jw2yang commited on
Commit
9f74ec1
·
1 Parent(s): deea38c
Files changed (1) hide show
  1. app.py +4 -3
app.py CHANGED
@@ -57,9 +57,10 @@ MARKDOWN = """
57
 
58
  This demo is powered by [Gradio](https://gradio.app/) and uses [OmniParserv2](https://github.com/microsoft/OmniParser) to generate [Set-of-Mark prompts](https://github.com/microsoft/SoM).
59
 
60
- The model can do two things simutaneously:
61
- 1. **UI Grounding and Navigation**: Ask the model to generate a click action.
62
- 2. **Visual Question Answering**: Ask the model with any verbal questions by appending a prefix "Q:" to the question.
 
63
  </div>
64
  """
65
 
 
57
 
58
  This demo is powered by [Gradio](https://gradio.app/) and uses [OmniParserv2](https://github.com/microsoft/OmniParser) to generate [Set-of-Mark prompts](https://github.com/microsoft/SoM).
59
 
60
+ The demo supports three modes:
61
+ 1. Empty text inut: it downgrades to an OmniParser demo.
62
+ 2. Text input starting with "Q:": it leads to a visual question answering demo.
63
+ 3. Text input for UI navigation: it leads to a UI navigation demo.
64
  </div>
65
  """
66