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

# Initialize the pipeline with the image captioning model
caption_pipeline = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")

def generate_caption(image):
    # The image is received as a PIL Image, so no need for conversion
    result = caption_pipeline(image)
    caption = result[0]["generated_text"]
    return caption

# Setup the Gradio interface
interface = gr.Interface(fn=generate_caption,
                         inputs=gr.inputs.Image(label="Upload an Image", type="pil"),
                         outputs=gr.outputs.Textbox(label="Generated Caption"))
interface.launch()