Update app.py

app.py

@@ -315,6 +315,15 @@ example_list = load_examples(examples_csv_path)
 # Create Gradio interface
 with gr.Blocks(theme="Respair/Shiki@9.1.0", css=css) as demo:
     gr.Markdown('<h1 style="text-align: center; width: 100%; display: block;">🌸 Takane</h1>')
+    gr.Markdown('''
+        <div style="text-align: center; background-color: #fff3cd; border: 1px solid #ffc107; 
+                    border-radius: 8px; padding: 12px; margin: 10px auto; max-width: 800px;">
+            <p style="color: #856404; margin: 0; font-weight: 500;">
+                ⚠️ This demo doesn't have load balancing or parallel query handling. 
+                You must wait for everyone else to finish first during busy times. Sorry!
+            </p>
+        </div>
+    ''')
    
     with gr.Tabs():
         with gr.TabItem("Speech Generation"):
@@ -597,7 +606,7 @@ with gr.Blocks(theme="Respair/Shiki@9.1.0", css=css) as demo:
         
         <p style="color: #1a1a1a; font-weight: 500; line-height: 1.8; margin-bottom: 20px; font-size: 16px;">
         Takane also comes with an Anti-Hallucination Algorithm (AHA) that generates a few candidates in parallel and automatically returns the best one at the cost of introducing a small overhead. 
-        If you need the fastest response time possible, feel free to enable the Turbo mode. It will disable AHA and tweak the parameters internally to produce samples as fast as 2-3 seconds.
+        If you need the fastest response time possible, feel free to enable the Turbo mode. It will disable AHA and tweak the parameters internally to produce samples as fast as 2-3 seconds (though due to an influx of users coming in, you probably will be qeued and have to wait!)
         </p>
         
         <p style="color: #1a1a1a; font-weight: 500; line-height: 1.8; margin-bottom: 20px; font-size: 16px;">