OmniParser
OmniParser copied to clipboard
microsoft
A simple screen parsing tool towards pure vision based GUI agent
Running into issues trying to Setup Omnibox. When I run the `.\manage_vm.ps1 create` command, I get this error after some time ``` BdsDxe: failed to load Boot0002 "UEFI QEMU QEMU...
The link in "omnitool/omnibox/vm/win11setup/setupscripts/tools_config.json" used for downloading GIMP during Windows 11 setup is really slow. And it would cause the setup stuck there for around 1-2 hour. Please check and...
When installing Win11 Enterprise Evaluation according to the README file in omnibox, it would look for "win11x64-enterprise.xml", instead of "win11x64-enterprise-eval.xml". This would cause Windows 11 unable to boot. Temporary fix...
Do you have any plans to integrate LLaVa for image captioning? Feel free to assign me for this!
> [2025/2] We release OmniParser V2 [checkpoints](https://huggingface.co/microsoft/OmniParser-v2.0). [Watch Video](https://1drv.ms/v/c/650b027c18d5a573/EWXbVESKWo9Buu6OYCwg06wBeoM97C6EOTG6RjvWLEN1Qg?e=alnHGC) [2025/2] We introduce OmniTool: Control a Windows 11 VM with OmniParser + your vision model of choice. OmniTool supports out of...
Both "Watch Video" Links Under the News Header don't work. Onedrive errors with "The sharing token is invalid"
In response to Issue #153 Updated the mirror site for faster downloading GIMP via a new mirror website.
 When I installed OmniTool on a Windows 10 OS, a kvm problem occurred when launching a Windows 11 container. I found that the problem occurred after the build was...
