app.py

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

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

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

iface = gr.Interface(
    fn=caption_image,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Captionify: AI Image Caption Generator"
)

iface.launch()