Update app.py

app.py

@@ -1,22 +1,14 @@
-import requests
+import streamlit as st
+from transformers import pipeline
 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")
+pipeline = pipeline(task="image-to-text", model="Salesforce/blip-image-captioning-large)
 
-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')
+file_name = st.file_uploader("")
 
-# conditional image captioning
-text = "a photography of"
-inputs = processor(raw_image, text, return_tensors="pt")
+if file_name is not None:
+    col1, col2 = st.columns(2)
 
-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))
+    image = Image.open(file_name)
+    col1.image(image, use_column_width=True)
+    pipeline(image)