Update image_to_text.py

image_to_text.py

@@ -1,13 +1,18 @@
 from transformers import BlipProcessor, BlipForConditionalGeneration
 import torch
+from PIL import Image
 
 # Load the BLIP model and processor
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 
 def generate_initial_caption(image):
+    # Ensure the image is in RGB format
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+    
     # Prepare the image for the model
-    inputs = processor(images=image, return_tensors="pt")
+    inputs = processor(images=image, return_tensors="pt", padding=True)
     
     # Generate the caption
     with torch.no_grad():