app.py

# -*- coding: utf-8 -*-
"""app.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1yM6SHreIA1NYzW6CrVDyUl5Fub4VPwDy
"""

!pip install transformers

import torch
from PIL import Image
from transformers import CLIPProcessor, CLIPModel

device = torch.device("cpu")  # Use CPU device
model_name = "openai/clip-vit-base-patch32"  # Pretrained CLIP model
model = CLIPModel.from_pretrained(model_name).to(device)
processor = CLIPProcessor.from_pretrained(model_name)

def stable_diffusion(image_path):
    image = Image.open(image_path)
    inputs = processor(text=["a photo"], images=image, return_tensors="pt", padding=True)
    inputs = {k: v.to(device) for k, v in inputs.items()}
    outputs = model(**inputs)
    # Process the outputs as per your requirements
    # For example, you can access the image and text embeddings as follows:
    image_embed = outputs["image_embeds"]
    text_embed = outputs["text_embeds"]
    # Perform further computations or display the results

from flask import Flask, request, render_template
import os

app = Flask(__name__)

@app.route("/", methods=["GET", "POST"])
def upload_image():
    if request.method == "POST":
        if "image" not in request.files:
            return "No image uploaded"

        image = request.files["image"]
        image.save("uploaded_image.jpg")
        stable_diffusion("uploaded_image.jpg")
        os.remove("uploaded_image.jpg")

        return "Stable Diffusion completed!"

    return render_template("index.html")