lms icon indicating copy to clipboard operation
lms copied to clipboard

Please add support for Omniparser V2

Open Emasoft opened this issue 9 months ago • 1 comments
trafficstars

Microsoft presented Omniparser V2 and it is showing the best performances in GUI parsing. You can read about the details here. It is not a multimodal but a visual parsing model specialized in detecting the GUI elements and can be combined with any LLM.

It would be great to add support for Omniparser V2 in MLStudio. It would be even better if it were possible to serve both Omniparser and some distilled Deepseek-R1 models at the same time, to serve Computer-Use clients.

https://github.com/microsoft/OmniParser/

Thanks!

Emasoft avatar Feb 15 '25 19:02 Emasoft