Update app.py

app.py

@@ -1,14 +1,19 @@
-# Import part
+# This is NOT a complete program
+
+
+# import part
 import streamlit as st
-from PIL import Image
-import time
 from transformers import pipeline
+from PIL import Image
+import io
 
-# Function part
-def generate_image_caption(image_path):
+# function part
+def generate_image_caption(image):
     """Generates a caption for the given image using a pre-trained model."""
     img2caption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
-    result = img2caption(image_path)
+
+    # Generate caption
+    result = img2caption(image)
     return result[0]['generated_text']
 
 # text2story
@@ -17,21 +22,23 @@ def text2story(text):
     story_text = pipe(text)[0]['generated_text']
     return story_text
 
-# Main part
-# App title
-st.title("Assignment")
+def main():
+    # App title
+    st.title("Streamlit Demo on Hugging Face")
 
-# Write some text
-st.write("Image to Story")
+    # Write some text
+    st.write("Welcome to a demo app showcasing basic Streamlit components!")
 
-# File uploader for image and audio
-uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+    uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
 
-# Display image with spinner
-if uploaded_image is not None:
-    with st.spinner("Loading image..."):  # make sure this line ends with a colon!
-        time.sleep(1)  # Simulate a delay
-        image = Image.open(uploaded_image)
+    if uploaded_image is not None:
+        image = Image.open(uploaded_image).convert("RGB")   # Create an image object
         st.image(image, caption="Uploaded Image", use_column_width=True)
-        caption = generate_image_caption(uploaded_image)
-        st.write(f"Generated Caption: {caption}")
+
+        # Stage 1: Image to Text
+        st.text('Processing img2text...')
+        image_caption = generate_image_caption(image)
+        st.write(image_caption)
+
+if __name__ == "__main__":
+    main()