app.py

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

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

# Function to generate captions
def generate_caption(image):
    image = Image.open(image).convert("RGB")
    inputs = processor(image, return_tensors="pt")
    outputs = model.generate(**inputs)
    caption = processor.decode(outputs[0], skip_special_tokens=True)
    return caption

# Create Gradio Interface
iface = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="AI Image Caption Generator",
    description="Upload an image and get an AI-generated caption.",
)

# Run app
iface.launch()