# StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis

arXiv: https://arxiv.org/abs/2401.17093 · HTML: https://mlsanity.com/paper/2401.17093/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 37 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion](https://mlsanity.com/paper/2111.12417/) (2021)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [Emu: Generative Pretraining in Multimodality](https://mlsanity.com/paper/2307.05222/) (2023)
- [Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model](https://mlsanity.com/paper/2304.13731/) (2023)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [SVGDreamer: Text Guided SVG Generation with Diffusion Model](https://mlsanity.com/paper/2312.16476/) (2023)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [FIGR: Few-shot Image Generation with Reptile](https://mlsanity.com/paper/1901.02199/) (2019)
- [Robust Semantic Communications with Masked VQ-VAE Enabled Codebook](https://mlsanity.com/paper/2206.04011/) (2022)
- [Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers](https://mlsanity.com/paper/2310.05400/) (2023)
- [Stacked Quantizers for Compositional Vector Compression](https://mlsanity.com/paper/1411.2173/) (2014)
- [Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer](https://mlsanity.com/paper/2206.04452/) (2022)

## Built on by (most cited first, 26 of 26)

- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer](https://mlsanity.com/paper/2502.01105/) (2025)
- [Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models](https://mlsanity.com/paper/2411.16602/) (2024)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities](https://mlsanity.com/paper/2404.13710/) (2024)
- [SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation](https://mlsanity.com/paper/2506.03139/) (2025)
- [Visually Descriptive Language Model for Vector Graphics Reasoning](https://mlsanity.com/paper/2404.06479/) (2024)
- [Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback](https://mlsanity.com/paper/2604.20730/) (2026)
- [Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings](https://mlsanity.com/paper/2508.18733/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance](https://mlsanity.com/paper/2512.10894/) (2025)
- [VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation](https://mlsanity.com/paper/2605.01517/) (2026)
- [Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision](https://mlsanity.com/paper/2410.05991/) (2024)
- [SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation](https://mlsanity.com/paper/2412.10437/) (2024)
- [Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review](https://mlsanity.com/paper/2503.04983/) (2025)
- [OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens](https://mlsanity.com/paper/2603.02138/) (2026)
- [AutoSketch: VLM-assisted Style-Aware Vector Sketch Completion](https://mlsanity.com/paper/2502.06860/) (2025)
- [Style Customization of Text-to-Vector Generation with Image Diffusion Priors](https://mlsanity.com/paper/2505.10558/) (2025)
- [Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling](https://mlsanity.com/paper/2604.05072/) (2026)
- [mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval](https://mlsanity.com/paper/2604.17054/) (2026)
- [SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation](https://mlsanity.com/paper/2411.17832/) (2024)
- [Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with B'ezier Curves](https://mlsanity.com/paper/2511.00076/) (2025)
- [Draw This First](https://mlsanity.com/paper/2608.12064/) (2026)
- [CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation](https://mlsanity.com/paper/2608.30689/) (2026)
- [SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation](https://mlsanity.com/paper/2609.03806/) (2026)

## Abstract (arXiv)

To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes. This paper posits that an alternative representation of images, vector graphics, can effectively surmount this limitation by enabling a more natural and semantically coherent segmentation of the image information. Thus, we introduce StrokeNUWA, a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics, which is inherently visual semantics rich, naturally compatible with LLMs, and highly compressed. Equipped with stroke tokens, StrokeNUWA can significantly surpass traditional LLM-based and optimization-based methods across various metrics in the vector graphic generation task. Besides, StrokeNUWA achieves up to a 94x speedup in inference over the speed of prior methods with an exceptional SVG code compression ratio of 6.9%.