app.py

import gradio as gr
from transformers import pipeline

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

def captioner(input):
    output = get_completion(input)
    return output[0]['generated_text']

gr.close_all()
demo = gr.Interface(fn=captioner,
                    inputs=[gr.Image(label="Upload image", type="pil")],
                    outputs=[gr.Textbox(label="Caption")],
                    title="Image Captioning with BLIP",
                    description="Caption any image using the BLIP model",
                    allow_flagging="never",
                    examples=["christmas_dog.jpeg", "bird_flight.jpeg", "cow.jpeg"])

demo.launch()