UnZipLoRA：从单张图像中分离内容与风格
UnZipLoRA: Separating Content and Style from a Single Image
AI总结：
本文提出UnZipLoRA方法，通过同时训练两个LoRA从单张图像中解耦主体与风格，确保LoRA兼容性并支持独立操作，经评估其效果优于现有先进方法。
摘要：
本文介绍了UnZipLoRA，这是一种将图像分解为其组成主体和风格的方法，两者分别表示为两个不同的LoRA（低秩适配）。与现有仅孤立关注主体或风格、或需为两者分别提供训练集的个性化技术不同，UnZipLoRA通过同时训练两个LoRA，从单张图像中解耦这些元素。UnZipLoRA确保生成的LoRA具有兼容性，即能通过直接相加无缝组合。它支持主体和风格的独立操作与重新语境化，包括生成两者的变体、将提取的风格应用于新主体，以及重组以重建原图或创建新变体。为应对主体与风格纠缠的挑战，UnZipLoRA采用新颖的提示分离技术，以及列和块分离策略，以准确保留主体和风格特征，并确保所学LoRA的兼容性。通过人类研究和定量指标的评估表明，UnZipLoRA相比DreamBooth-LoRA、Inspiration Tree和B-LoRA等其他最先进方法具有有效性。
英文摘要：
This paper introduces UnZipLoRA, a method for decomposing an image into its constituent subject and style, represented as two distinct LoRAs (Low-Rank Adaptations). Unlike existing personalization techniques that focus on either subject or style in isolation, or require separate training sets for each, UnZipLoRA disentangles these elements from a single image by training both the LoRAs simultaneously. UnZipLoRA ensures that the resulting LoRAs are compatible, i.e., they can be seamlessly combined using direct addition. UnZipLoRA enables independent manipulation and recontextualization of subject and style, including generating variations of each, applying the extracted style to new subjects, and recombining them to reconstruct the original image or create novel variations. To address the challenge of subject and style entanglement, UnZipLoRA employs a novel prompt separation technique, as well as column and block separation strategies to accurately preserve the characteristics of subject and style, and ensure compatibility between the learned LoRAs. Evaluation with human studies and quantitative metrics demonstrates UnZipLoRA's effectiveness compared to other state-of-the-art methods, including DreamBooth-LoRA, Inspiration Tree, and B-LoRA.
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。
