Update app.py

app.py

@@ -1,27 +1,28 @@
 import streamlit as st
 from transformers import pipeline
 
-# Initialize the model
+# Initialize the image captioning pipeline
 captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
 
 # Streamlit app title
-st.title("Image Captioning with Transformers")
+st.title("Image to Text Captioning")
 
-# Input for the image URL
-image_url = st.text_input("Enter the URL of an image", "https://www.simplilearn.com/ice9/free_resources_article_thumb/random_forest_algorithm.jpg")
+# Input for image URL
+image_url = st.text_input("Enter the URL of the image:")
 
-# Display the image
+# If an image URL is provided
 if image_url:
-    st.image(image_url, caption="Input Image", use_column_width=True)
+    try:
+        # Display the image
+        st.image(image_url, caption="Provided Image", use_column_width=True)
+        
+        # Generate the caption
+        caption = captioner(image_url)
+        
+        # Display the caption
+        st.write("**Generated Caption:**")
+        st.write(caption[0]['generated_text'])
+    except Exception as e:
+        st.error(f"An error occurred: {e}")
 
-    # Generate the caption
-    if st.button("Generate Caption"):
-        with st.spinner("Generating caption..."):
-            caption = captioner(image_url)
-            st.write("**Caption:**", caption[0]['generated_text'])
-
-# Add some information about the app
-st.write("""
-    This app uses a pre-trained model from the Hugging Face Transformers library to generate captions for images.
-    Enter an image URL above and click "Generate Caption" to see the result.
-""")
+# To run this app, save this code to a file (e.g., `app.py`) and run `streamlit run app.py` in your terminal.