from transformers import pipeline
import gradio as gr
from PIL import Image

# Load the image captioning pipeline
pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")

def generate_caption(image):
    # Generate a caption for the image
    captions = pipe(image)
    return captions[0]['generated_text']

# Create a Gradio interface for image captioning
demo = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil", label="Upload an Image"),
    outputs=gr.Textbox(label="Generated Caption"),
    title="Image Caption Generator",
    description="Upload an image to generate a caption using the BLIP model."
)

# Launch the Gradio interface
if __name__ == "__main__":
    demo.launch(share=True)