app.py

from transformers import pipeline
import gradio as gr
import os
import io
import IPython.display
from PIL import Image
import base64

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

def summarize(input):
    output = get_completion(input)
    return output[0]['generated_text']

import gradio as gr 

def image_to_base64_str(pil_image):
    byte_arr = io.BytesIO()
    pil_image.save(byte_arr, format='PNG')
    byte_arr = byte_arr.getvalue()
    return str(base64.b64encode(byte_arr).decode('utf-8'))

def captioner(image):
    base64_image = image_to_base64_str(image)
    result = get_completion(base64_image)
    return result[0]['generated_text']

gr.close_all()
demo = gr.Interface(fn=captioner,
                    inputs=[gr.Image(label="Upload image", type="pil")],
                    outputs=[gr.Textbox(label="Caption")],
                    title="Image Captioning with BLIP",
                    description="Caption any image using the BLIP model",
                    allow_flagging="never")

demo.launch()