AnyStory：迈向文本到图像生成中单一与多主体的统一个性化
AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation
AI总结：
本文提出AnyStory统一方法，通过“先编码后路由”机制结合ReferenceNet与CLIP视觉编码器及实例感知路由器，解决了文本到图像生成中单一与多主体高保真个性化难题。
摘要：
最近，大规模生成模型展现出了出色的文本到图像生成能力。然而，生成具有特定主体的高保真个性化图像仍然存在挑战，尤其是在涉及多个主体的情况下。在本文中，我们提出了AnyStory，一种用于个性化主体生成的统一方法。AnyStory不仅实现了单一主体的高保真个性化，还实现了多主体的个性化，且不牺牲主体保真度。具体而言，AnyStory以“先编码后路由”的方式对主体个性化问题进行建模。在编码步骤中，AnyStory利用通用且强大的图像编码器，即ReferenceNet，结合CLIP视觉编码器，实现对主体特征的高保真编码。在路由步骤中，AnyStory利用解耦的实例感知主体路由器，准确感知并预测对应主体在潜在空间中的潜在位置，并指导主体条件的注入。详细的实验结果表明，我们的方法在保留主体细节、对齐文本描述以及多主体个性化方面表现出色。项目页面位于 https://aigcdesigngroup.github.io/AnyStory/ 。
英文摘要：
Recently, large-scale generative models have demonstrated outstanding text-to-image generation capabilities. However, generating high-fidelity personalized images with specific subjects still presents challenges, especially in cases involving multiple subjects. In this paper, we propose AnyStory, a unified approach for personalized subject generation. AnyStory not only achieves high-fidelity personalization for single subjects, but also for multiple subjects, without sacrificing subject fidelity. Specifically, AnyStory models the subject personalization problem in an "encode-then-route" manner. In the encoding step, AnyStory utilizes a universal and powerful image encoder, i.e., ReferenceNet, in conjunction with CLIP vision encoder to achieve high-fidelity encoding of subject features. In the routing step, AnyStory utilizes a decoupled instance-aware subject router to accurately perceive and predict the potential location of the corresponding subject in the latent space, and guide the injection of subject conditions. Detailed experimental results demonstrate the excellent performance of our method in retaining subject details, aligning text descriptions, and personalizing for multiple subjects. The project page is at https://aigcdesigngroup.github.io/AnyStory/ .
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。
