CLIP_and_Dall_E.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ETwtDgkSnq-Z",
        "outputId": "32121a57-da94-4f7c-d8d1-7efb0788b87d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting flask-ngrok\n",
            "  Downloading flask_ngrok-0.0.25-py3-none-any.whl.metadata (1.8 kB)\n",
            "Collecting openai\n",
            "  Downloading openai-1.45.0-py3-none-any.whl.metadata (22 kB)\n",
            "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.4.0+cu121)\n",
            "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (0.19.0+cu121)\n",
            "Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (9.4.0)\n",
            "Collecting clip-by-openai\n",
            "  Downloading clip_by_openai-1.1-py3-none-any.whl.metadata (369 bytes)\n",
            "Requirement already satisfied: Flask>=0.8 in /usr/local/lib/python3.10/dist-packages (from flask-ngrok) (2.2.5)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from flask-ngrok) (2.32.3)\n",
            "Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai) (3.7.1)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai) (1.7.0)\n",
            "Collecting httpx<1,>=0.23.0 (from openai)\n",
            "  Downloading httpx-0.27.2-py3-none-any.whl.metadata (7.1 kB)\n",
            "Collecting jiter<1,>=0.4.0 (from openai)\n",
            "  Downloading jiter-0.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.6 kB)\n",
            "Requirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from openai) (2.9.1)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.1)\n",
            "Requirement already satisfied: tqdm>4 in /usr/local/lib/python3.10/dist-packages (from openai) (4.66.5)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.11 in /usr/local/lib/python3.10/dist-packages (from openai) (4.12.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.16.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.13.2)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.3)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.4)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch) (2024.6.1)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torchvision) (1.26.4)\n",
            "Collecting ftfy (from clip-by-openai)\n",
            "  Downloading ftfy-6.2.3-py3-none-any.whl.metadata (7.8 kB)\n",
            "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from clip-by-openai) (2024.5.15)\n",
            "INFO: pip is looking at multiple versions of clip-by-openai to determine which version is compatible with other requirements. This could take a while.\n",
            "Collecting clip-by-openai\n",
            "  Downloading clip_by_openai-1.0.1-py3-none-any.whl.metadata (407 bytes)\n",
            "  Downloading clip_by_openai-0.1.1.5-py3-none-any.whl.metadata (8.6 kB)\n",
            "  Downloading clip_by_openai-0.1.1.4-py3-none-any.whl.metadata (8.6 kB)\n",
            "  Downloading clip_by_openai-0.1.1.3-py3-none-any.whl.metadata (8.7 kB)\n",
            "  Downloading clip_by_openai-0.1.1.2-py3-none-any.whl.metadata (9.0 kB)\n",
            "  Downloading clip_by_openai-0.1.1-py3-none-any.whl.metadata (9.0 kB)\n",
            "  Downloading clip_by_openai-0.1.0-py3-none-any.whl.metadata (9.0 kB)\n",
            "INFO: pip is still looking at multiple versions of clip-by-openai to determine which version is compatible with other requirements. This could take a while.\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.19.1-cp310-cp310-manylinux1_x86_64.whl.metadata (6.0 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.4.1-cp310-cp310-manylinux1_x86_64.whl.metadata (26 kB)\n",
            "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch)\n",
            "  Downloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch)\n",
            "  Downloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch)\n",
            "  Downloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch)\n",
            "  Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch)\n",
            "  Downloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch)\n",
            "  Downloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-curand-cu12==10.3.2.106 (from torch)\n",
            "  Downloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch)\n",
            "  Downloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch)\n",
            "  Downloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-nccl-cu12==2.20.5 (from torch)\n",
            "  Downloading nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n",
            "Collecting nvidia-nvtx-cu12==12.1.105 (from torch)\n",
            "  Downloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)\n",
            "Collecting triton==3.0.0 (from torch)\n",
