Art reinterpretation is the practice of creating a variation of a reference work, making a paired artwork that exhibits a distinct artistic style. We ask if such an image pair can be used to customize a generative model to capture the demonstrated stylistic difference. We propose Pair Customization, a new customization method that learns stylistic difference from a single image pair and then applies the acquired style to the generation process. Unlike existing methods that learn to mimic a single concept from a collection of images, our method captures the stylistic difference between paired images. This allows us to apply a stylistic change without overfitting to the specific image content in the examples. To address this new task, we employ a joint optimization method that explicitly separates the style and content into distinct LoRA weight spaces. We optimize these style and content weights to reproduce the style and content images while encouraging their orthogonality. During inference, we modify the diffusion process via a new style guidance based on our learned weights. Both qualitative and quantitative experiments show that our method can effectively learn style while avoiding overfitting to image content, highlighting the potential of modeling such stylistic differences from a single image pair.

翻译：艺术再诠释是指创作参考作品的变体，形成具有独特艺术风格的配对艺术品。我们探究是否可以利用这种图像对来定制生成模型，以捕捉所展示的风格差异。我们提出“配对定制”（Pair Customization）这一新方法，该方法从单一图像对中学习风格差异，并将习得的风格应用于生成过程。与现有方法从图像集合中学习模仿单一概念不同，我们的方法捕捉配对图像之间的风格差异，从而能够在不过度拟合示例中特定图像内容的情况下应用风格变化。为应对这一新任务，我们采用联合优化方法，将风格和内容显式分离到不同的 LoRA 权重空间中。我们优化这些风格和内容权重，以再现风格图像和内容图像，同时鼓励它们之间的正交性。在推理阶段，我们基于学习到的权重，通过新的风格引导修改扩散过程。定性和定量实验均表明，我们的方法能够有效学习风格，同时避免对图像内容的过拟合，凸显了从单一图像对建模此类风格差异的潜力。