app.py

import gradio as gr
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration


processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

def execute(image): 
    inputs = processor(image, return_tensors="pt")
    out = model.generate(**inputs)
    output = processor.decode(out[0], skip_special_tokens=True)
    return output
    
iface = gr.Interface(
    execute,
    inputs=[
        "image",
    ], 
    outputs="textbox"
)

iface.launch()