发表机构
Black Forest Labs（黑森林实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究个性化人物图像生成中面部保真度与外观一致性权衡问题，提出双分支基线及动态平衡缩放策略DBS，由自适应时间门控和区域感知优化组成，实验表明DBS比现有基线更好，为整体身份建模提供可控框架。
AI 中文摘要
个性化人物图像生成需要在局部面部细节和更广泛的外观线索上保留主体身份。现有方法通常只强调一种身份信息级别，导致面部保真度和整体外观一致性之间存在内在权衡。为此，我们首先提出一个简单的双分支基线，在共享生成框架内统一全局外观控制和局部面部控制。这种不同分支的简单组合产生了有希望的结果，但由于分支贡献不协调在实践中存在不稳定性。为此，我们提出动态平衡缩放（DBS），一种用于改善面部和外观身份协调的微调策略。DBS由两个组件组成：自适应时间门控，它沿着去噪轨迹动态调制分支贡献，以及区域感知优化，它改善面部、外观和全局监督的协调。这些设计共同减轻了持续的面部分支过度主导，并鼓励更有效的外观感知指导。我们还引入了Pexels-100，一个用于评估个性化人物生成中整体身份一致性的基准。实验表明，DBS在面部保真度和外观一致性之间比现有的开源基线实现了更好的权衡，同时为整体身份建模提供了一个可控的基本框架。
英文摘要
Personalized person image generation requires preserving subject identity across both local facial details and broader appearance cues. Existing methods typically emphasize only one level of identity information, leading to an inherent trade-off between facial fidelity and overall appearance consistency. To address this, we first propose a simple dual-branch baseline that unifies global appearance control and local facial control within a shared generation framework. This simple combination of different branches yields promising results, but suffers from instability in practice due to uncoordinated branch contributions. To this end, we propose Dynamic Balancing Scaling (DBS), a fine-tuning strategy for improving face and appearance identity coordination. DBS consists of two components: adaptive temporal gating, which dynamically modulates branch contributions along the denoising trajectory, and region-aware optimization, which improves the coordination of facial, appearance, and global supervision. Together, these designs alleviate persistent face-branch over-dominance and encourage more effective appearance-aware guidance. We also introduce Pexels-100, a benchmark for evaluating holistic identity consistency in personalized person generation. Experiments show that DBS achieves a better trade-off between facial fidelity and appearance consistency than existing open-source baselines, while providing a controllable basic framework for holistic identity modeling.
