We introduce DiffSketch, a method for generating a variety of stylized
sketches from images. Our approach focuses on selecting representative features
from the rich semantics of deep features within a pretrained diffusion model.
This novel sketch generation method can be trained with one manual drawing.
Furthermore, efficient sketch extraction is ensured by distilling a trained
generator into a streamlined extractor. We select denoising diffusion features
through analysis and integrate these selected features with VAE features to
produce sketches. Additionally, we propose a sampling scheme for training
models using a conditional generative approach. Through a series of
comparisons, we verify that distilled DiffSketch not only outperforms existing
state-of-the-art sketch extraction methods but also surpasses diffusion-based
stylization methods in the task of extracting sketches.

DiffSketch 是一种从图像中生成各种风格化素描的方法，通过从预先训练好的扩散模型中选择代表性特征，我们的方法专注于从深层特征的丰富语义中选择。这种新颖的素描生成方法可以通过一个手绘图进行训练，通过将经过训练的生成器提炼成简化的提取器，确保了高效的素描提取。我们通过分析选择去噪扩散特征，并将这些选定的特征与 VAE 特征结合起来生成素描。此外，我们提出了一种使用条件生成方法来训练模型的采样方案。通过一系列比较，我们验证了提炼的 DiffSketch 不仅优于现有最先进的素描提取方法，而且在提取素描的任务中超过了基于扩散的风格化方法。