            "  Downloading triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (1.3 kB)\n",
            "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch)\n",
            "  Downloading nvidia_nvjitlink_cu12-12.6.68-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "INFO: This is taking longer than usual. You might need to provide the dependency resolver with stricter constraints to reduce runtime. See https://pip.pypa.io/warnings/backtracking for guidance. If you want to abort this run, press Ctrl + C.\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.19.0-cp310-cp310-manylinux1_x86_64.whl.metadata (6.0 kB)\n",
            "  Downloading torchvision-0.18.1-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.3.1-cp310-cp310-manylinux1_x86_64.whl.metadata (26 kB)\n",
            "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch)\n",
            "  Downloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting triton==2.3.1 (from torch)\n",
            "  Downloading triton-2.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.18.0-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.3.0-cp310-cp310-manylinux1_x86_64.whl.metadata (26 kB)\n",
            "Collecting triton==2.3.0 (from torch)\n",
            "  Downloading triton-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.17.2-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.2.2-cp310-cp310-manylinux1_x86_64.whl.metadata (26 kB)\n",
            "Collecting nvidia-nccl-cu12==2.19.3 (from torch)\n",
            "  Downloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl.metadata (1.8 kB)\n",
            "Collecting triton==2.2.0 (from torch)\n",
            "  Downloading triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.17.1-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.2.1-cp310-cp310-manylinux1_x86_64.whl.metadata (26 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.17.0-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.2.0-cp310-cp310-manylinux1_x86_64.whl.metadata (25 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.16.2-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.1.2-cp310-cp310-manylinux1_x86_64.whl.metadata (25 kB)\n",
            "Collecting nvidia-nccl-cu12==2.18.1 (from torch)\n",
            "  Downloading nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl.metadata (1.8 kB)\n",
            "Collecting triton==2.1.0 (from torch)\n",
            "  Downloading triton-2.1.0-0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (1.3 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.16.1-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.1.1-cp310-cp310-manylinux1_x86_64.whl.metadata (25 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.16.0-cp310-cp310-manylinux1_x86_64.whl.metadata (6.6 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.1.0-cp310-cp310-manylinux1_x86_64.whl.metadata (25 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.15.2-cp310-cp310-manylinux1_x86_64.whl.metadata (11 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.0.1-cp310-cp310-manylinux1_x86_64.whl.metadata (24 kB)\n",
            "Collecting nvidia-cuda-nvrtc-cu11==11.7.99 (from torch)\n",
            "  Downloading nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-runtime-cu11==11.7.99 (from torch)\n",
            "  Downloading nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cuda-cupti-cu11==11.7.101 (from torch)\n",
            "  Downloading nvidia_cuda_cupti_cu11-11.7.101-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cudnn-cu11==8.5.0.96 (from torch)\n",
            "  Downloading nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cublas-cu11==11.10.3.66 (from torch)\n",
            "  Downloading nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cufft-cu11==10.9.0.58 (from torch)\n",
            "  Downloading nvidia_cufft_cu11-10.9.0.58-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-curand-cu11==10.2.10.91 (from torch)\n",
            "  Downloading nvidia_curand_cu11-10.2.10.91-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cusolver-cu11==11.4.0.1 (from torch)\n",
            "  Downloading nvidia_cusolver_cu11-11.4.0.1-2-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cusparse-cu11==11.7.4.91 (from torch)\n",
            "  Downloading nvidia_cusparse_cu11-11.7.4.91-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-nccl-cu11==2.14.3 (from torch)\n",
            "  Downloading nvidia_nccl_cu11-2.14.3-py3-none-manylinux1_x86_64.whl.metadata (1.8 kB)\n",
            "Collecting nvidia-nvtx-cu11==11.7.91 (from torch)\n",
            "  Downloading nvidia_nvtx_cu11-11.7.91-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)\n",
            "Collecting triton==2.0.0 (from torch)\n",
