Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from PIL import Image | |
| import requests | |
| from transformers import BlipProcessor, BlipForConditionalGeneration | |
| # Load the BLIP model | |
| processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large") | |
| model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large") | |
| # Streamlit app | |
| st.title("Image Captioning with BLIP") | |
| # Uploading the image | |
| uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"]) | |
| if uploaded_image is not None: | |
| image = Image.open(uploaded_image).convert('RGB') | |
| st.image(image, caption='Uploaded Image', use_column_width=True) | |
| # Perform conditional image captioning | |
| captioning_mode = st.selectbox("Captioning Mode", ["Conditional", "Unconditional"]) | |
| if captioning_mode == "Conditional": | |
| text = st.text_input("Provide a condition for the captioning (e.g., 'a photo of', 'an illustration of'): ", "a photo of") | |
| if text: # Only proceed if the user has provided a text | |
| inputs = processor(image, text, return_tensors="pt") | |
| out = model.generate(**inputs) | |
| caption = processor.decode(out[0], skip_special_tokens=True) | |
| st.write(f"Generated Caption: {caption}") | |
| else: # Unconditional captioning | |
| inputs = processor(image, return_tensors="pt") | |
| out = model.generate(**inputs) | |
| caption = processor.decode(out[0], skip_special_tokens=True) | |
| st.write(f"Generated Caption: {caption}") | |