ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning

Sun Yat-Sen University(SYSU)    ByteDance Inc.
  *Equal Contribution   Project Lead

Abstract

The rapid development of diffusion models has triggered diverse applications. Identity-preserving text-to-image generation (ID-T2I) particularly has received significant attention due to its wide range of application scenarios like AI portrait and advertising. While existing ID-T2I methods have demonstrated impressive results, several key challenges remain: (1) It is hard to maintain the identity characteristics of reference portraits accurately, (2) The generated images lack aesthetic appeal especially while enforcing identity retention, and (3) There is a limitation that cannot be compatible with LoRA-based and Adapter-based methods simultaneously. To address these issues, we present \textbf{ID-Aligner}, a general feedback learning framework to enhance ID-T2I performance. To resolve identity features lost, we introduce identity consistency reward fine-tuning to utilize the feedback from face detection and recognition models to improve generated identity preservation. Furthermore, we propose identity aesthetic reward fine-tuning l everaging rewards from human-annotated preference data and automatically constructed feedback on character structure generation to provide aesthetic tuning signals. Thanks to its universal feedback fine-tuning framework, our method can be readily applied to both LoRA and Adapter models, achieving consistent performance gains. Extensive experiments on SD1.5 and SDXL diffusion models validate the effectiveness of our approach.

Pipeline


Pipeline: Our method exploits face detection and face encoder to achieve identity preservation via feedback learning. We further incorporated the aesthetic reward model to improve the visual appeal of the generation results. Our method is a general framework that can be applied to both LoRA and Adapter methods.

Comparsions

Diverse Prompts Results

More results

BibTeX

@misc{chen2024idaligner,
      title={ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning}, 
      author={Weifeng Chen and Jiacheng Zhang and Jie Wu and Hefeng Wu and Xuefeng Xiao and Liang Lin},
      year={2024},
      eprint={2404.15449},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
      }