app.py

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

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

def caption(img):
    inputs = processor(images=img, return_tensors="pt")
    out = model.generate(**inputs)
    return processor.decode(out[0], skip_special_tokens=True)

gr.Interface(fn=caption, inputs=gr.Image(), outputs="text", title="Image Captioning").launch()