omnitool icon indicating copy to clipboard operation
omnitool copied to clipboard

Published 20 hours ago • verified publisher icon omnitool-ai

Please add support for Omniparser V2

Open Emasoft opened this issue 9 months ago • 1 comments

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 omnitool. It would even be able to create the workflows automatically!

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

Emasoft avatar Feb 15 '25 22:02 Emasoft

Seems to have been supported?

ShawshankLin avatar Feb 22 '25 11:02 ShawshankLin