Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization

TL;DR

This paper introduces Character-Adapter, a novel framework that uses prompt-guided segmentation and region-level adapters to generate high-fidelity, consistent character images, significantly improving over previous methods.

Contribution

The paper presents a new plug-and-play framework that enhances character consistency in image generation by addressing feature extraction and concept confusion issues.

Findings

Achieves 24.8% improvement in character consistency.

Outperforms existing methods in quantitative evaluations.

Demonstrates high-fidelity character preservation in qualitative results.

Abstract

Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encountered challenges in preserving characters with high-fidelity consistency due to inadequate feature extraction and concept confusion of reference characters. Therefore, we propose Character-Adapter, a plug-and-play framework designed to generate images that preserve the details of reference characters, ensuring high-fidelity consistency. Character-Adapter employs prompt-guided segmentation to ensure fine-grained regional features of reference characters and dynamic region-level adapters to mitigate concept confusion. Extensive experiments are conducted to validate the effectiveness of Character-Adapter. Both quantitative and qualitative results demonstrate that Character-Adapter achieves the state-of-the-art performance of consistent character generation, with an improvement of 24.8% compared with other methods. Our code will be released at https://github.com/Character-Adapter/Character-Adapter.