VecFusion: Vector Font Generation with Diffusion

TL;DR

VecFusion introduces a cascaded diffusion approach combining raster and vector models, utilizing transformers and novel vector representations to generate high-quality, diverse vector fonts with complex structures and precise control points.

Contribution

The paper proposes a novel cascaded diffusion architecture with transformer-based vector modeling and a new vector representation for improved font generation.

Findings

Produces higher quality vector fonts than previous models

Capable of generating complex structures and diverse styles

Uses a two-stage diffusion process for style and shape capture

Abstract

We present VecFusion, a new neural architecture that can generate vector fonts with varying topological structures and precise control point positions. Our approach is a cascaded diffusion model which consists of a raster diffusion model followed by a vector diffusion model. The raster model generates low-resolution, rasterized fonts with auxiliary control point information, capturing the global style and shape of the font, while the vector model synthesizes vector fonts conditioned on the low-resolution raster fonts from the first stage. To synthesize long and complex curves, our vector diffusion model uses a transformer architecture and a novel vector representation that enables the modeling of diverse vector geometry and the precise prediction of control points. Our experiments show that, in contrast to previous generative models for vector graphics, our new cascaded vector diffusion model generates higher quality vector fonts, with complex structures and diverse styles.