app.py

# Import Part
import streamlit as st
import time
from PIL import Image
from transformers import pipeline

# Function Part
def generate_image_caption(image_path):
  img2caption = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
  result = img2caption(image_path)
  return result[0]['generated_text']

def text2story(text):
  text2story = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
  generated_story = text2story(text)
  return generated_story[0]['generated_text']

# Main Part

# App title
st.title("Assignment")

# Write some text
st.write("Welcome to a demo app showcasting basic streamlit component")

# file upload
uploaded_image = st.file_uploader("Upload an image", type=['jpg','jpeg','png'], accept_multiple_files=False, key="file_uploader")
# uploaded_audio = st.file_uploader("Upload an audio file", type = ['mp3','mov','egg'])

if uploaded_image is not None:
    with st.spinner("Loading image..."):
        time.sleep(1) # Simulate a delay
        image = Image.open(uploaded_image)
        # st.image(image, caption='Uploaded Image', use_column_width=True)
        
        # Generate caption
        caption = generate_image_caption(image)
        st.write("Generated Caption:", caption)
        
        # Generate story
        if st.button("Generate Story"):
            with st.spinner("Generating story..."):
                generated_story = text2story(caption)
                st.write("Generated Story:", generated_story)
        

# #Play audio with apinner:
# if uploaded_audio is not None:
#     with st.spinner("Loading audio..."):
#         time.sleep(1)
#         st.audo(uploaded_audio)

# # Button interaction:
# if st.button("Click Me"):
#     st.write("you clicked the button!")