StyleComposer：无需训练的多参考风格组合方法

AI 摘要

arXiv 上发表了一篇题为 StyleComposer 的论文，提出了一种无需训练的多参考风格组合方法。该方法通过将颜色、纹理和结构等风格属性分别路由到扩散模型中分离效果最好的表示，并在去噪过程中协调这些路径，从而在无需训练或反转的情况下，同时满足多个参考风格和文本提示。该方法为每个属性提供了强度滑块，比现有方法更接近联合满足三个参考和提示。

正文节选

Computer Science > Computer Vision and Pattern Recognition Title:StyleComposer: Training-Free Multi-Reference Style Composition View PDF HTML (experimental) Abstract: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 other

发布时间：2026-08-07 12:00

抓取时间：2026-08-07 15:26

来源机构：arXiv