app.py

from transformers import pipeline
import gradio as gr
from PIL import Image
import numpy as np

# Load the image captioning pipeline
pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")

def fun2(image):
    # Convert input image (which may be a NumPy array) to PIL Image
    if isinstance(image, np.ndarray):
        image = Image.fromarray(image)
    
    ans = pipe(image)
    return ans[0]['generated_text']

# Set up Gradio interface
obj4 = gr.Interface(fn=fun2, inputs="image", outputs="text")
obj4.launch(debug=True)