AnyStory：朝向在文本到圖像生成中統一的單一和多主題個性化方向前進

AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation

January 16, 2025

作者: Junjie He, Yuxiang Tuo, Binghui Chen, Chongyang Zhong, Yifeng Geng, Liefeng Bo

cs.AI

摘要

最近，大規模生成模型展示了出色的文本到圖像生成能力。然而，在生成具有特定主題的高保真個性化圖像方面仍然存在挑戰，特別是在涉及多個主題的情況下。本文提出了AnyStory，一種統一的個性化主題生成方法。AnyStory不僅實現了對單個主題的高保真個性化，還能對多個主題進行個性化，而不會犧牲主題的保真度。具體來說，AnyStory以“編碼-路由”方式建模主題個性化問題。在編碼步驟中，AnyStory利用通用且強大的圖像編碼器，即ReferenceNet，結合CLIP視覺編碼器，實現對主題特徵的高保真編碼。在路由步驟中，AnyStory利用解耦的實例感知主題路由器準確感知並預測潛在主題在潛在空間中的位置，並引導主題條件的注入。詳細的實驗結果展示了我們的方法在保留主題細節、對齊文本描述和對多個主題進行個性化方面的優異表現。該項目頁面位於 https://aigcdesigngroup.github.io/AnyStory/ 。

English

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/ .