diff --git a/imgs/gradioicon.png b/imgs/gradioicon.png new file mode 100644 index 0000000..d6b62c8 Binary files /dev/null and b/imgs/gradioicon.png differ diff --git a/imgs/omniboxicon.png b/imgs/omniboxicon.png new file mode 100644 index 0000000..de05f63 Binary files /dev/null and b/imgs/omniboxicon.png differ diff --git a/imgs/omniparsericon.png b/imgs/omniparsericon.png new file mode 100644 index 0000000..877427a Binary files /dev/null and b/imgs/omniparsericon.png differ diff --git a/omnitool/readme.md b/omnitool/readme.md index c572fc0..a017a8c 100644 --- a/omnitool/readme.md +++ b/omnitool/readme.md @@ -1,6 +1,4 @@ -

- OmniParser+X Computer Use Demo screenshot -

+OmniTool Header # OmniTool @@ -10,9 +8,27 @@ Control a Windows 11 VM with OmniParser+X (OpenAI (4o/o1/o3-mini), DeepSeek (R1) There are three components: -1. **omnibox**: A Windows 11 VM running in a Docker container + + + + + + + + + + + + + + + + +
omniboxA Windows 11 VM running in a Docker container.
omniparserserverFastAPI server running OmniParser V2.
gradioUI to provide commands and watch reasoning + execution on OmniBox
+ + Notes: