mlsanityData to 14 Oct 2026

EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering

arXiv 2505.24417 ↗First posted 30 May 2025cs.CVcited by 26

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an unexplored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.

Key facts. Cited by 26 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 52 of its 67 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

52 of 67 references.

Closest ancestors · 20

Same direction, newest first

  1. 2025ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations16 Feb
  2. 2025MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation3 Feb
  3. 2025LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer3 Feb
  4. 2024JoyType: A Robust Design for Multilingual Visual Text Creation26 Sep
  5. 2024GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models2 Jul
  6. 2024ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback11 Apr
  7. 2024Fast Personalized Text-to-Image Syntheses With Attention Injection17 Mar
  8. 2024Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model12 Mar
  9. 2024InstantID: Zero-shot Identity-Preserving Generation in Seconds15 Jan
  10. 2023Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model19 Dec
  11. 2023VecFusion: Vector Font Generation with Diffusion16 Dec
  12. 2023UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models8 Dec
8 more
  1. 2023TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering28 Nov
  2. 2023AnyText: Multilingual Visual Text Generation And Editing6 Nov
  3. 2023GlyphControl: Glyph Conditional Control for Visual Text Generation29 May
  4. 2023TextDiffuser: Diffusion Models as Text Painters18 May
  5. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models16 Feb
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  7. 2022Diff-Font: Diffusion Model for Robust One-Shot Font Generation12 Dec
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov

Other references · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  9. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  10. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 455
  11. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  12. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 174
20 more
  1. 2025Seedream 3.0 Technical Reportcited by 154
  2. 2020PP-OCR: A Practical Ultra Lightweight OCR Systemcited by 151
  3. 2023SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generationcited by 143
  4. 2025EasyControl: Adding Efficient and Flexible Control for Diffusion Transformercited by 119
  5. 2017Multi-Content GAN for Few-Shot Font Style Transfercited by 100
  6. 2019Editing Text in the Wildcited by 82
  7. 2024Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Renderingcited by 81
  8. 2025Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Taskscited by 63
  9. 2024AnyText2: Visual Text Generation and Editing With Customizable Attributescited by 53
  10. 2024Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Renderingcited by 48
  11. 2020Few-shot Compositional Font Generation with Dual Memorycited by 44
  12. 2024FonTS: Text Rendering with Typography and Style Controlscited by 40
  13. 2024ProcessPainter: Learn Painting Process from Sequence Datacited by 38
  14. 2024Stable-Hair: Real-World Hair Transfer via Diffusion Modelcited by 35
  15. 2022Few-Shot Font Generation by Learning Fine-Grained Local Stylescited by 34
  16. 2022CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphicscited by 34
  17. 2023GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generationcited by 34
  18. 2024StableGarment: Garment-Centric Generation via Stable Diffusioncited by 27
  19. 2025PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Datacited by 24
  20. 2025RepText: Rendering Visual Text via Replicatingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 17.

26 papers.

Sort:

By area:

  1. 2025RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformerscited by 26
  2. 2025Mitty: Diffusion-based Human-to-Robot Video Generationcited by 14
  3. 2025WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generationcited by 9
  4. 2026InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generationcited by 6
  5. 2026GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Renderingcited by 6
  6. 2025Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceiverscited by 5
  7. 2025OmniRefiner: Reinforcement-Guided Local Diffusion Refinementcited by 5
  8. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  9. 2025NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-based Image Editingcited by 4
  10. 2026GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflowscited by 4
  11. 2025DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategycited by 3
  12. 2025Markovian Scale Prediction: A New Era of Visual Autoregressive Generationcited by 2
14 more
  1. 2026SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokenscited by 2
  2. 2026TextWand: A Unified Framework for Scene Text Editingcited by 2
  3. 2026InnoText: A Unified Model for Visual Text Generation and Editingcited by 2
  4. 2026GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priorscited by 2
  5. 2025TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidancecited by 1
  6. 2026On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generationcited by 1
  7. 2026PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Postercited by 1
  8. 2026GenPuzzle: Benchmarking Visual Reasoning in Image Generation Modelscited by 1
  9. 2026Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image Generationcited by 0
  10. 2026ArtChart: Faithful Artistic Chart Generation with Integrated Text Renderingcited by 0
  11. 2026I Am AdMan: A Pipeline for Automatic Generation of Personalized Advertising Imagerycited by 0
  12. 2026VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphicscited by 0
  13. 2026Beyond Legibility: Benchmarking Visual Text Rendering and In-Place Editing in Unified Video Generationcited by 0
  14. 2026CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing
  2. 2026FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection
  3. 2025TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
  4. 2025TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment
  5. 2024CustomText: Customized Textual Image Generation using Diffusion Models
  6. 2023DiffUTE: Universal Text Editing Diffusion Model
  7. 2024MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost
  8. 2024ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models