no examples

app.py

@@ -58,14 +58,17 @@ with gr.Blocks() as demo:
     with gr.Column():            
         with gr.Tab("Upload image"):
             gr.Markdown(""" 
-                        [OWL-ViT](https://huggingface.co/docs/transformers/model_doc/owlvit) is a vision transformer architecture that can be used for image inputs with text queries. This is achieved by adding a text embedding layer to the model, which allows it to process both image and text inputs.
+                         OWL-ViT(https://huggingface.co/docs/transformers/model_doc/owlvit) is a vision transformer architecture that can be used for image inputs with text queries. This is achieved by adding a text embedding layer to the model, which allows it to process both image and text inputs.
                          \n  You can use to query images with text descriptions of any object. To use it, simply upload an image or capture one with the webcam and enter comma separated text descriptions of objects you want to query the image for. 
-                         \n You can also use the score threshold slider to set a threshold to filter out low probability predictions.
                         """)
             with gr.Row():
                 with gr.Column():
+
                     inputs_file=[gr.Image(source="upload"), gr.Textbox(),  gr.Slider(0, 1, value=0.1)]
                     submit_btn = gr.Button("Submit")
+                    gr.Markdown("""Insert an image above and add text descriptions of what you are looking for. 
+                                \n You can also use the score threshold slider to set a threshold to filter out low probability predictions.
+                                """)
 
                 im_output = gr.Image()