OmniParser icon indicating copy to clipboard operation
OmniParser copied to clipboard

A simple screen parsing tool towards pure vision based GUI agent

Results 136 OmniParser issues
Sort by recently updated
recently updated
newest added

The following three lines can be removed. https://github.com/microsoft/OmniParser/blob/a14c4010ebd91aae83a240badadc9e5721aaf0c8/utils.py#L11 https://github.com/microsoft/OmniParser/blob/a14c4010ebd91aae83a240badadc9e5721aaf0c8/requirements.txt#L5 https://github.com/microsoft/OmniParser/blob/a14c4010ebd91aae83a240badadc9e5721aaf0c8/requirements.txt#L8 `azure-identity` and `openai` are listed in `requirements.txt`, but they are not actually used in the code. `AzureOpenAI` is imported from...

Can you provide a way to inference it with onnx? This way we'll be able to use the GPU and much less dependencies and also it will be easier to...

I wonder what minimal resources are needed to run this pipeline. What are also the recommended resources? This information could be latter added to the README.md

Thanks for putting this up! In full view, the icons in the top right weren't recognize: ![Image](https://github.com/user-attachments/assets/56ff1e1c-5735-4b8a-95dd-f9510f36367d) I put a close up version, it works for the search icon but...

why not useing GPU

I run the program in pycharm, one error listed below occurs, how to solve it? ValueError: Unrecognized model in weights/icon_caption_florence. Should have a `model_type` key in its config.json, or contain...

When i try to open ubuntu settings,the screen freezes and the system is unresponsive.

Hi OmniParser Team, Thank you for making this excellent work available! Can you please clarify whether you have any plans to release fine-tuning code for OmniParser? Thanks, Richard

https://youtu.be/IJsDfoZg2QM