OmniSVG

B tier on AI Vector GeneratorsScore 7.1 · #2 of 26

Android app: Not listed
Free plan: Yes
Runs on: Linux, Mac, self-hosted, Web

omnisvg.net

Summary

OmniSVG creates scalable SVG graphics from natural-language descriptions and converts PNG, JPG, BMP and WebP images into editable SVG. Image uploads are limited to 5 MB. Generated graphics can be previewed, downloaded or copied as code for editing in an SVG-compatible tool. Its free demo requires no account, shows the remaining daily generations in the browser and allows five generations per day. The research project also supports character-reference SVG generation. Its model combines a pretrained Qwen-VL vision-language model with an SVG tokenizer, and the project introduces MMSVG-2M, a dataset containing two million annotated SVG assets. The code is licensed under Apache License 2.0. The repository offers local Gradio deployment instructions using Python 3.10, Cairo and CUDA 12.1-tested dependencies, and lists model downloads from 7.69 GB to 17.2 GB. Reported inference memory use is 17 GB for OmniSVG1.1_4B and 26 GB for OmniSVG1.1_8B. The project also lists a community-contributed ComfyUI plugin.

Who it is for

OmniSVG may suit web developers, UI/UX designers, content creators, and people making print or merchandise graphics. Its local deployment option is relevant to users considering the listed model downloads and dependencies.

What is good

Creates SVG graphics from text descriptions.
Converts four listed image formats to editable SVG.
Free demo requires no account.
Generated SVGs can be downloaded or copied as code.
Code is licensed under Apache License 2.0.

What to know first

Five free generations are allowed per day.
Image uploads are limited to 5 MB.
Listed model downloads range up to 17.2 GB.
Local setup lists Python, Cairo and CUDA dependencies.

Verdict

OmniSVG offers both text-to-vector generation and image conversion, with editable SVG output. The daily generation and upload limits matter for the free demo, while local use involves substantial listed model files and dependencies.

OmniSVG plans and pricing

All plans

Free Free Free demo; no account required 5 free generations per day · image uploads up to 5 MB omnisvg.net · 30 Sept 2026

Compared on AI vector generators

Free plan: Yesomnisvg.net
Editable vector output: Yesomnisvg.net
SVG export: Yesomnisvg.net
Text-to-vector generation: Yesomnisvg.net
Image-to-vector conversion: Yesomnisvg.net
Export formats: SVGomnisvg.net

Facts

Text generation: OmniSVG converts natural-language descriptions into clean, scalable SVG graphics.omnisvg.net · 30 Sept 2026
Image conversion: The image converter accepts PNG, JPG, BMP, and WebP files up to 5 MB and outputs editable SVG.omnisvg.net · 30 Sept 2026
Editing and export: Generated SVGs can be previewed, downloaded, or copied as code for editing in an SVG-compatible tool.omnisvg.net · 30 Sept 2026
No account: The free demo does not require an account and displays the remaining daily generations in the browser.omnisvg.net · 30 Sept 2026
Use cases: The site lists web developers, UI/UX designers, content creators, and print or merchandise users as target audiences.omnisvg.net · 30 Sept 2026
Generation modalities: The research project supports Text-to-SVG, Image-to-SVG, and Character-Reference SVG generation.omnisvg.github.io · 30 Sept 2026
Model architecture: OmniSVG uses a pretrained Qwen-VL vision-language model together with an SVG tokenizer.omnisvg.github.io · 30 Sept 2026
Dataset: The project introduces MMSVG-2M, a multimodal dataset containing two million richly annotated SVG assets.omnisvg.github.io · 30 Sept 2026
Local deployment: The repository provides local Gradio deployment and installation instructions using Python 3.10, Cairo, and CUDA 12.1-tested dependencies.github.com · 30 Sept 2026
Model downloads: The repository lists OmniSVG1.1_8B at 17.2 GB, OmniSVG1.1_4B at 7.69 GB, and OmniSVG-3B at 8.49 GB.github.com · 30 Sept 2026
License: The OmniSVG code is licensed under Apache License 2.0.github.com · 30 Sept 2026
Online demo: The repository links to an online Hugging Face Spaces demo.github.com · 30 Sept 2026
Performance limit: The repository reports 26 GB GPU memory usage for OmniSVG1.1_8B inference and 17 GB for OmniSVG1.1_4B.github.com · 30 Sept 2026
Project affiliations: The project lists Fudan University and StepFun as the authors’ affiliations.omnisvg.github.io · 30 Sept 2026
Community integration: The repository lists a community-contributed ComfyUI OmniSVG plugin.github.com · 30 Sept 2026