Dom/OmniParser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add highlihgts to readme for OmniTool

Browse Source
This commit is contained in:
Thomas Dhome-Casanova
2025-02-05 11:04:59 -08:00
parent ba5c5162c6
commit 2327acbab2
2 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
imgs/header_bar_small.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 76 KiB

9
omnitool/readme.md
View File

@@ -26,10 +26,13 @@ There are three components:
</tr> </tr>
</table> </table>
Notes: ## Highlights:
1. **OmniParser V2** is 60% faster than V1 and now understands a wide variety of OS, app and inside app icons!
2. **OmniBox** uses 50% less disk space than other Windows VMs for agent testing, whilst providing the same computer use API
1. Though OmniParser can run on a CPU, we have separated this out if you want to run it fast on a GPU machine ## Notes:
2. The Windows 11 VM docker is dependent on KVM so can only run quickly on Windows and Linux. This can run on a CPU machine (doesn't need GPU). 1. Though **OmniParser V2** can run on a CPU, we have separated this out if you want to run it fast on a GPU machine
2. The **OmniBox** Windows 11 VM docker is dependent on KVM so can only run quickly on Windows and Linux. This can run on a CPU machine (doesn't need GPU).
3. The Gradio UI can also run on a CPU machine. We suggest running **omnibox** and **gradio** on the same CPU machine and **omniparserserver** on a GPU server. 3. The Gradio UI can also run on a CPU machine. We suggest running **omnibox** and **gradio** on the same CPU machine and **omniparserserver** on a GPU server.
## Setup ## Setup