Update app.py

app.py

@@ -61,7 +61,7 @@ def infer(audio_file):
     llama_q = f"""
 
     I'll give you music description, then i want you to provide an illustrative image description that would fit well with the music.
-    MAX 77 tokens.
+    
     Answer with only one image description. Never do lists. Do not processs each segment, but provide a summary for the whole instead.
 
     Here's the music description :