Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model

TL;DR

This paper introduces LVGM, a novel model for generating vectorized Chinese glyphs by predicting stroke sequences, enabling scalable and flexible character creation with a large dataset and validated by expert assessments.

Contribution

The paper presents a new large-scale Chinese SVG dataset and a stroke-based glyph generation model that extends LLM capabilities to vectorized character synthesis.

Findings

Model scales well with data size

Generated glyphs are semantically coherent

Expert validation confirms quality

Abstract

Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often seen as special sequences composed of ordered strokes. This concept extends to the token sequence prediction abilities of large language models (LLMs), enabling vectorized character generation through stroke modeling. In this paper, we propose a novel Large Vectorized Glyph Model (LVGM) designed to generate vectorized Chinese glyphs by predicting the next stroke. Initially, we encode strokes into discrete latent variables called stroke embeddings. Subsequently, we train our LVGM via fine-tuning DeepSeek LLM by predicting the next stroke embedding. With limited strokes given, it can generate complete characters, semantically elegant words, and even unseen verses in vectorized form. Moreover, we release a new large-scale Chinese SVG dataset containing 907,267 samples based on strokes for dynamically vectorized glyph generation. Experimental results show that our model has scaling behaviors on data scales. Our generated vectorized glyphs have been validated by experts and relevant individuals.