app.py

import os
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']

markdown_message= gr.Markdown(
                    """
                    # Image Captioning!
                    BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.
                """)

iface = gr.Interface(launch,
                     inputs=gr.Image(type='pil'),
                     outputs="text",
                     title="Image Captioning based on Salesforce Blip",
                     description="Upload an image and get its caption.")

iface.launch()