            "  Downloading triton-2.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (1.0 kB)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (71.0.4)\n",
            "Requirement already satisfied: wheel in /usr/local/lib/python3.10/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (0.44.0)\n",
            "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch) (3.30.3)\n",
            "Collecting lit (from triton==2.0.0->torch)\n",
            "  Downloading lit-18.1.8-py3-none-any.whl.metadata (2.5 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.15.1-cp310-cp310-manylinux1_x86_64.whl.metadata (11 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-2.0.0-cp310-cp310-manylinux1_x86_64.whl.metadata (24 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.14.1-cp310-cp310-manylinux1_x86_64.whl.metadata (11 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-1.13.1-cp310-cp310-manylinux1_x86_64.whl.metadata (24 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.14.0-cp310-cp310-manylinux1_x86_64.whl.metadata (11 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-1.13.0-cp310-cp310-manylinux1_x86_64.whl.metadata (23 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.13.1-cp310-cp310-manylinux1_x86_64.whl.metadata (10 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-1.12.1-cp310-cp310-manylinux1_x86_64.whl.metadata (22 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.13.0-cp310-cp310-manylinux1_x86_64.whl.metadata (10 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-1.12.0-cp310-cp310-manylinux1_x86_64.whl.metadata (22 kB)\n",
            "Collecting torchvision\n",
            "  Downloading torchvision-0.12.0-cp310-cp310-manylinux1_x86_64.whl.metadata (10 kB)\n",
            "Collecting torch\n",
            "  Downloading torch-1.11.0-cp310-cp310-manylinux1_x86_64.whl.metadata (24 kB)\n",
            "\u001b[31mERROR: Cannot install clip-by-openai==0.1.0, clip-by-openai==0.1.1, clip-by-openai==0.1.1.2, clip-by-openai==0.1.1.3, clip-by-openai==0.1.1.4, clip-by-openai==0.1.1.5, clip-by-openai==1.0.1, clip-by-openai==1.1, torch and torchvision==0.12.0 because these package versions have conflicting dependencies.\u001b[0m\u001b[31m\n",
            "\u001b[0m\n",
            "The conflict is caused by:\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 1.1 depends on torch<1.7.2 and >=1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 1.0.1 depends on torch<1.7.2 and >=1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 0.1.1.5 depends on torch==1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 0.1.1.4 depends on torch==1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 0.1.1.3 depends on torch==1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 0.1.1.2 depends on torch==1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 0.1.1 depends on torch==1.7.1\n",
            "    The user requested torch\n",
            "    torchvision 0.12.0 depends on torch==1.11.0\n",
            "    clip-by-openai 0.1.0 depends on torch==1.7.1\n",
            "\n",
            "To fix this you could try to:\n",
            "1. loosen the range of package versions you've specified\n",
            "2. remove package versions to allow pip to attempt to solve the dependency conflict\n",
            "\n",
            "\u001b[31mERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts\u001b[0m\u001b[31m\n",
            "\u001b[0mCollecting git+https://github.com/openai/CLIP.git\n",
            "  Cloning https://github.com/openai/CLIP.git to /tmp/pip-req-build-qht66d3t\n",
            "  Running command git clone --filter=blob:none --quiet https://github.com/openai/CLIP.git /tmp/pip-req-build-qht66d3t\n",
            "  Resolved https://github.com/openai/CLIP.git to commit dcba3cb2e2827b402d2701e7e1c7d9fed8a20ef1\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting ftfy (from clip==1.0)\n",
            "  Using cached ftfy-6.2.3-py3-none-any.whl.metadata (7.8 kB)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from clip==1.0) (24.1)\n",
            "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from clip==1.0) (2024.5.15)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from clip==1.0) (4.66.5)\n",
            "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from clip==1.0) (2.4.0+cu121)\n",
            "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from clip==1.0) (0.19.0+cu121)\n",
            "Requirement already satisfied: wcwidth<0.3.0,>=0.2.12 in /usr/local/lib/python3.10/dist-packages (from ftfy->clip==1.0) (0.2.13)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch->clip==1.0) (3.16.0)\n",
