistency Models employing consistency distillation can effectively extract representative Consistency Features from noisy images. To blend the Consistency Features extracted from both content and style images, we introduce a Style Enhancement Attention Control technique that meticulously merges content and style features within the attention space of the target image. Moreover, we propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control. Extensive experiments have validated the effectiveness of our proposed framework in enhancing stylization efficiency and fidelity. The code is available at \url{https://github.com/liujin112/ZePo}.
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。
