VecGlypher: Unified Vector Glyph Generation with Language Models

TL;DR

On cross-family OOD evaluation, VecGlypher substantially outperforms both general-purpose LLMs and specialized vector-font baselines for text-only generation, while image-referenced generation reaches a state-of-the-art performance.

Abstract

Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, which limits accessibility and editability. We introduce VecGlypher, a single multimodal language model that generates high-fidelity vector glyphs directly from text descriptions or image exemplars. Given a style prompt, optional reference glyph images, and a target character, VecGlypher autoregressively emits SVG path tokens, avoiding raster intermediates and producing editable, watertight outlines in one pass. A typography-aware data and training recipe makes this possible: (i) a large-scale continuation stage on 39K noisy Envato fonts to master SVG syntax and long-horizon geometry, followed by (ii) post-training on 2.5K expert-annotated Google Fonts with descriptive tags and exemplars to align language and imagery with geometry; preprocessing normalizes coordinate frames, canonicalizes paths, de-duplicates families, and quantizes coordinates for stable long-sequence decoding. On cross-family OOD evaluation, VecGlypher substantially outperforms both general-purpose LLMs and specialized vector-font baselines for text-only generation, while image-referenced generation reaches a state-of-the-art performance, with marked gains over DeepVecFont-v2 and DualVector. Ablations show that model scale and the two-stage recipe are critical and that absolute-coordinate serialization yields the best geometry. VecGlypher lowers the barrier to font creation by letting users design with words or exemplars, and provides a scalable foundation for future multimodal design tools.

Figures (8)

• Figure 1: VecGlypher generates high-fidelity vector glyphs directly as editable SVG outlines under two types of conditioning: (a) image-referenced generation, where a handful of exemplar glyph images specify the style and the model synthesizes new glyphs in the same visual form; and (b) text-referenced generation, where a natural-language prompt drives the synthesis without requiring exemplars. The figure shows the synthesized wordmark and sample vector outlines, highlighting one-pass generation of clean, controllable contours for typography workflows.
• Figure 2: Paradigm comparisons. a) Prior image-referenced pipelines use separate image and vector encoder–decoders and a geometry post-optimizer. b) Diffusion-based approaches cascade image diffusion with a vector decoder. c) VecGlypher unifies both text- and image-referenced conditioning within a single LLM: given a style description or reference glyph images plus a target character, the model autoregressively emits SVG path tokens that detokenize to a valid SVG path. This formulation removes raster intermediates and exemplar-sheet requirements while producing directly editable vectors. A practical workflow is to first generate a few reference glyphs from text descriptions, then bootstrap with those images to synthesize the full font.
• Figure 3: VecGlypher pipeline and training recipe. a) A text tokenizer or image encoder condition the LLM ($||$ denotes mutually exclusive choice), which predicts the next SVG token until the path is produced; detokenization yields SVG paths that we rasterize for display only. b) Training is two-stage: 1) SFT on Envato (text-referenced only) teaches SVG syntax and long-horizon geometry; 2) SFT on Google Fonts (text- or image-referenced) aligns geometry to appearance instructions. No raster denoisers or post-optimizers are used.
• Figure 4: Text-referenced ablations. Representative text-to-glyph generations across model sizes and data regimens: ground truth (GT), Google-only 4B and 27B models, Envato-only 27B, mixed E+G 27B, and two-stage E$\to$G 27B. Using the same style tags across columns, scaling and the two-stage recipe yield cleaner closures, stable counters, and more faithful style. Please refer to the supplementary materials for comprehensive results.
• Figure 5: Image-referenced ablations. Given 1--8 reference glyphs from a font, we compare Google-only 4B/27B with two-stage variants (E$\to$G I and E$\to$G T,I). The two-stage settings at 27B best transfer style and preserve thin structures and closures; Google-only baselines underperform in geometry. Please refer to the supplementary materials for comprehensive results.