Update app.py

app.py

@@ -217,7 +217,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 with gr.Blocks(css=css) as demo:
     gr.HTML(
-        '<h1 style="height: 136px; display: flex; align-items: center; justify-content: space-around;"><span style="height: 100%; width:136px;"><img src="file/foleycrafter.png" alt="logo" style="height: 100%; width:auto; object-fit: contain; margin: 0px 0px; padding: 0px 0px;"></span><strong style="font-size: 40px;">FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds</strong></h1>'
+        '<h1 style="height: 136px; display: flex; align-items: center; justify-content: space-around;"><span style="height: 100%; width:136px;"><img src="file/foleycrafter.png" alt="logo" style="height: 100%; width:auto; object-fit: contain; margin: 0px 0px; padding: 0px 0px;"></span><strong style="font-size: 36px;">FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds</strong></h1>'
     )
     gr.HTML(
     '<p id="authors" style="text-align:center; font-size:24px;"> \
@@ -279,11 +279,17 @@ 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. \
-                ')
+                with gr.Row():
+                    gr.Markdown(
+                        "<div style='word-spacing: 6px;'><font size='5'><b>Tips</b>: <br> \
+                        1. With strong temporal visual cues in input video, you can scale up the <b>Temporal Align Scale</b>. <br>\
+                        2. <b>Visual content scale</b> is the level of semantic alignment with visual content.</font></div> \
+                    ")
+                # gr.HTML(
+                #     '<p style="font-size: 16px;">**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.</p> \
+                # ')
 
         generate_button.click(
             fn=controller.foley,