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-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

def caption(img):
    raw_image = Image.open(img).convert('RGB')
  
    inputs = processor(raw_image, return_tensors="pt")
    
    out = model.generate(**inputs, min_length=30, max_length=1000)
    return processor.decode(out[0], skip_special_tokens=True)

def greet(img):
    return caption(img)

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