            "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch->clip==1.0) (4.12.2)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->clip==1.0) (1.13.2)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->clip==1.0) (3.3)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->clip==1.0) (3.1.4)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch->clip==1.0) (2024.6.1)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torchvision->clip==1.0) (1.26.4)\n",
            "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision->clip==1.0) (9.4.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->clip==1.0) (2.1.5)\n",
            "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->clip==1.0) (1.3.0)\n",
            "Downloading ftfy-6.2.3-py3-none-any.whl (43 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.0/43.0 kB\u001b[0m \u001b[31m1.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: clip\n",
            "  Building wheel for clip (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for clip: filename=clip-1.0-py3-none-any.whl size=1369490 sha256=20a0035d3faa598f0771bc5120fb14cf7ca6c480af8eb54ab658fe8133d99704\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-zezn1icx/wheels/da/2b/4c/d6691fa9597aac8bb85d2ac13b112deb897d5b50f5ad9a37e4\n",
            "Successfully built clip\n",
            "Installing collected packages: ftfy, clip\n",
            "Successfully installed clip-1.0 ftfy-6.2.3\n",
            "Collecting openai==0.28\n",
            "  Downloading openai-0.28.0-py3-none-any.whl.metadata (13 kB)\n",
            "Requirement already satisfied: requests>=2.20 in /usr/local/lib/python3.10/dist-packages (from openai==0.28) (2.32.3)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from openai==0.28) (4.66.5)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from openai==0.28) (3.10.5)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai==0.28) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai==0.28) (3.8)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai==0.28) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20->openai==0.28) (2024.8.30)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (2.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (24.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (6.1.0)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (1.11.1)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->openai==0.28) (4.0.3)\n",
            "Requirement already satisfied: typing-extensions>=4.1.0 in /usr/local/lib/python3.10/dist-packages (from multidict<7.0,>=4.5->aiohttp->openai==0.28) (4.12.2)\n",
            "Downloading openai-0.28.0-py3-none-any.whl (76 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.5/76.5 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: openai\n",
            "Successfully installed openai-0.28.0\n"
          ]
        }
      ],
      "source": [
        "!pip install flask-ngrok openai torch torchvision pillow clip-by-openai\n",
        "!pip install git+https://github.com/openai/CLIP.git\n",
        "!pip install openai==0.28\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!git clone --recursive https://huggingface.co/spaces/hysts/ControlNet-v1-1\n",
        "%cd ControlNet-v1-1\n",
        "%pip install -q -r requirements.txt"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "D1pek6ju9ADb",
        "outputId": "307cffc0-ebe5-4301-be48-056fca013c08"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'ControlNet-v1-1'...\n",
            "remote: Enumerating objects: 277, done.\u001b[K\n",
            "remote: Counting objects: 100% (20/20), done.\u001b[K\n",
            "remote: Compressing objects: 100% (12/12), done.\u001b[K\n",
            "remote: Total 277 (delta 12), reused 8 (delta 8), pack-reused 257 (from 1)\u001b[K\n",
            "Receiving objects: 100% (277/277), 55.62 KiB | 11.12 MiB/s, done.\n",
            "Resolving deltas: 100% (194/194), done.\n",
            "/content/ControlNet-v1-1\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m113.6/113.6 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.4/42.4 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.4/50.4 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h\u001b[33mWARNING: The candidate selected for download or install is a yanked version: 'opencv-python-headless' candidate (version 4.8.0.74 at https://files.pythonhosted.org/packages/76/02/f128517f3ade4bb5f71e2afd8461dba70e3f466ce745fa1fd1fade9ad1b7/opencv_python_headless-4.8.0.74-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (from https://pypi.org/simple/opencv-python-headless/) (requires-python:>=3.6))\n",
