app.py

# -*- coding: utf-8 -*-
'''AI Image Caption Generator - Hugging Face Deployment'''

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

warnings.filterwarnings("ignore")

# Use BASE model (faster + safer on HF free CPU)
processor = BlipProcessor.from_pretrained(
    "Salesforce/blip-image-captioning-base"
)
model = BlipForConditionalGeneration.from_pretrained(
    "Salesforce/blip-image-captioning-base"
)

def generate_caption(image):
    image = Image.open(image).convert("RGB")
    inputs = processor(image, return_tensors="pt")

    with torch.no_grad():
        output = model.generate(**inputs)

    caption = processor.decode(output[0], skip_special_tokens=True)
    return caption

iface = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="filepath"),
    outputs=gr.Textbox(label="Generated Caption"),
    title="AI Image Caption Generator",
    description="Upload an image and the model will generate a meaningful caption."
)

iface.launch()