# UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

arXiv: https://arxiv.org/abs/2507.00992 · HTML: https://mlsanity.com/paper/2507.00992/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 30 of 35)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [Composer: Creative and Controllable Image Synthesis with Composable Conditions](https://mlsanity.com/paper/2302.09778/) (2023)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation](https://mlsanity.com/paper/2406.01900/) (2024)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering](https://mlsanity.com/paper/2311.16465/) (2023)
- [GlyphControl: Glyph Conditional Control for Visual Text Generation](https://mlsanity.com/paper/2305.18259/) (2023)
- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [Character-Aware Models Improve Visual Text Rendering](https://mlsanity.com/paper/2212.10562/) (2022)
- [Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering](https://mlsanity.com/paper/2403.09622/) (2024)
- [Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning](https://mlsanity.com/paper/2506.05207/) (2025)
- [Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors](https://mlsanity.com/paper/2503.08099/) (2025)
- [Follow-Your-Creation: Empowering 4D Creation through Video Inpainting](https://mlsanity.com/paper/2506.04590/) (2025)
- [Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow](https://mlsanity.com/paper/2410.07303/) (2024)
- [UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models](https://mlsanity.com/paper/2312.04884/) (2023)
- [LayoutPrompter: Awaken the Design Ability of Large Language Models](https://mlsanity.com/paper/2311.06495/) (2023)
- [Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering](https://mlsanity.com/paper/2406.10208/) (2024)
- [ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding](https://mlsanity.com/paper/2409.03277/) (2024)
- [Improving Diffusion Models for Scene Text Editing with Dual Encoders](https://mlsanity.com/paper/2304.05568/) (2023)
- [Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model](https://mlsanity.com/paper/2312.12232/) (2023)
- [Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent](https://mlsanity.com/paper/2501.01230/) (2025)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)
- [GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models](https://mlsanity.com/paper/2407.02252/) (2024)

## Built on by (most cited first, 8 of 8)

- [VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction](https://mlsanity.com/paper/2511.23386/) (2025)
- [Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling](https://mlsanity.com/paper/2601.15664/) (2026)
- [GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering](https://mlsanity.com/paper/2603.15616/) (2026)
- [Text-guided Visual Prompt DINO for Generic Segmentation](https://mlsanity.com/paper/2508.06146/) (2025)
- [UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing](https://mlsanity.com/paper/2601.08321/) (2026)
- [TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards](https://mlsanity.com/paper/2605.19320/) (2026)
- [PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow](https://mlsanity.com/paper/2603.25738/) (2026)
- [Evaluating Reasoning Fidelity in Visual Text Generation](https://mlsanity.com/paper/2606.04479/) (2026)

## Abstract (arXiv)

Text-to-image generation has greatly advanced content creation, yet accurately rendering visual text remains a key challenge due to blurred glyphs, semantic drift, and limited style control. Existing methods often rely on pre-rendered glyph images as conditions, but these struggle to retain original font styles and color cues, necessitating complex multi-branch designs that increase model overhead and reduce flexibility. To address these issues, we propose a segmentation-guided framework that uses pixel-level visual text masks -- rich in glyph shape, color, and spatial detail -- as unified conditional inputs. Our method introduces two core components: (1) a fine-tuned bilingual segmentation model for precise text mask extraction, and (2) a streamlined diffusion model augmented with adaptive glyph conditioning and a region-specific loss to preserve textual fidelity in both content and style. Our approach achieves state-of-the-art performance on the AnyText benchmark, significantly surpassing prior methods in both Chinese and English settings. To enable more rigorous evaluation, we also introduce two new benchmarks: GlyphMM-benchmark for testing layout and glyph consistency in complex typesetting, and MiniText-benchmark for assessing generation quality in small-scale text regions. Experimental results show that our model outperforms existing methods by a large margin in both scenarios, particularly excelling at small text rendering and complex layout preservation, validating its strong generalization and deployment readiness.