All tasks / Models
OmniSVG1.1_8B
Open vision-language model fine-tuned from Qwen2.5-VL that generates SVG icons and illustrations from text or images.
- OmniSVG (Fudan University and StepFun)
- Open weights
- Released 2 Dec 2025
Where it ranks
- –Vector graphics & logosModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- OmniSVG (Fudan University and StepFun)
- Family
- OmniSVG
- Released
- 2 Dec 2025
- Weights
- Open: download and run it yourself
- License
- apache-2.0
- GPU memory to run locally
- ~26 GB (GPU memory listed in the README; the 4B variant (OmniSVG1.1_4B) needs 17 GB)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from github.com, 19 Oct 2026.
Benchmark results
No public benchmark results recorded yet.
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.
Earlier versions
- OmniSVG-3B · 22 Jul 2025