FlexIP：定制化圖像生成中保存與個性化的動態控制

FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation

April 10, 2025

作者: Linyan Huang, Haonan Lin, Yanning Zhou, Kaiwen Xiao

cs.AI

摘要

隨著二維生成模型的快速發展，如何在實現多樣化編輯的同時保持主體身份，已成為一個關鍵的研究焦點。現有方法通常面臨身份保持與個性化操控之間的固有權衡。我們提出了FlexIP，這是一種新穎的框架，通過兩個專用組件來解耦這些目標：用於風格操控的個性化適配器和用於身份維護的保持適配器。通過將這兩種控制機制顯式注入生成模型，我們的框架能夠在推理過程中通過動態調節權重適配器來實現靈活的參數化控制。實驗結果表明，我們的方法突破了傳統方法的性能限制，在支持更豐富的個性化生成能力的同時，實現了更優越的身份保持效果（項目頁面：https://flexip-tech.github.io/flexip/）。

English

With the rapid advancement of 2D generative models, preserving subject identity while enabling diverse editing has emerged as a critical research focus. Existing methods typically face inherent trade-offs between identity preservation and personalized manipulation. We introduce FlexIP, a novel framework that decouples these objectives through two dedicated components: a Personalization Adapter for stylistic manipulation and a Preservation Adapter for identity maintenance. By explicitly injecting both control mechanisms into the generative model, our framework enables flexible parameterized control during inference through dynamic tuning of the weight adapter. Experimental results demonstrate that our approach breaks through the performance limitations of conventional methods, achieving superior identity preservation while supporting more diverse personalized generation capabilities (Project Page: https://flexip-tech.github.io/flexip/).