Update app.py

app.py

@@ -1,3 +1,5 @@
+# app.py
+
 import streamlit as st
 from PIL import Image
 from transformers import pipeline
@@ -11,9 +13,9 @@ st.title("🖼️ ➡️ 📖 Interactive Storyteller")
 # —––––––– Cache model loading
 @st.cache_resource
 def load_pipelines():
-    # 1) Image captioning
+    # 1) Image-to-text (captioning)
     captioner = pipeline(
-        "image-captioning",
+        "image-to-text",
         model="Salesforce/blip-image-captioning-base"
     )
     # 2) Story generation with Flan-T5
@@ -33,7 +35,9 @@ if uploaded:
 
     # —––––––– 1. Caption
     with st.spinner("🔍 Looking at the image..."):
-        cap = captioner(image)[0]["generated_text"]
+        cap_outputs = captioner(image)
+        # BLIP returns a list of dicts with key "generated_text"
+        cap = cap_outputs[0].get("generated_text", "").strip()
     st.markdown(f"**Caption:** {cap}")
 
     # —––––––– 2. Story generation
@@ -60,4 +64,4 @@ if uploaded:
         tmp = tempfile.NamedTemporaryFile(suffix=".mp3", delete=False)
         tts.write_to_fp(tmp)
         tmp.flush()
-    st.audio(tmp.name, format="audio/mp3")
+    st.audio(tmp.name, format="audio/mp3")