LIPE: Learning Personalized Identity Prior for Non-rigid Image Editing
This addresses identity inconsistency in image editing for users needing personalized modifications, representing an incremental advance in a specific domain.
The paper tackles the problem of inconsistent identity in non-rigid image editing by learning a personalized identity prior from a few images of a subject, resulting in improved editing performance over leading methods as shown in experiments.
Although recent years have witnessed significant advancements in image editing thanks to the remarkable progress of text-to-image diffusion models, the problem of non-rigid image editing still presents its complexities and challenges. Existing methods often fail to achieve consistent results due to the absence of unique identity characteristics. Thus, learning a personalized identity prior might help with consistency in the edited results. In this paper, we explore a novel task: learning the personalized identity prior for text-based non-rigid image editing. To address the problems in jointly learning prior and editing the image, we present LIPE, a two-stage framework designed to customize the generative model utilizing a limited set of images of the same subject, and subsequently employ the model with learned prior for non-rigid image editing. Experimental results demonstrate the advantages of our approach in various editing scenarios over past related leading methods in qualitative and quantitative ways.