Update app.py

app.py

@@ -43,8 +43,10 @@ def process_image_and_text(image_pil, text_input, num_beams, temperature, seed):
         # Load the image using load_image
         image = load_image(image_pil)
 
+        prompt = ""
+
         # Use the provided text input
-        model_inputs = processor(images=image, return_tensors="pt").to(
+        model_inputs = processor(text=prompt, images=image, return_tensors="pt").to(
             device, dtype=torch.bfloat16
         )
         input_len = model_inputs["input_ids"].shape[-1]