Spaces:
Sleeping
Sleeping
File size: 1,848 Bytes
b830598 5d63cd1 b830598 5d63cd1 b830598 5d63cd1 b830598 5d63cd1 b830598 5d63cd1 b830598 5d63cd1 |
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 |
import streamlit as st
from PIL import Image
import requests
from transformers import BlipProcessor, BlipForConditionalGeneration
# Load the model and processor outside the main function to avoid reloading on every run
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
def generate_caption(img_url):
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# Conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")
out = model.generate(**inputs)
conditional_caption = processor.decode(out[0], skip_special_tokens=True)
# Unconditional image captioning
inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs)
unconditional_caption = processor.decode(out[0], skip_special_tokens=True)
return conditional_caption, unconditional_caption
def main():
st.title("Image Captioning App")
img_url = st.text_input("Enter the image URL:")
if img_url:
try:
# Display the image
image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
st.image(image, caption='Input Image', use_column_width=True)
# Generate captions
conditional_caption, unconditional_caption = generate_caption(img_url)
# Display captions
st.subheader("Conditional Image Caption")
st.write(conditional_caption)
st.subheader("Unconditional Image Caption")
st.write(unconditional_caption)
except Exception as e:
st.error(f"Error processing the image: {e}")
if __name__ == "__main__":
main()
|