app.py

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

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

def generate_caption(image):
    result = captioner(image)
    return result[0]['generated_text']

# Define the Gradio interface
interface = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil"),
    outputs=gr.Textbox(label="Caption"),
    title="Image Captioning App",
    description="Upload an image and get a caption using the BLIP model."
)

# Launch the app
if __name__ == "__main__":
    interface.launch()