Papers
arxiv:2609.02349

GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors

Published on Nov 11
Authors:
,
,
,
,
,
,

Abstract

GlyphAnchor enhances text-to-image and image-editing diffusion transformer models by using position-anchored glyph patch conditions and staged finetuning, improving text fidelity while maintaining image quality, and is evaluated with the InfoTextBench benchmark.

Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arranged text or rare characters. Existing approaches either improve native text rendering through stronger backbones and data-centric training without explicit glyph priors, or incorporate glyph priors through specialized designs that remain insufficiently accurate and robust under challenging scenarios. We introduce GlyphAnchor, a novel text-rendering enhancement method for both text-to-image and image-editing diffusion transformer models. GlyphAnchor enhances the backbone with lightweight glyph patch conditions whose positions are anchored to the target image through the model's native positional encoding. We train this capability with staged supervised finetuning and further refine it with text-aware post-training to improve robustness. We also introduce InfoTextBench, a benchmark for evaluating text-rich visual text rendering in both generation and editing settings. Experiments across multiple backbones and benchmarks, including long, complex, and densely arranged text and rare character scenarios, show that GlyphAnchor consistently improves text fidelity while preserving overall image quality.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.02349
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.02349 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.02349 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.