            "Reason for being yanked: deprecated, use 4.8.0.76\u001b[0m\u001b[33m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.2/244.2 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m261.9/261.9 kB\u001b[0m \u001b[31m12.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m33.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.2/42.2 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.2/20.2 MB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m16.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.8/33.8 MB\u001b[0m \u001b[31m14.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.1/49.1 MB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m37.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m619.9/619.9 MB\u001b[0m \u001b[31m1.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.0/6.0 MB\u001b[0m \u001b[31m80.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.2/7.2 MB\u001b[0m \u001b[31m64.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m109.1/109.1 MB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m298.4/298.4 kB\u001b[0m \u001b[31m18.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m317.1/317.1 MB\u001b[0m \u001b[31m1.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.8/11.8 MB\u001b[0m \u001b[31m63.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.0/21.0 MB\u001b[0m \u001b[31m50.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m849.3/849.3 kB\u001b[0m \u001b[31m34.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m557.1/557.1 MB\u001b[0m \u001b[31m768.8 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m168.4/168.4 MB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.6/54.6 MB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m102.6/102.6 MB\u001b[0m \u001b[31m9.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m173.2/173.2 MB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m177.1/177.1 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.6/98.6 kB\u001b[0m \u001b[31m7.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m63.3/63.3 MB\u001b[0m \u001b[31m12.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.9/141.9 kB\u001b[0m \u001b[31m10.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m91.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.8/62.8 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.0/94.0 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.4/76.4 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m64.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.4/71.4 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m96.4/96.4 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "albucore 0.0.14 requires opencv-python-headless>=4.9.0.80, but you have opencv-python-headless 4.8.0.74 which is incompatible.\n",
            "albumentations 1.4.14 requires opencv-python-headless>=4.9.0.80, but you have opencv-python-headless 4.8.0.74 which is incompatible.\n",
            "torchaudio 2.4.0+cu121 requires torch==2.4.0, but you have torch 2.0.1 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0m"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from flask import Flask, request, jsonify\n",
        "import openai\n",
        "import clip\n",
        "from PIL import Image\n",
        "import torch\n",
        "import requests\n",
        "from io import BytesIO\n",
        "\n",
        "# Initialize Flask app\n",
        "app = Flask(__name__)\n",
        "\n",
        "# OpenAI API key setup\n",
        "openai.api_key = \"sk-proj-vtucyOlCS-i2HoJrXtiFmmB-AAEk\"\n",
        "\n",
        "# CLIP model setup\n",
        "device = \"cpu\"\n",
        "model, preprocess = clip.load(\"ViT-B/32\", device=device)\n",
        "\n",
        "@app.route('/generate-augmented-image', methods=['POST'])\n",
        "def generate_augmented_image():\n",
        "    data = request.json\n",
        "    image_url = data.get(\"imageUrl\")\n",
        "\n",
        "    # Download the image from the provided URL with User-Agent header\n",
        "    headers = {\n",
        "        \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36\"\n",
        "    }\n",
        "    try:\n",
        "        response = requests.get(image_url, headers=headers)\n",
        "        response.raise_for_status()  # Check for HTTP errors\n",
        "    except requests.exceptions.RequestException as e:\n",
        "        return jsonify({\"error\": f\"Failed to download image: {str(e)}\"}), 400\n",
        "\n",
        "    # Check if the response is an image\n",
        "    if 'image' not in response.headers['Content-Type']:\n",
        "        return jsonify({\"error\": \"URL does not point to a valid image\"}), 400\n",
        "\n",
        "    try:\n",
        "        img = Image.open(BytesIO(response.content))\n",
        "    except Exception as e:\n",
        "        return jsonify({\"error\": f\"Failed to open image: {str(e)}\"}), 400\n",
        "\n",
        "    image_tensor = preprocess(img).unsqueeze(0).to(device)\n",
        "\n",
