improved UI

app.py

@@ -514,9 +514,11 @@ def load_models():
 def build_demo():
     with gr.Blocks(title="AAS2F: Ambiguity-Aware Speech-to-Face Synthesis with Speaker-Conditioned Diffusion Models") as demo:
         gr.Markdown("# AAS2F: Ambiguity-Aware Speech-to-Face Synthesis with Speaker-Conditioned Diffusion Models")
-        gr.Markdown("**Steps to use the demo:**")
-        gr.Markdown("1. Upload or record a speech audio clip and generate face images conditioned on the speaker's voice. **Please provide at least 5 seconds of speech.** Note that it works best with **English** as the model is trained on English speech, but should work with other languages as well.")
-        gr.Markdown("2. Click the 'Generate' button to start the generation process.")
+        gr.Markdown(
+            "**Steps to use the demo:**\n\n"
+            "1. Upload or record a speech audio clip and generate face images conditioned on the speaker's voice. **Please provide at least 5 seconds of speech.** Note that it works best with **English** as the model is trained on English speech, but should work with other languages as well.\n"
+            "2. Click the 'Generate' button to start the generation process."
+        )
 
         with gr.Row():
             with gr.Column():