mlsanityData to 7 Oct 2026

Diffusion models for Handwriting Generation

arXiv 2011.06704 ↗First posted 13 Nov 2020cs.LG cs.CVcited by 25

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

Abstract (arXiv)

In this paper, we propose a diffusion probabilistic model for handwriting generation. Diffusion models are a class of generative models where samples start from Gaussian noise and are gradually denoised to produce output. Our method of handwriting generation does not require using any text-recognition based, writer-style based, or adversarial loss functions, nor does it require training of auxiliary networks. Our model is able to incorporate writer stylistic features directly from image data, eliminating the need for user interaction during sampling. Experiments reveal that our model is able to generate realistic , high quality images of handwritten text in a similar style to a given writer. Our implementation can be found at https://github.com/tcl9876/Diffusion-Handwriting-Generation

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 25 of its 32 references that are in the map. First posted on arXiv 13 Nov 2020.

Builds on

25 of 32 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2016Layer Normalizationcited by 5,579
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  10. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  11. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  12. 2013Generating Sequences With Recurrent Neural Networkscited by 549
13 more
  1. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  2. 2020Learning Gradient Fields for Shape Generationcited by 245
  3. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  4. 2020Adversarial score matching and improved sampling for image generationcited by 95
  5. 2020ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generationcited by 69
  6. 2020GANwriting: Content-Conditioned Generation of Styled Handwritten Word Imagescited by 68
  7. 2018Geometry Score: A Method For Comparing Generative Adversarial Networkscited by 56
  8. 2020Efficient Learning of Generative Models via Finite-Difference Score Matchingcited by 49
  9. 2018DeepWriting: Making Digital Ink Editable via Deep Generative Modelingcited by 39
  10. 2019Adversarial Generation of Handwritten Text Images Conditioned on Sequencescited by 37
  11. 2020Generating Handwriting via Decoupled Style Descriptorscited by 23
  12. 2020Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesiscited by 11
  13. 2020Spatio-Temporal Handwriting Imitationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 8; 2024: 9; 2025: 2; 2026: 3.

25 papers.

Sort:

By area:

  1. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  2. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  3. 2022A Morphology Focused Diffusion Probabilistic Model for Synthesis of Histopathology Imagescited by 74
  4. 2023Conditional Text Image Generation with Diffusion Modelscited by 57
  5. 2023FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learningcited by 48
  6. 2024Visual Text Generation in the Wildcited by 22
  7. 2024One-Shot Diffusion Mimicker for Handwritten Text Generationcited by 20
  8. 2024VATr++: Choose Your Words Wisely for Handwritten Text Generationcited by 18
  9. 2023ChiroDiff: Modelling chirographic data with Diffusion Modelscited by 14
  10. 2023Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognitioncited by 10
  11. 2023DiffSketching: Sketch Control Image Synthesis with Diffusion Modelscited by 10
  12. 2023Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Modelcited by 8
13 more
  1. 2024Freehand Sketch Generation from Mechanical Componentscited by 8
  2. 2024Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Modelscited by 5
  3. 2024HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolutioncited by 5
  4. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4
  5. 2025Autoregressive Styled Text Image Generation, but Make it Reliablecited by 3
  6. 2024StylusAI: Stylistic Adaptation for Robust German Handwritten Text Generationcited by 2
  7. 2024Latent Diffusion for Guided Document Table Generationcited by 2
  8. 2024Semi-Supervised Adaptation of Diffusion Models for Handwritten Text Generationcited by 2
  9. 2023Conditional Human Sketch Synthesis with Explicit Abstraction Controlcited by 1
  10. 2023Sampling and Ranking for Digital Ink Generation on a tight computational budgetcited by 0
  11. 2025Layout Stroke Imitation: A Layout Guided Handwriting Stroke Generation for Style Imitation with Diffusion Modelcited by 0
  12. 2026Telling Human and Machine Handwriting Apartcited by 0
  13. 2026HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Spacecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models
  2. 2024DiffusionPen: Towards Controlling the Style of Handwritten Text Generation
  3. 2026CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization
  4. 2025DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation
  5. 2025Dual Orthogonal Guidance for Robust Diffusion-based Handwritten Text Generation
  6. 2024Generative Modeling with Diffusion
  7. 2023DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion
  8. 2023Calliffusion: Chinese Calligraphy Generation and Style Transfer with Diffusion Modeling