无训练的主体增强注意力引导用于组合式文本到图像生成
Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
AI总结：
针对主体驱动文本到图像生成中组合主体的对象缺失与属性混淆问题，提出无训练注意力引导方法，实现精确属性绑定，并提出GroundingScore指标验证有效性。
摘要：
现有的主体驱动文本到图像生成模型存在繁琐的微调步骤，并难以同时保持文本-图像对齐和主体保真度。在生成组合式主体时，常遇到对象缺失和属性混淆等问题，即输入提示中的某些主体未被生成或其属性被错误组合。为解决这些局限，我们提出了一种主体驱动生成框架，并引入无训练引导在推理阶段干预生成过程。该方法强化注意力图，实现对每个主体的精确属性绑定和特征注入。值得注意的是，我们的方法展现出卓越的零样本生成能力，尤其在具有挑战性的组合生成任务中。此外，我们提出了一种新指标GroundingScore，以全面评估主体对齐程度。所获得的定量结果有力证明了所提方法的有效性。代码即将发布。
英文摘要：
Existing subject-driven text-to-image generation models suffer from tedious fine-tuning steps and struggle to maintain both text-image alignment and subject fidelity. For generating compositional subjects, it often encounters problems such as object missing and attribute mixing, where some subjects in the input prompt are not generated or their attributes are incorrectly combined. To address these limitations, we propose a subject-driven generation framework and introduce training-free guidance to intervene in the generative process during inference time. This approach strengthens the attention map, allowing for precise attribute binding and feature injection for each subject. Notably, our method exhibits exceptional zero-shot generation ability, especially in the challenging task of compositional generation. Furthermore, we propose a novel metric GroundingScore to evaluate subject alignment thoroughly. The obtained quantitative results serve as compelling evidence showcasing the effectiveness of our proposed method. The code will be released soon.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
