Sissi：通过语义-风格整合实现零样本风格引导图像合成
Sissi: Zero-shot Style-guided Image Synthesis via Semantic-style Integration
AI总结：
Sissi通过语义-风格整合实现零样本风格引导图像合成，采用上下文学习框架提升风格化效果与语义一致性。
摘要：
文本引导的图像生成随着大规模扩散模型的发展而迅速进步，但实现精确的风格化仍难以通过视觉示例达成。现有方法往往依赖于任务特定的重新训练或昂贵的反转过程，这可能会破坏内容完整性，降低风格保真度，并导致语义提示遵循与风格对齐之间的不满意的权衡。在本工作中，我们介绍了一个无需训练的框架，将风格引导的合成重新表述为一个上下文学习任务。在文本语义提示的指导下，我们的方法将参考风格图像与掩码目标图像进行连接，利用预训练的ReFlow-based修复模型，通过多模态注意力融合无缝整合语义内容与所需风格。我们进一步分析了多模态注意力融合中固有的不平衡性和噪声敏感性，并提出了一种动态语义-风格整合（DSSI）机制，该机制重新加权文本语义和风格视觉标记之间的注意力，有效解决指导冲突并提高输出连贯性。实验表明，我们的方法在高保真度的风格化方面表现优异，具有优越的语义-风格平衡和视觉质量，提供了一种简单而强大的替代方案，替代复杂且易产生伪影的先验方法。
英文摘要：
Text-guided image generation has advanced rapidly with large-scale diffusion models, yet achieving precise stylization with visual exemplars remains difficult. Existing approaches often depend on task-specific retraining or expensive inversion procedures, which can compromise content integrity, reduce style fidelity, and lead to an unsatisfactory trade-off between semantic prompt adherence and style alignment. In this work, we introduce a training-free framework that reformulates style-guided synthesis as an in-context learning task. Guided by textual semantic prompts, our method concatenates a reference style image with a masked target image, leveraging a pretrained ReFlow-based inpainting model to seamlessly integrate semantic content with the desired style through multimodal attention fusion. We further analyze the imbalance and noise sensitivity inherent in multimodal attention fusion and propose a Dynamic Semantic-Style Integration (DSSI) mechanism that reweights attention between textual semantic and style visual tokens, effectively resolving guidance conflicts and enhancing output coherence. Experiments show that our approach achieves high-fidelity stylization with superior semantic-style balance and visual quality, offering a simple yet powerful alternative to complex, artifact-prone prior methods.
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。
