Update app.py

app.py

@@ -5,6 +5,7 @@ import numpy as np
 import soundfile as sf
 import tempfile
 import os
+from PIL import Image
 
 # Initialize pipelines
 @st.cache_resource
@@ -18,8 +19,11 @@ captioner, storyer, tts = load_pipelines()
 
 # Main logic
 def generate_content(image):
+    # Convert Streamlit uploaded image to PIL image
+    pil_image = Image.open(image)
+    
     # Generate caption
-    caption = captioner(image)[0]["generated_text"]
+    caption = captioner(pil_image)[0]["generated_text"]
     st.write("**Caption:**", caption)
 
     # Generate story