https://github.com/OmniSVG/OmniSVG
OmniSVG: A Unified Scalable Vector Graphics Generation Model
https://github.com/OmniSVG/OmniSVG
Last synced: about 1 year ago
JSON representation
OmniSVG: A Unified Scalable Vector Graphics Generation Model
- Host: GitHub
- URL: https://github.com/OmniSVG/OmniSVG
- Owner: OmniSVG
- License: mit
- Created: 2025-04-07T11:14:32.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-04-07T12:26:52.000Z (about 1 year ago)
- Last Synced: 2025-04-07T13:28:44.795Z (about 1 year ago)
- Size: 4.52 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - OmniSVG/OmniSVG - 语言模型（VLM）生成复杂的SVG图像。该项目能够生成从简单图标到复杂动漫人物等各种细节丰富的SVG。OmniSVG的核心在于其利用VLM理解图像内容并将其转化为矢量图形的能力。它是一个多模态系统，意味着它可以处理多种输入类型（例如文本和图像）来生成SVG。OmniSVG旨在简化SVG创作流程，并为设计师和开发者提供强大的工具。该项目代表了AI在矢量图形生成领域的前沿探索。 (多模态大模型 / 资源传输下载)
README
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](https://huggingface.co/OmniSVG).
- [2025/04/09] Upload paper and init project.
## To Do List
- [ ] Code and Pretrained Models Release
- [ ] MMSVG-Character Release
- [x] MMSVG-Icon and MMSVG-Illustration Dataset Release
- [x] Project Page & Technical Report
## Citation
```bibtex
@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](https://icon-shop.github.io/): 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](https://arxiv.org/abs/2412.11102): treats SVG coordinates as number strings and predicts decimal part for higher spatial accuracy.
[StarVector](https://starvector.github.io/): equips LLM with an image encoder for Image-to-SVG generation.
## Star History
[](https://www.star-history.com/#OmniSVG/OmniSVG&Date)