        "    # Tree descriptor: Describes the number of trees in the image\n",
        "    tree_descriptor = [\n",
        "        \"The area is barren with no trees around.\",\n",
        "        \"There are a few scattered trees in the area.\",\n",
        "        \"The area has many trees, providing shade and greenery.\",\n",
        "        \"The area is densely filled with trees, looking like a forest.\"\n",
        "    ]\n",
        "\n",
        "    # Two-story house descriptor: Describes the number of two-story houses\n",
        "    house_descriptor = [\n",
        "        \"There are no small two-story houses visible.\",\n",
        "        \"There are one or two small two-story houses visible.\",\n",
        "        \"There are several two-story houses scattered around.\",\n",
        "        \"The area is filled with many two-story houses.\"\n",
        "    ]\n",
        "\n",
        "    # Tall buildings/skyscrapers descriptor: Describes the number of tall buildings\n",
        "    skyscraper_descriptor = [\n",
        "        \"There are no tall buildings or skyscrapers visible.\",\n",
        "        \"There are a few skyscrapers in the background.\",\n",
        "        \"The area has several tall buildings dominating the skyline.\",\n",
        "        \"The area is full of tall buildings and skyscrapers.\"\n",
        "    ]\n",
        "\n",
        "    # Empty space descriptor: Describes the presence of empty lawns, sidewalks, or open areas\n",
        "    empty_space_descriptor = [\n",
        "        \"There are no sidewalks or open areas visible.\",\n",
        "        \"There are some sidewalks but not much empty space.\",\n",
        "        \"The area has visible sidewalks and open spaces for walking.\",\n",
        "        \"The area has large sidewalks and expansive empty spaces.\"\n",
        "    ]\n",
        "\n",
        "    # Tokenize the text prompts\n",
        "    tree_text = clip.tokenize(tree_descriptor).to(device)\n",
        "    house_text = clip.tokenize(house_descriptor).to(device)\n",
        "    skyscraper_text = clip.tokenize(skyscraper_descriptor).to(device)\n",
        "    empty_space_text = clip.tokenize(empty_space_descriptor).to(device)\n",
        "\n",
        "    # Process with CLIP to find the best descriptors\n",
        "    with torch.no_grad():\n",
        "        image_features = model.encode_image(image_tensor)\n",
        "\n",
        "        # Compute similarity scores for each descriptor\n",
        "        tree_features = model.encode_text(tree_text)\n",
        "        house_features = model.encode_text(house_text)\n",
        "        skyscraper_features = model.encode_text(skyscraper_text)\n",
        "        empty_space_features = model.encode_text(empty_space_text)\n",
        "\n",
        "        tree_similarity = torch.cosine_similarity(image_features, tree_features).cpu().numpy()\n",
        "        house_similarity = torch.cosine_similarity(image_features, house_features).cpu().numpy()\n",
        "        skyscraper_similarity = torch.cosine_similarity(image_features, skyscraper_features).cpu().numpy()\n",
        "        empty_space_similarity = torch.cosine_similarity(image_features, empty_space_features).cpu().numpy()\n",
        "\n",
        "    # Determine the most relevant descriptors\n",
        "    tree_score = len(tree_descriptor) - list(tree_similarity).index(max(tree_similarity))\n",
        "    house_score = len(house_descriptor) - list(house_similarity).index(max(house_similarity))\n",
        "    skyscraper_score = len(skyscraper_descriptor) - list(skyscraper_similarity).index(max(skyscraper_similarity))\n",
        "    empty_space_score = len(empty_space_descriptor) - list(empty_space_similarity).index(max(empty_space_similarity))\n",
        "\n",
        "    # Assign one or two descriptors based on similarity scores\n",
        "    descriptors = [\n",
        "        tree_descriptor[tree_score],\n",
        "        skyscraper_descriptor[skyscraper_score] if skyscraper_similarity[skyscraper_score] > house_similarity[house_score] else house_descriptor[house_score]\n",
        "    ]\n",
        "\n",
        "    # Use OpenAI Image API (DALL-E) to generate the augmented image\n",
        "    response = openai.Image.create(\n",
        "        prompt=f\"Generate a realistic render of {image_url}. {descriptors[0]} {descriptors[1]}. Add more trees and greenery if there are mpty spaces or sidewalks.\",\n",
        "        n=1,\n",
        "        size=\"512x512\"\n",
        "    )\n",
        "\n",
        "    return jsonify({\"generatedImageUrl\": response['data'][0]['url']})"
      ],
      "metadata": {
