Official repo for OmniSVG

OmniSVG: A Unified Scalable Vector Graphics Generation Model

              

🏃 Intro OmniSVG

OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.

🚩 News

• [2025/04/09] Release MMSVG-Icon and MMSVG-Illustration 🤗Dataset.
• [2025/04/09] Upload paper and init project.

To Do List

• Code and Pretrained Models Release
• MMSVG-Character Release
• MMSVG-Icon and MMSVG-Illustration Dataset Release
• Project Page & Technical Report

Citation

@article{yang2025omnisvg,
  title={OmniSVG: A Unified Scalable Vector Graphics Generation Model}, 
  author={Yiying Yang and Wei Cheng and Sijin Chen and Xianfang Zeng and Jiaxu Zhang and Liao Wang and Gang Yu and Xinjun Ma and Yu-Gang Jiang},
  journal={arXiv preprint arxiv:2504.06263},
  year={2025}
}

Acknowledgments

We thank the following excellent open-source works:

IconShop: is the first advanced work that leverages LLMs to generate monochrome, icon-level SVGs. We referred to its parametric implementation.

Here is the list of highly related concurrent works:

LLM4SVG: treats SVG corodinates as number strings and predicts decimal part for higher spatial accuracy.

StarVector: equips LLM with a image encoder for Image-to-SVG generation.