无需训练即可精准控制草图风格，支持多风格生成
Text to Sketch Generation with Multi-Styles
- 用文本提示和参考草图引导扩散模型生成
- 通过线性平滑减少内容泄露，提升低相似度场景质量
- 支持多参考草图联合控制，适合风格化设计应用
视觉语言模型的进步推动了草图生成的发展。然而，现有方法主要关注通用合成，缺乏对草图风格的精确控制。本文提出一种基于扩散模型的免训练框架，通过文本提示和参考风格草图实现显式风格引导。不同于以往通过覆盖自注意力中的键值矩阵进行风格迁移的方法，我们引入参考特征作为辅助信息，采用线性平滑并结合风格-内容引导机制，有效降低参考草图的内容泄露，尤其在参考与目标草图结构差异较大时仍能保持高质量生成。此外，通过联合AdaIN模块整合多个参考草图特征，扩展框架以支持可控多风格生成。大量实验表明，该方法在风格对齐精度和风格控制灵活性上均表现优异。官方代码已开源：https://github.com/CMACH508/M3S。
原文摘要 · Abstract (English)
Recent advances in vision-language models have facilitated progress in sketch generation. However, existing specialized methods primarily focus on generic synthesis and lack mechanisms for precise control over sketch styles. In this work, we propose a training-free framework based on diffusion models that enables explicit style guidance via textual prompts and referenced style sketches. Unlike previous style transfer methods that overwrite key and value matrices in self-attention, we incorporate the reference features as auxiliary information with linear smoothing and leverage a style-content guidance mechanism. This design effectively reduces content leakage from reference sketches and enhances synthesis quality, especially in cases with low structural similarity between reference and target sketches. Furthermore, we extend our framework to support controllable multi-style generation by integrating features from multiple reference sketches, coordinated via a joint AdaIN module. Extensive experiments demonstrate that our approach achieves high-quality sketch generation with accurate style alignment and improved flexibility in style control. The official implementation of M3S is available at https://github.com/CMACH508/M3S.
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。