LogoDiffuser: 无需训练的多语言标志生成与风格化通过字母感知注意力控制
LogoDiffuser: Training-Free Multilingual Logo Generation and Stylization via Letter-Aware Attention Control
AI总结：
LogoDiffuser通过字母感知注意力控制，无需训练实现多语言标志生成与风格化，通过多模态扩散变换器整合字符结构与视觉设计，提升多语言标志生成效果。
摘要：
近年来，文本到图像生成的进展令人印象深刻，但生成和谐融合视觉和文本元素的多语言设计标志仍是一项具有挑战性的任务。现有方法在应用创意风格时往往扭曲字符几何结构，并且难以在不额外训练的情况下支持多语言文本生成。为了解决这些挑战，我们提出了LogoDiffuser，一种无需训练的方法，利用多模态扩散变换器合成多语言标志设计。与使用文本提示不同，我们输入目标字符作为图像，从而能够稳健地控制字符结构，无论语言如何。我们首先分析联合注意力机制以识别核心令牌，这些是强烈响应文本结构的令牌。基于这一观察，我们的方法通过注入最有信息量的注意力地图来整合字符结构和视觉设计。此外，我们对注意力地图进行逐层聚合，以缓解跨层的注意力偏移，并获得一致的核心令牌。广泛的实验和用户研究证明，我们的方法在多语言标志生成中实现了最先进的性能。
英文摘要：
Recent advances in text-to-image generation have been remarkable, but generating multilingual design logos that harmoniously integrate visual and textual elements remains a challenging task. Existing methods often distort character geometry when applying creative styles and struggle to support multilingual text generation without additional training. To address these challenges, we propose LogoDiffuser, a training-free method that synthesizes multilingual logo designs using the multimodal diffusion transformer. Instead of using textual prompts, we input the target characters as images, enabling robust character structure control regardless of language. We first analyze the joint attention mechanism to identify core tokens, which are tokens that strongly respond to textual structures. With this observation, our method integrates character structure and visual design by injecting the most informative attention maps. Furthermore, we perform layer-wise aggregation of attention maps to mitigate attention shifts across layers and obtain consistent core tokens. Extensive experiments and user studies demonstrate that our method achieves state-of-the-art performance in multilingual logo generation.
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。
