Update app.py

app.py

@@ -1,4 +1,6 @@
 import torch
+from PIL import Image
+import requests
 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
 
@@ -14,14 +16,23 @@ model = model.to(device)
 # Default processor
 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
 
-# Prepare input messages
+# Resize the image to a smaller resolution (e.g., 512x512)
+image_url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
+response = requests.get(image_url)
+img = Image.open(BytesIO(response.content))
+
+# Resize the image
+img_resized = img.resize((512, 512))  # Resize the image to 512x512
+image_inputs = processor(images=img_resized, return_tensors="pt").to(device)
+
+# Prepare the text input
 messages = [
     {
         "role": "user",
         "content": [
             {
                 "type": "image",
-                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+                "image": img_resized,
             },
             {"type": "text", "text": "Describe this image."},
         ],
@@ -56,4 +67,4 @@ output_text = processor.batch_decode(
 )
 
 # Print the output
-print(output_text)
+print(output_text)