Update app.py

app.py

@@ -51,31 +51,35 @@ def array_to_image_path(image_array):
 def run_example(image, text_input=None):
     image_path = array_to_image_path(image)
     image = Image.fromarray(image).convert("RGB")
+    
     messages = [
     {
             "role": "user",
             "content": [
                 {
                     "type": "image",
-                    "image": image_path,
+                    "text": None,
                 },
                 {
-                    "type": "text", 
-                    "text": text_input
+                    "text": text_input, 
+                    "type": "text"
                 },
             ],
         }
     ]
-    
+        
     # Preparation for inference
     text = processor.apply_chat_template(
         messages, tokenize=False, add_generation_prompt=True
     )
-    image_inputs, video_inputs = process_vision_info(messages)
+    image_inputs = []
+    if image.mode != 'RGB':
+        image = image.convert('RGB')
+    image_inputs.append([image])
+    
     inputs = processor(
-        text=[text],
+        text=text,
         images=image_inputs,
-        videos=video_inputs,
         padding=True,
         return_tensors="pt",
     )