FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation
This addresses a critical research focus in generative AI for applications requiring customized image generation, though it appears incremental as it builds on existing methods to improve trade-offs.
The paper tackles the problem of preserving subject identity while enabling diverse editing in 2D generative models, introducing FlexIP to decouple these objectives and achieving superior identity preservation with more diverse personalized generation capabilities.
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/).