app.py

import gradio as gr
from transformers import pipeline

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

def launch(input):
    out = pipe(input)
    return out[0]['generated_text']

iface = gr.Interface(launch,
                     inputs=[gr.Image(label="Upload Image",type='pil')],
                     outputs=[gr.Textbox(label="Caption of the image provided", lines=3)],
                     description="Caption any image using the BLIP model",
                     title="Image Description",
                     #examples=["uncle_bought_car.jpg","ajaj_photo.jpg","half_moon.jpg","scooty.jpg"]
                    )

iface.launch()