Update app.py

app.py

@@ -279,8 +279,9 @@ def predict(
 with gr.Blocks() as demo:
     gr.HTML("""
         <h1 align="center" style=" display: flex; flex-direction: row; justify-content: center; font-size: 25pt; "><img src='./file=bot.png' width="50" height="50" style="margin-right: 10px;">M<sup style="line-height: 200%; font-size: 60%">2</sup>UGen</h1>
-        <h3>This is the demo page of M<sup>2</sup>UGen, a Multimodal LLM capable of Music Understanding and Generation!</h3>
-        <div style="display: flex;"><a href='https://arxiv.org/pdf/2311.11255.pdf'><img src='https://img.shields.io/badge/Paper-PDF-red'></a></div>
+        <h3>This is the demo page of M<sup>2</sup>UGen, a Music Understanding and Generation model that is capable of Music Question Answering and also Music Generation from texts, images, videos and audios, as well as Music Editing. 
+        The model utilizes encoders such as MERT for music understanding, ViT for image understanding and ViViT for video understanding and the MusicGen/AudioLDM2 model as the music generation model (music decoder), coupled with adapters and the LLaMA 2 model to make the model capable of multiple abilities!</h3>
+        <div style="display: flex;"><a href='https://crypto-code.github.io/M2UGen-Demo/'><img src='https://img.shields.io/badge/Project-Page-Green'></a> &nbsp  &nbsp  &nbsp <a href='https://github.com/shansongliu/M2UGen'><img src='https://img.shields.io/badge/Github-Code-blue'></a> &nbsp &nbsp  &nbsp  <a href='https://arxiv.org/pdf/2311.11255.pdf'><img src='https://img.shields.io/badge/Paper-PDF-red'></a></div>
         """)
 
     with gr.Row():