Research map / Image generation / Text-to-image diffusion
Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering
Zeyu Liu, Weicong Liang, Zhanhao Liang, Chong Luo, Ji Li, Gao Huang, Yuhui Yuan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add glyph-alignment pretraining (Glyph-ByT5-S) over plain ByT5-S (ablation) | SDXL · VisualParagraphy (<=20 chars) | word precision (%): 60.52 -> 92.58 | Improved |
| use character-aware ByT5-S instead of T5-L (ablation) | SDXL · VisualParagraphy (>=100 chars) | word precision (%): 26.09 -> 42.05 | Improved |
| scale glyph-text pairs from 500K to 1M (ablation) | Glyph-ByT5-S · VisualParagraphy (>=100 chars) | word precision (%): 83.17 -> 89.17 | Improved |
| use DINOv2 instead of CLIP as frozen visual encoder (ablation) | Glyph-ByT5 pretraining · VisualParagraphy ablation (>=100 chars) | word precision (%): 66.34 -> 73.29 | Improved |
| use box-level contrastive loss instead of image-level (ablation) | Glyph-ByT5 pretraining · VisualParagraphy ablation (>=100 chars) | word precision (%): 69.42 -> 73.29 | Improved |
| add image-level loss on top of box-level loss (ablation) | Glyph-ByT5 pretraining · VisualParagraphy ablation (>=100 chars) | word precision (%): 73.29 -> 70.54 | Hurt |
| add glyph augmentation (1:16 ratio) (ablation) | Glyph-ByT5 pretraining · VisualParagraphy ablation (>=100 chars) | word precision (%): 65.40 -> 73.29 | Improved |
| raise glyph augmentation ratio from 1:16 to 1:32 (ablation) | Glyph-ByT5 pretraining · VisualParagraphy ablation (>=100 chars) | word precision (%): 73.29 -> 72.16 | No clear effect |
| add ByT5-to-SDXL mapper (ablation) | Glyph-SDXL · VisualParagraphy ablation (>=100 chars) | word precision (%): 65.02 -> 73.29 | Improved |
| scale text encoder from Glyph-ByT5-S to B and L (ablation) | Glyph-SDXL · VisualParagraphy ablation (>=100 chars) | word precision (%): 73.29 -> 73.72 | No clear effect |
| use region-wise cross-attention instead of concatenating text embeddings (ablation) | Glyph-SDXL · VisualParagraphy ablation (>=100 chars) | word precision (%): 3.91 -> 73.29 | Improved |
| use Glyph-ByT5 instead of ControlNet-style glyph conditioning (ablation) | SDXL · VisualParagraphy (>=100 chars) | word precision (%): 32.75 -> 73.29 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- TextDiffuser-2 — TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering (ECCV 2024) · better on 2 of 2 shared results
- TextDiffuser — TextDiffuser: Diffusion Models as Text Painters (NeurIPS 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors (NeurIPS 2026 · similarity 0.92)
- GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing (CVPR 2025 · similarity 0.91)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.89)
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025 · similarity 0.89)
- GlyphSR: A Simple Glyph-Aware Framework for Scene Text Image Super-Resolution (AAAI 2025 · similarity 0.89)
- DreamText: High Fidelity Scene Text Synthesis (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
