忠于本源：具有平滑过渡的连续图像风格化
Staying True to the Origin: Continuous Image Stylization with Smooth Transitions
浏览论文内容
中文总结 AI 辅助
该研究针对图像风格化的内容保留与过渡问题，提出两阶段训练策略及风格强度感知样条插值方法，让基于DiT的模型实现精确连续的风格强度控制，生成高保真结果。
中文摘要 AI 辅助
生成模型的近期进展在文本和图像条件编辑方面取得了显著性能，但在参考另一图像的风格模式的同时保留给定图像的内容仍具挑战性，常导致不可控的风格化结果。本文从连续控制的角度研究图像风格化，旨在让基于现代扩散Transformer（DiT）的多参考编辑模型实现三点目标：一是忠实地保留内容图像的语义结构，二是呈现强烈的风格化效果，三是在两者之间实现平滑过渡。为此，我们提出一种简单却有效的两阶段训练策略，以及一种感知风格强度的样条公式。具体而言，第一阶段训练模型生成强风格化输出，同时尽可能保留内容语义；第二阶段中，冻结基础模型，我们学习一组锚定投影器，将不同的风格强度映射到模型参数空间。推理阶段，通过在低秩空间中执行感知风格强度的样条插值，即便模型仅用少量离散强度水平训练，我们的方法仍能实现对风格强度的连续控制。大量实验表明，该方法支持对风格强度的精确连续操控，同时利用现代DiT模型生成高保真结果。项目页面：this https URL。
英文摘要
Recent advances in generative models have achieved remarkable performance in text- and image-conditioned editing. However, preserving the content of a given image while referencing style patterns from another remains challenging, often leading to uncontrollable stylization results. In this paper, we approach image stylization from the perspective of continuous control, aiming to enable modern Diffusion Transformer (DiT)-based multi-reference editing models to (1) faithfully preserve the semantic structure of the content image, (2) render strong stylization effects, and (3) smoothly transition between the two. To this end, we propose a simple yet effective two-stage training strategy along with a style-strength-aware spline formulation. Specifically, in the first stage, the model is trained to produce strongly stylized outputs while preserving the content semantics as much as possible. In the second stage, with the base model frozen, we learn a set of anchor projectors that map various stylization strengths into the model parameter space. During inference, by performing style-strength-aware spline interpolation in a low-rank space, our method enables continuous control over stylization strength, even though the model is trained with only a few discrete strength levels. Extensive experiments demonstrate that our method supports precise and continuous manipulation of stylization strength while generating high-fidelity results with modern DiT models. Project page: https://reychiaro.github.io/StyleController.
