app.py

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

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

# Captioning function with fallback logic
def caption_image(image):
    try:
        inputs = processor(images=image, return_tensors="pt").to(device)
        output = model.generate(**inputs, max_length=30)
        caption = processor.tokenizer.decode(output[0], skip_special_tokens=True)
        return caption.capitalize()
    except Exception as e:
        return f"⚠️ Error: {str(e)[:100]}"

# Gradio UI
gr.Interface(
    fn=caption_image,
    inputs=gr.Image(type="pil", label="Upload Image"),
    outputs=gr.Textbox(label="Generated Caption"),
    title="🖼️ BLIP Image Caption Generator",
    description="Fast, accurate image captioning using BLIP. No API keys. CPU-friendly. Instant output.",
    allow_flagging="never"
).launch()