Use Transformers

app.py

@@ -1,9 +1,10 @@
 import streamlit as st
 from PIL import Image
-from transformers import BlipProcessor, BlipForConditionalGeneration
 
-processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
+processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-large")
 
 enable = st.checkbox("Enable camera")
 picture = st.camera_input("Take a picture", disabled=not enable)