一个LoRA搞定图像风格迁移，稳定又高效。
AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer
- 用单一LoRA统一捕捉风格，避免多适配器冲突。
- 无需训练内容引导，直接利用模型注意力保持结构完整。
- 适合追求高可控性和高质量输出的风格迁移用户。
图像引导风格迁移旨在将风格图像的艺术特征应用于内容图像，同时保留其语义结构和布局。尽管扩散模型取得进展，现有方法在内容与风格解耦上仍面临挑战，尤其当独立优化的适配器简单组合时，会产生适配器冲突，限制推理中内容-风格平衡的控制力。我们进一步证明，通过预训练模型的内部注意力直接获取的免训练结构引导，相比专用内容LoRA适配器，在结构保真度和计算效率上表现更优。基于此，我们提出AnyStyle，一种简化的图像引导风格迁移框架。该框架采用统一的单适配器范式，从风格图像中一致捕获风格，并结合来自内容图像的免训练结构引导，从而避免多适配器间的复杂纠缠，提升可控性与稳定性。大量实验表明，本方法在定量性能上具有竞争力，且显著提升感知质量。代码已开源：https://github.com/Yvan1001/AnyStyle。
原文摘要 · Abstract (English)
Image-guided style transfer aims to apply the artistic characteristics of a style image to a content image while preserving its semantic structure and layout. Despite advances in diffusion-based methods, existing approaches often face challenges in disentangling content and style, particularly when independently optimized adapters are naively combined, causing conflicts between adapters and limiting controllability over the content-style balance in inference. We further demonstrate that training-free structural guidance directly derived from the content image through the internal attention of pre-trained model outperforms a dedicated content LoRA adapter in terms of structural fidelity and computational efficiency. Building on these observations, we propose AnyStyle, a streamlined framework for image-guided style transfer. The framework adopts a unified single-adapter paradigm for coherent style capture from the style image and incorporates training-free structural guidance from the content image, thus avoiding complex entanglement between multiple adapters and improving controllability and stability. Extensive experiments show that our method delivers competitive quantitative performance and significantly improved perceptual quality. Code is available at https://github.com/Yvan1001/AnyStyle.
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。