import os
import gradio as gr
from transformers import pipeline

model_id = "Salesforce/blip-vqa-base"

pipe = pipeline("image-to-text", model=model_id)

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

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

iface.launch()