# FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection

arXiv: https://arxiv.org/abs/2601.00535 · HTML: https://mlsanity.com/paper/2601.00535/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 2 Jan 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 23 of 23)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [What the DAAM: Interpreting Stable Diffusion Using Cross Attention](https://mlsanity.com/paper/2210.04885/) (2022)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [Linear Representations of Sentiment in Large Language Models](https://mlsanity.com/paper/2310.15154/) (2023)
- [See What You Are Told: Visual Attention Sink in Large Multimodal Models](https://mlsanity.com/paper/2503.03321/) (2025)
- [GlyphControl: Glyph Conditional Control for Visual Text Generation](https://mlsanity.com/paper/2305.18259/) (2023)
- [X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again](https://mlsanity.com/paper/2507.22058/) (2025)
- [FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark](https://mlsanity.com/paper/2509.09680/) (2025)
- [GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation](https://mlsanity.com/paper/2303.17870/) (2023)
- [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021)
- [Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation](https://mlsanity.com/paper/2503.23461/) (2025)
- [Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings](https://mlsanity.com/paper/2502.00919/) (2025)
- [LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis](https://mlsanity.com/paper/2503.21749/) (2025)
- [LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers](https://mlsanity.com/paper/2502.15007/) (2025)
- [Punctuation and Predicates in Language Models](https://mlsanity.com/paper/2508.14067/) (2025)

## Built on by (most cited first, 5 of 5)

- [Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation](https://mlsanity.com/paper/2604.10098/) (2026)
- [GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows](https://mlsanity.com/paper/2603.12155/) (2026)
- [GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors](https://mlsanity.com/paper/2609.02349/) (2026)
- [Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation](https://mlsanity.com/paper/2603.10210/) (2026)
- [Training-Free Occluded Text Rendering via Glyph Priors and Attention-Guided Semantic Blending](https://mlsanity.com/paper/2605.16810/) (2026)

## Abstract (arXiv)

Large-scale text-to-image (T2I) diffusion models excel at open-domain synthesis but still struggle with precise text rendering, especially for multi-line layouts, dense typography, and long-tailed scripts such as Chinese. Prior solutions typically require costly retraining or rigid external layout constraints, which can degrade aesthetics and limit flexibility. We propose FreeText, a training-free, plug-and-play framework that improves text rendering by exploiting intrinsic mechanisms of Diffusion Transformer (DiT) models. FreeText decomposes the problem into where to write and what to write. For where to write, we localize writing regions by reading token-wise spatial attribution from endogenous image-to-text attention, using sink-like tokens as stable spatial anchors and topology-aware refinement to produce high-confidence masks. For what to write, we introduce Spectral-Modulated Glyph Injection (SGMI), which injects a noise-aligned glyph prior with frequency-domain band-pass modulation to strengthen glyph structure and suppress semantic leakage (rendering the concept instead of the word). Extensive experiments on Qwen-Image, FLUX.1-dev, and SD3 variants across longText-Benchmark, CVTG, and our CLT-Bench show consistent gains in text readability while largely preserving semantic alignment and aesthetic quality, with modest inference overhead.