from transformers import pipeline
import gradio as gr

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

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

# iface = gr.Interface(
# fn = launch,
# inputs = gr.Image(type='pil',),
# outputs = gr.Textbox()
# )
# iface.launch()

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

iface.launch()