Tutorials
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
arXiv:2306.14685v5 Announce Type: replace-cross Abstract: We demonstrate that pre-trained text-to-image diffusion models, despite being trained on raster images, possess a remarkable capacity to guide
arXiv:2306.14685v5 Announce Type: replace-cross Abstract: We demonstrate that pre-trained text-to-image diffusion models, despite being trained on raster images, possess a remarkable capacity to guide vector sketch synthesis. In this paper, we introduce DiffSketcher, a novel algorithm for generating vectorized free-hand sketches directly from natural language prompts. Our method optimizes a set of Bezier curves via an extended Score Distillation Sampling (SDS) loss, successfully bridging a raster-level diffusion prior with a parametric vector generator. To further accelerate the generation process, we propose a stroke initialization strategy driven by the diffusion model's intrinsic attention maps. Results show that DiffSketcher produces sketches across varying levels of abstraction while maintaining the structural integrity and essential visual details of the subject. Experiments confirm that our approach yields superior perceptual quality and controllability over existing methods. The code and demo are available at https://ximinng.github.io/DiffSketcher-project/
Related
- BADiff: Bandwidth Adaptive Diffusion Model
- ODE-free Neural Flow Matching for One-Step Generative Modeling
- Adversarial Flow Models
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
Source: arXiv cs.AI | 2026-04-10