SerialGen: Personalized Image Generation by First Standardization Then Personalization

TL;DR

SerialGen is a two-stage personalized image generation framework that standardizes reference images before generating consistent, text-controllable human characters, improving appearance fidelity and prompt responsiveness.

Contribution

The paper introduces SerialGen, a novel serial generation framework with a standardization stage and two modules, enhancing personalized image consistency and controllability.

Findings

Produces images with high appearance consistency

Accurately responds to diverse text prompts

Enhances serial image generation quality

Abstract

In this work, we are interested in achieving both high text controllability and whole-body appearance consistency in the generation of personalized human characters. We propose a novel framework, named SerialGen, which is a serial generation method consisting of two stages: first, a standardization stage that standardizes reference images, and then a personalized generation stage based on the standardized reference. Furthermore, we introduce two modules aimed at enhancing the standardization process. Our experimental results validate the proposed framework's ability to produce personalized images that faithfully recover the reference image's whole-body appearance while accurately responding to a wide range of text prompts. Through thorough analysis, we highlight the critical contribution of the proposed serial generation method and standardization model, evidencing enhancements in appearance consistency between reference and output images and across serial outputs generated from diverse text prompts. The term "Serial" in this work carries a double meaning: it refers to the two-stage method and also underlines our ability to generate serial images with consistent appearance throughout.