StyleComposer：无需训练的多参考风格合成
StyleComposer: Training-Free Multi-Reference Style Composition
AI总结：
针对现有参考引导风格方法无法控制各属性来源与强度的问题，提出无需训练的StyleComposer，通过将各风格属性路由至最佳表示并协调去噪时间，实现更贴合多参考与提示的风格合成，且支持各属性强度调节。
AI中文摘要：
绘画的风格并非单一整体，色彩、纹理和结构可来自不同来源。现有参考引导方法将它们作为单一风格信号传递，使用户无法控制各属性的来源与强度。我们探究扩散模型中某一属性可改变而其余属性保持不变的位置，发现无单一表示能隔离所有三者。因此提出的StyleComposer将各风格属性路由至其分离度最佳的表示，并在去噪时间上协调这些路由。无需训练或反转，它能比现有方法更紧密地同时满足三个参考和提示，且为每个属性提供一个强度滑块。项目页面：this https URL
英文摘要：
The style of a painting is not monolithic: color, texture, and structure may come from different sources. Existing reference-guided methods transfer them as one style signal, leaving each attribute's source and strength outside the user's control. We ask where in a diffusion model one attribute can change while the others hold, and find that no single representation isolates all three. The proposed StyleComposer therefore routes each style attribute through the representation where it separates best and coordinates the routes over denoising time. Without training or inversion, it satisfies three references and the prompt jointly more closely than prior methods, and exposes one strength slider per attribute. Project page: https://lexxsh.github.io/StyleComposer
