app.py

import gradio as gr

from transformers import pipeline

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


def describe(raw_image):
    out = model(raw_image)
    return out[0]['generated_text']


iface = gr.Interface(describe,
                     inputs = gr.Image(type = 'pil'),
                     outputs = gr.Textbox())

if __name__ == '__main__':
    iface.launch()