        "id": "tTR7ZJnCdmrn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install diffusers"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mLfgZq__3gcD",
        "outputId": "2a5532fc-6994-4cf2-db51-aeb64be75c34"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting diffusers\n",
            "  Downloading diffusers-0.30.2-py3-none-any.whl.metadata (18 kB)\n",
            "Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.10/dist-packages (from diffusers) (8.5.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from diffusers) (3.16.0)\n",
            "Requirement already satisfied: huggingface-hub>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from diffusers) (0.24.6)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from diffusers) (1.26.4)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from diffusers) (2024.5.15)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from diffusers) (2.32.3)\n",
            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from diffusers) (0.4.5)\n",
            "Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from diffusers) (9.4.0)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.23.2->diffusers) (2024.6.1)\n",
            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.23.2->diffusers) (24.1)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.23.2->diffusers) (6.0.2)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.23.2->diffusers) (4.66.5)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.23.2->diffusers) (4.12.2)\n",
            "Requirement already satisfied: zipp>=3.20 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata->diffusers) (3.20.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->diffusers) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->diffusers) (3.8)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->diffusers) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->diffusers) (2024.8.30)\n",
            "Downloading diffusers-0.30.2-py3-none-any.whl (2.6 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.6/2.6 MB\u001b[0m \u001b[31m33.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: diffusers\n",
            "Successfully installed diffusers-0.30.2\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from threading import Thread\n",
        "def run_app():\n",
        "    app.run(host='0.0.0.0', port=5005)\n",
        "\n",
        "# Start the Flask app in the background\n",
        "Thread(target=run_app).start()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wLzfE8xu4zEA",
        "outputId": "7d17f800-7196-42c4-9a9f-6274c0ea543b"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            " * Serving Flask app '__main__'\n",
            " * Debug mode: off\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "INFO:werkzeug:\u001b[31m\u001b[1mWARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.\u001b[0m\n",
            " * Running on all addresses (0.0.0.0)\n",
            " * Running on http://127.0.0.1:5005\n",
            " * Running on http://172.28.0.12:5005\n",
            "INFO:werkzeug:\u001b[33mPress CTRL+C to quit\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import requests\n",
        "\n",
        "# Use a valid image URL (direct link to an image file)\n",
        "image_url = \"https://kickinthecreatives.com/wp-content/uploads/2020/04/streetview-building-draw.jpg\"\n",
        "\n",
        "# Make a request to the API\n",
        "response = requests.post(\"http://127.0.0.1:5005/generate-augmented-image\", json={\"imageUrl\": image_url})\n",
        "\n",
        "# Output the result\n",
        "if response.status_code == 200:\n",
        "    augmented_image_url = response.json().get(\"generatedImageUrl\")\n",
        "    print(\"Generated Image URL:\", augmented_image_url)\n",
        "else:\n",
        "    print(f\"Error: {response.json()['error']}\")\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2F4SyKec2PYg",
        "outputId": "e73f76a1-68b0-4d61-8c24-79db12eb095f"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "INFO:werkzeug:127.0.0.1 - - [15/Sep/2024 03:56:49] \"POST /generate-augmented-image HTTP/1.1\" 200 -\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Generated Image URL: https://oaidalleapiprodscus.blob.core.windows.net/private/org-RBQ2Q8CEZiw1McLBsr4laXXi/user-mCX9NdmXBpTNWiuKlgQ1fxOS/img-1Z4HU5PmY0kLtfjgrsgJucri.png?st=2024-09-15T02%3A56%3A48Z&se=2024-09-15T04%3A56%3A48Z&sp=r&sv=2024-08-04&sr=b&rscd=inline&rsct=image/png&skoid=d505667d-d6c1-4a0a-bac7-5c84a87759f8&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skt=2024-09-14T23%3A21%3A02Z&ske=2024-09-15T23%3A21%3A02Z&sks=b&skv=2024-08-04&sig=TsQ%2BwIFap1XccIq9d6c3dm5UmIJfbIoMJ7JD2cUDzh8%3D\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "o6ZOpvXn2PnZ"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}