# SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation Source: [SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:46:56.735Z Authors: Ellie Arar, Yarden Frenkel, Daniel Cohen-Or, Ariel Shamir, Yael Vinker Published: 2025-02-12T18:57:12.000Z ## Abstract Recent advancements in large vision-language models have enabled highly expressive and diverse vector sketch generation. However, state-of-the-art methods rely on a time-consuming optimization process involving repeated feedback from a pretrained model to determine stroke placement. Consequently, despite producing impressive sketches, these methods are limited in practical applications. In this work, we introduce SwiftSketch, a diffusion model for image-conditioned vector sketch generation that can produce high-quality sketches in less than a second. SwiftSketch operates by progressively denoising stroke control points sampled from a Gaussian distribution. Its transformer-decoder architecture is designed to effectively handle the discrete nature of vector representation and capture the inherent global dependencies between strokes. To train SwiftSketch, we construct a synthetic dataset of image-sketch pairs, addressing the limitations of existing sketch datasets, which are often created by non-artists and lack professional quality. For generating these synthetic sketches, we introduce ControlSketch, a method that enhances SDS-based techniques by incorporating precise spatial control through a depth-aware ControlNet. We demonstrate that SwiftSketch generalizes across diverse concepts, efficiently producing sketches that combine high fidelity with a natural and visually appealing style. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image-Based Sketch Generation on ControlSketch (seen)](): Image-Based Sketch Generation; ControlSketch (seen); MS-SSIM: 69.1. - [Image-Based Sketch Generation on ControlSketch (unseen)](): Image-Based Sketch Generation; ControlSketch (unseen); MS-SSIM: 0.691. - [Image-guided portrait sketch generation on CelebA-HQ 1024x1024 (randomly sampled 50 images)](): Image-guided portrait sketch generation; CelebA-HQ 1024x1024 (randomly sampled 50 images); LPIPS: 0.54. ## Original sources and implementation [Original paper]() [PDF]()