Representative feature extraction during diffusion process for sketch extraction with one example

Sketching is both a fundamental artistic expression and a crucial aspect of art. The significance of sketching has increased alongside the development of sketch-based generative and editing models. To enable individuals to use sketch-based generative models effectively, personalizing sketch extraction is crucial. In response, we introduce DiffSketch, a novel method capable of generating various geometrically aligned sketches from text or images, using a single manual drawing for training the style. Our method exploits rich information available in features from a pretrained stable diffusion model to achieve effective domain adaptation. To further streamline the process of sketch extraction, we further refine our approach by distilling the knowledge from the trained generator into the image-to-sketch network, which is termed ${\text{DiffSketch}}_{\text{distilled}}$. Through a series of comparisons, we verify that our method not only outperforms existing state-of-the-art sketch extraction methods but also surpasses diffusion-based stylization methods in the task of extracting sketches. See https://github.com/kwanyun/diffsketch.