OmniSVG
BTR ACTIVE STEADY
[NeurIPS 2025] 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.
stars 3k
last activity 4mo ago
open issues 36
language Python
license Apache-2.0
latest release n/a
momentum · per month since covered + 91/mo
(+8%/mo) · + 1k total since PR#6
metrics as of today
star history
Exact curve on star-history.com ↗- PR#6 1k★ 2025-04-16
- now 3k★ + 1k since first covered
curve is sampled from GitHub's star history; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
covered in
-
A multimodal generator that uses VLMs to create detailed SVGs, from simple icons to complex anime characters
// comments
COMING SOONSign in with GitHub to weigh in on OmniSVG. We're wiring this up; check back soon.