Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual Injection, causing identity features to contaminate non-facial regions (e.g., backgrounds and lighting) and degrading text adherence. To address this without expensive fine-tuning, we propose SpatialID, a training-free spatially-adaptive identity modulation framework. SpatialID fundamentally decouples identity injection into face-relevant and context-free regions using a Spatial Mask Extractor derived from cross-attention responses. Furthermore, we introduce a Temporal-Spatial Scheduling strategy that dynamically adjusts spatial constraints - transitioning from Gaussian priors to attention-based masks and adaptive relaxation - to align with the diffusion generation dynamics. Extensive experiments on IBench demonstrate that SpatialID achieves state-of-the-art performance in text adherence (CLIP-T: 0.281), visual consistency (CLIP-I: 0.827), and image quality (IQ: 0.523), significantly eliminating background contamination while maintaining robust identity preservation.

翻译：个性化文本到图像生成旨在将特定身份特征融入任意场景。然而，现有免调优方法通常采用空间均匀的视觉注入，导致身份特征污染非面部区域（如背景与光照）并削弱文本遵循能力。为解决此问题并避免昂贵的微调，我们提出SpatialID——一种免训练的空间自适应身份调制框架。SpatialID基于跨注意力响应构建的空间掩码提取器，从根本上将身份注入解耦为面部相关区域与上下文无关区域。此外，我们提出时空调度策略，通过从高斯先验过渡到注意力掩码及自适应松弛的动态空间约束调整，使其与扩散生成动力学对齐。在IBench上的大量实验表明，SpatialID在文本遵循（CLIP-T: 0.281）、视觉一致性（CLIP-I: 0.827）和图像质量（IQ: 0.523）方面均达到最先进性能，显著消除背景污染的同时保持鲁棒的身份保持能力。