分离颜色与风格，实现无需微调的通用风格迁移。
CDST: Color Disentangled Style Transfer for Universal Style Reference Customization
- 双流架构分离颜色与风格，强制风格分支无视颜色信息。
- 无需微调即可保持风格特征，提升风格相似度并保留编辑能力。
- 适合需要快速适配多种风格的图像生成应用。
我们提出颜色解耦风格迁移（CDST），一种新颖高效的双流风格迁移训练范式，完全将颜色与风格分离，并强制风格流对颜色无感知。仅用一个统一模型，CDST 在推理阶段即可实现无需微调的通用风格迁移能力。尤其首次以无微调方式解决了保留特征的风格-内容参考风格迁移问题。通过多特征图像嵌入压缩，CDST 显著提升风格相似度；同时基于扩散模型UNet解耦规律设计的新风格定义，保持了强大的编辑能力。经全面的定性、定量实验及人类评估，CDST 在多种风格迁移任务中达到领先性能。
原文摘要 · Abstract (English)
We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm which completely isolates color from style and forces the style stream to be color-blinded. With one same model, CDST unlocks universal style transfer capabilities in a tuning-free manner during inference. Especially, the characteristics-preserved style transfer with style and content references is solved in the tuning-free way for the first time. CDST significantly improves the style similarity by multi-feature image embeddings compression and preserves strong editing capability via our new CDST style definition inspired by Diffusion UNet disentanglement law. By conducting thorough qualitative and quantitative experiments and human evaluations, we demonstrate that CDST achieves state-of-the-art results on various style transfer tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。