import gradio as gr
from transformers import pipeline

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

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

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

iface.launch()