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']


title = "Generate caption for uploaded image"
description = "Uses the Blip Image Captioning Model from Salesforce"


iface = gr.Interface(launch,
                     inputs=gr.Image(type='pil'),
                     outputs="text",
                     title=title,
                     description=description)

iface.launch()