Diffusion-based style transfer must balance inference efficiency with stylization fidelity. Adapter-based methods are efficient, but they inject style as an external condition and can either weaken reference-specific appearance or copy reference semantics into the generated image. Optimization-based personalization methods such as LoRA internalize style more effectively, but require a separate training process for every new style. We introduce i2L (image-to-LoRA), a framework that amortizes style LoRA training into a single forward pass. Given one or more reference images, i2L predicts LoRA weights for a text-to-image model, enabling immediate style instantiation without per-style optimization. The architecture combines an image encoder, learnable LoRA queries, and compressed decoding heads that generate adapted matrices. Training on semantically diverse style pairs encourages the predictor to preserve appearance cues while suppressing reference-content copying. Experiments on Z-Image, FLUX.2, and Hidream-O1 show that i2L improves style fidelity, prompt alignment, and perceptual quality over existing baselines. Because i2L produces explicit LoRA weights, it also supports asymmetric classifier-free guidance, multi-reference style fusion, and composition with controllable-generation modules.

翻译：基于扩散的风格迁移需在推理效率与风格化保真度之间寻求平衡。适配器类方法虽高效，但将风格作为外部条件注入，可能导致参考图像外观特征弱化或语义被复制至生成图像。基于优化的个性化方法（如LoRA）能更有效内化风格，但需为每个新风格单独训练。我们提出i2L（图像至LoRA）框架，将风格LoRA训练摊销至单次前向传播。给定一张或多张参考图像，i2L可预测文生图模型的LoRA权重，无需逐风格优化即可即时实例化风格。其架构融合图像编码器、可学习LoRA查询与生成适配矩阵的压缩解码头。在语义多样化的风格对上进行训练，可促使预测器在抑制参考语义复制的同时保留外观线索。在Z-Image、FLUX.2和Hidream-O1上的实验表明，i2L在风格保真度、提示对齐及感知质量上均超越现有基线。由于i2L生成显式LoRA权重，还支持非对称分类器自由引导、多参考风格融合及与可控生成模块的组合。