app.py

import gradio as gr
from transformers import pipeline

pipe = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")

def generate_caption(image):
    result = pipe(image)
    return result[0]["generated_text"].strip()

title = "🖼️ Image Caption Generator"
description = "Upload an image and get a caption"

demo = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil"),
    outputs=gr.Textbox(label="Generated Caption"),
    title=title,
    description=description,
    flagging_mode="never"
)

if __name__ == "__main__":
    demo.launch(share=False)