mlsanityData to 14 Oct 2026

SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation

arXiv 2412.10437 ↗First posted 11 Dec 2024cs.CV cs.GR cs.LGcited by 3

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

Abstract (arXiv)

Generating high-quality Scalable Vector Graphics (SVGs) from text remains a significant challenge. Existing LLM-based models that generate SVG code as a flat token sequence struggle with poor structural understanding and error accumulation, while optimization-based methods are slow and yield uneditable outputs. To address these limitations, we introduce SVGFusion, a unified framework that adapts the VAE-diffusion architecture to bridge the dual code-visual nature of SVGs. Our model features two core components: a Vector-Pixel Fusion Variational Autoencoder (VP-VAE) that learns a perceptually rich latent space by jointly encoding SVG code and its rendered image, and a Vector Space Diffusion Transformer (VS-DiT) that achieves globally coherent compositions through iterative refinement. Furthermore, this architecture is enhanced by a Rendering Sequence Modeling strategy, which ensures accurate object layering and occlusion. Evaluated on our novel SVGX-Dataset comprising 240k human-designed SVGs, SVGFusion establishes a new state-of-the-art, generating high-quality, editable SVGs that are strictly semantically aligned with the input text.

Key facts. Cited by 3 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 48 of its 74 references that are in the map. First posted on arXiv 11 Dec 2024.

Builds on

48 of 74 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Model27 Dec
  2. 2023DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models26 Jun
  3. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models21 Nov
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  10. 2022Scalable Diffusion Models with Transformerscited by 6,054
  11. 2022Classifier-Free Diffusion Guidancecited by 5,847
  12. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
30 more
  1. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  5. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  6. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  7. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  9. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  10. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  11. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  12. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 477
  13. 2017A Neural Representation of Sketch Drawingscited by 313
  14. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 287
  15. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 187
  16. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 159
  17. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 116
  18. 2023StarVector: Generating Scalable Vector Graphics Code from Images and Textcited by 102
  19. 2019A Learned Representation for Scalable Vector Graphicscited by 91
  20. 2022Towards Layer-wise Image Vectorizationcited by 79
  21. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 75
  22. 2023Word-As-Image for Semantic Typographycited by 63
  23. 2019FIGR: Few-shot Image Generation with Reptilecited by 56
  24. 2021Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Conceptscited by 40
  25. 2022CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphicscited by 34
  26. 2024Text-to-Vector Generation with Neural Path Representationcited by 33
  27. 2023DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Qualitycited by 27
  28. 2024StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesiscited by 26
  29. 2024SuperSVG: Superpixel-based Scalable Vector Graphics Synthesiscited by 19
  30. 2024NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generationcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learningcited by 8
  2. 2026Beyond NL2Code: A Structured Survey of Multimodal Code Intelligencecited by 6
  3. 2026Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
  2. 2025SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
  3. 2025SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation
  4. 2024CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion
  5. 2026VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
  6. 2025SVGen: Interpretable Vector Graphics Generation with Large Language Models
  7. 2025Latent Diffusion Model without Variational Autoencoder
  8. 2026Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback