Update app.py

app.py

@@ -1,10 +1,13 @@
 from transformers import BlipProcessor, BlipForConditionalGeneration
 from PIL import Image
+# Load model directly
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
 
 def generate_caption(image_path):
     image = Image.open(image_path)
-    processor = BlipProcessor.from_pretrained("facebook/blip-image-captioning-base")
-    model = BlipForConditionalGeneration.from_pretrained("facebook/blip-image-captioning-base")
+    processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+    model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-base")
     inputs = processor(image, return_tensors="pt")
     output = model.generate(**inputs)
     caption = processor.decode(output[0], skip_special_tokens=True)