InstructBooth: Instruction-following Personalized Text-to-Image Generation
CoRR(2023)
摘要
Personalizing text-to-image models using a limited set of images for a
specific object has been explored in subject-specific image generation.
However, existing methods often face challenges in aligning with text prompts
due to overfitting to the limited training images. In this work, we introduce
InstructBooth, a novel method designed to enhance image-text alignment in
personalized text-to-image models without sacrificing the personalization
ability. Our approach first personalizes text-to-image models with a small
number of subject-specific images using a unique identifier. After
personalization, we fine-tune personalized text-to-image models using
reinforcement learning to maximize a reward that quantifies image-text
alignment. Additionally, we propose complementary techniques to increase the
synergy between these two processes. Our method demonstrates superior
image-text alignment compared to existing baselines, while maintaining high
personalization ability. In human evaluations, InstructBooth outperforms them
when considering all comprehensive factors. Our project page is at
https://sites.google.com/view/instructbooth.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要