Update app.py

app.py

@@ -1,15 +1,22 @@
 import requests
 from PIL import Image
 from transformers import BlipProcessor, BlipForConditionalGeneration
-import streamlit as st
 
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 
-file_name = st.file_uploader("Upload")
+img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
 
-if file_name is not None:
-    inputs = processor(Image.open(file_name).convert('RGB'), return_tensors="pt")
-    
-    out = model.generate(**inputs)
-    print(processor.decode(out[0], skip_special_tokens=True))
+# conditional image captioning
+text = "a photography of"
+inputs = processor(raw_image, text, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))