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")

def caption(img):
    raw_image = Image.open(img).convert('RGB')
  
    inputs = processor(raw_image, return_tensors="pt")
    
    out = model.generate(**inputs, min_length=40, max_length=200)
    return processor.decode(out[0], skip_special_tokens=True)

def greet(img):
    return caption(img)

iface = gr.Interface(fn=greet, 
                     title='Blip Image Captioning Large', 
                     inputs=gr.Image(type='filepath', label='Image'), 
                     outputs=gr.Textbox(label='Caption'),
                     theme = gr.themes.Base(primary_hue="teal",secondary_hue="teal",neutral_hue="slate"),)
iface.launch()