SVGDreamer: Text Guided SVG Generation with Diffusion Model

Text-guided scalable vector graphics (SVG) synthesis has broad applications in icon and sketch generation. However, existing text-to-SVG methods often suffer from limited editability, suboptimal visual quality, and low sample diversity. To address these challenges, we propose $\mathbf{\text{SVGDreamer}}$, a novel framework for text-guided vector graphics synthesis. Our method introduces a $\mathbf{\text{semantic-driven}}\mathbf{\text{image}}\mathbf{\text{vectorization}}\mathbf{\text{(SIVE)}}$ process, which decomposes the generation procedure into foreground objects and background elements, thereby improving structural controllability and editability. In particular, SIVE incorporates attention-based primitive control and an attention-mask loss to facilitate fine-grained manipulation of individual vector elements. To further improve generation quality and diversity, we propose $\mathbf{\text{Vectorized}}\mathbf{\text{Particle-based}}\mathbf{\text{Score}}\mathbf{\text{Distillation}}\mathbf{\text{(VPSD)}}$, which models SVGs as distributions over control points and colors. Compared with existing text-to-SVG optimization methods, VPSD alleviates over-smoothed shapes, over-saturated colors, limited diversity, and slow convergence. Moreover, VPSD leverages a reward model to reweight vector particles, leading to better visual aesthetics and faster convergence. Extensive experiments demonstrate that SVGDreamer consistently outperforms existing baselines in editability, visual quality, and diversity. Project page: https://ximinng.github.io/SVGDreamer-project/