Update app.py

app.py

@@ -178,7 +178,7 @@ def chat(history, user_input, user_image):
         # Use Emu3-Chat for vision-language understanding
         response = vision_language_understanding(user_image, user_input)
         # Append the user input and response to the history
-        history = history + [(image2str(user_image) + user_input, response)]
+        history = history + [(image2str(user_image) + "\n" + user_input, response)]
     else:
         # Use Emu3-Gen for image generation
         generated_image = generate_image(user_input)