Spaces:
Sleeping
Sleeping
File size: 2,497 Bytes
33903b2 3fce1a1 401f179 33903b2 401f179 33903b2 15f27fa b8dff16 3fce1a1 b8dff16 33903b2 3145e0e 33903b2 34a52d9 33903b2 15f27fa 33903b2 |
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 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
from transformers import pipeline
from dotenv import find_dotenv, load_dotenv
from langchain import PromptTemplate, LLMChain, HuggingFaceHub
import streamlit as st
import requests
import os
load_dotenv(find_dotenv())
huggingface_api_key = os.getenv("HUGGINGFACE_API")
def image2text(url):
image_to_text = pipeline('image-to-text', model='Salesforce/blip-image-captioning-large')
text = image_to_text(url)[0]['generated_text']
print(text)
return text
def generate_story(scenario, length):
template = """
You are story teller, generate a short story in {length} words\n
CONTEXT:{scenario}\n
STORY:
"""
prompt = PromptTemplate(template=template, input_variables=["scenario","length"])
llm = LLMChain(llm=HuggingFaceHub(huggingfacehub_api_token=huggingface_api_key, repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1"), prompt=prompt, verbose=True)
story = llm.predict(scenario=scenario, length=length)
print(story)
return story
# def text2speech(message):
# API_URL = "https://api-inference.huggingface.co/models/microsoft/speecht5_tts"
# headers = {"Authorization": f"Bearer {HUGGINGFACE_API}"}
# payloads = {
# "inputs": message
# }
# response = requests.post(API_URL,headers=headers,json=payloads)
# with open('audio.wav', 'wb') as file:
# file.write(response.content)
def main():
st.set_page_config(page_title="Image Storyteller")
st.header("Image to Story")
length = st.number_input("Length")
if not length:
length = 10
uploaded_file = st.file_uploader("Choose an Image", type="jpg")
scenario = ""
successful_processing = False
if uploaded_file is not None:
print(uploaded_file)
bytes_data = uploaded_file.getvalue()
with open(uploaded_file.name, "wb") as file:
file.write(bytes_data)
st.image(uploaded_file.name, caption="Uploaded Image", use_column_width=True)
try:
scenario = image2text(uploaded_file.name)
successful_processing = True
except Exception as e:
st.error(f"Error processing the image: {e}")
if successful_processing:
story = generate_story(scenario, length)
# text2speech(story)
with st.expander("Scenario"):
st.write(scenario)
with st.expander("Generated Story"):
st.write(story)
# st.audio('audio.wav')
if __name__ == '__main__':
main()
|