File size: 1,684 Bytes
d87e8d0 a14c96e ba82693 a14c96e d87e8d0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import streamlit as st
from app.captioning import generate_caption
from app.storytelling import generate_story
from app.tts import speak_story
import tempfile
from PIL import Image
from huggingface_hub import login
import os
# Get token from Streamlit secrets
#hf_token = st.secrets["HF_TOKEN"]
hf_token = os.getenv("HF_TOKEN")
# Login to Hugging Face Hub
login(token=hf_token)
st.set_page_config(page_title="GenAI Storyteller", layout="centered")
st.title("📸🧠 GenAI Storyteller")
st.markdown("Upload an image, get a caption, a story, and hear it spoken aloud!")
uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
if uploaded_file:
# Show uploaded image
image = Image.open(uploaded_file)
st.image(image, caption="Uploaded Image", use_container_width=True)
# Process the pipeline on button click
if st.button("Generate Story"):
with st.spinner("Generating caption..."):
# Save uploaded image to a temp file
with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp:
image.save(tmp.name)
caption = generate_caption(tmp.name)
st.success("Caption Generated!")
st.write(f"**Caption**: {caption}")
with st.spinner("Generating story..."):
story = generate_story(caption)
st.success("Story Generated!")
st.text_area("📖 Story", story, height=250)
with st.spinner("Generating audio..."):
audio_path = speak_story(story)
st.success("Done! Here's the story in audio:")
audio_file = open(audio_path, "rb")
st.audio(audio_file.read(), format="audio/mp3")
|