Update app.py

app.py

@@ -33,7 +33,7 @@ def predict(image, text):
     inputs = processor(image, input_text, return_tensors="pt").to(model.device)
     outputs = model.generate(**inputs, max_new_tokens=250)
     response = processor.decode(outputs[0], skip_special_tokens=True)
-    return response
+    return f"\n{response}"
 
 # Gradio
 interface = gr.Interface(