Update app.py

app.py

@@ -32,7 +32,7 @@ def generate_input(input_type, image=None, text=None):
         inputs = processor(images=image, return_tensors="pt")
         out = image_model.generate(**inputs)
         image_caption = processor.decode(out[0], skip_special_tokens=True)
-        combined_input += image_caption + " " + text  # Combine image caption and text
+        combined_input += image_caption + " and " + text  # Combine image caption and text
     
     # If no input, fallback
     if not combined_input: