app.py

import os
os.environ["TRANSFORMERS_CACHE"] = "/tmp/hf-cache"



from flask import Flask, request, jsonify
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import torch
import io

app = Flask(__name__)

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

device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

@app.route("/caption", methods=["POST"])
def caption_image():
    if 'image' not in request.files:
        return jsonify({"error": "No image file provided"}), 400

    try:
        image_file = request.files['image']
        image = Image.open(io.BytesIO(image_file.read())).convert("RGB")

        processed_image = processor(images=image, return_tensors="pt").pixel_values.to(device)

        with torch.no_grad():
            output = model.generate(processed_image)

        caption = processor.decode(output[0], skip_special_tokens=True)
        return jsonify({"caption": caption})
    
    except Exception as e:
        return jsonify({"error": str(e)}), 500

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)