PSR：利用成对主体一致性奖励扩展多主体个性化图像生成
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
提出可扩展的多主体数据生成管线与成对主体一致性奖励，结合强化学习后训练，可直接用于提升现有个性化生成模型在多主体场景下的主体保真度与文本可控性。
原文依据 we design a set of Pairwise Subject-Consistency Rewards and general-purpose rewards, which are incorporated into a refined reinforcement learning stage.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单主体个性化生成模型已展现出显著效果，凸显其巨大潜力。然而，当扩展到多主体时，现有模型往往性能下降，尤其是在保持主体一致性和遵循文本提示方面。我们将这些局限归因于缺乏高质量多主体数据集和精细的后训练策略。为解决这些挑战，我们提出了一种可扩展的多主体数据生成管线，利用强大的单主体生成模型构建多样且高质量的多主体训练数据。通过该数据集，我们首先使单主体个性化模型获得合成多图像和多主体场景的知识。此外，为增强主体一致性和文本可控性，我们设计了一组成对主体一致性奖励和通用奖励，并将其纳入精细的强化学习阶段。为全面评估多主体个性化，我们引入了一个新基准，通过三个维度下的七个子集评估模型性能。大量实验证明了我们的方法在推进多主体个性化图像生成方面的有效性。Github链接：https://github.com/wang-shulei。
英文原文摘要 1370 字符
Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance, particularly in maintaining subject consistency and adhering to textual prompts. We attribute these limitations to the absence of high-quality multi-subject datasets and refined post-training strategies. To address these challenges, we propose a scalable multi-subject data generation pipeline that leverages powerful single-subject generation models to construct diverse and high-quality multi-subject training data. Through this dataset, we first enable single-subject personalization models to acquire knowledge of synthesizing multi-image and multi-subject scenarios. Furthermore, to enhance both subject consistency and text controllability, we design a set of Pairwise Subject-Consistency Rewards and general-purpose rewards, which are incorporated into a refined reinforcement learning stage. To comprehensively evaluate multi-subject personalization, we introduce a new benchmark that assesses model performance using seven subsets across three dimensions. Extensive experiments demonstrate the effectiveness of our approach in advancing multi-subject personalized image generation. Github Link: https://github.com/wang-shulei.