update demo

app.py

@@ -279,9 +279,10 @@ with gr.Blocks(css=css) as demo:
 
             with gr.Column():
                 result_video = gr.Video(label="Generated Audio", interactive=False)
-                gr.Markdown('**Tips**: <br> \
-                            1. With strong temporal visual cues in input video, you can scale up the **Temporal Align Scale**. <br>\
-                            2. **Visual content scale** is the level of semantic alignment with visual content. \
+                gr.Markdown(
+                    '**Tips**: <br> \
+                    1. With strong temporal visual cues in input video, you can scale up the **Temporal Align Scale**. <br>\
+                    2. **Visual content scale** is the level of semantic alignment with visual content. \
                 ')
 
         generate_button.click(