import gradio as gr
from transformers import pipeline

pipe = pipeline(
    "image-to-text",
    model="Salesforce/blip-image-captioning-base"
)

def caption_image(image):
    if image is None:
        return "Please upload an image."

    result = pipe(image)
    return result[0]["generated_text"]

demo = gr.Interface(
    fn=caption_image,
    inputs=gr.Image(type="pil", label="Upload Image"),
    outputs=gr.Textbox(label="Generated Caption"),
    title="Image Captioning App",
    description="Upload an image and the BLIP model will generate a caption."
)

if __name__ == "__main__":
    demo.launch()