app.py

# 🖼️ BLIP Image Captioning - Fast, Accurate, CPU-Friendly
import torch
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import gradio as gr

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

# Captioning function
def caption_image(image):
    try:
        inputs = processor(images=image, return_tensors="pt").to(device)
        out = model.generate(**inputs, max_length=30)
        caption = processor.tokenizer.decode(out[0], skip_special_tokens=True)
        return caption.capitalize()
    except Exception:
        return "Could not generate caption. Try a different image."

# Launch Gradio interface
gr.Interface(
    fn=caption_image,
    inputs=gr.Image(type="pil", label="Upload Image"),
    outputs=gr.Textbox(label="Generated Caption"),
    title="🖼️ Image Caption Generator (BLIP)",
    description="Accurate, fast image captioning using BLIP. No API keys. CPU-friendly. Instant output.",
    examples=["example.jpg"],  # Optional: preload sample image
    cache_examples=True        # Optional: speeds up UX
).launch()