app.py

import gradio as gr
from transformers import pipeline

captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")

def caption(image):
    return captioner(image)[0]["generated_text"]

gr.Interface(
    fn=caption,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Image Caption Generator"
).launch()