““ENGR2900_Final_Project_V3.ipynb”的副本”的副本

{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "Installing the project requirements"
      ],
      "metadata": {
        "id": "0IFRGG2-XB3K"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "Z31WvdiTgo-n",
        "outputId": "9d10c2f9-b53c-4b2a-8bb2-ebccf2cedfa2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting accelerate\n",
            "  Downloading accelerate-0.30.1-py3-none-any.whl (302 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.6/302.6 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.40.2)\n",
            "Requirement already satisfied: safetensors in /usr/local/lib/python3.10/dist-packages (0.4.3)\n",
            "Requirement already satisfied: opencv-python in /usr/local/lib/python3.10/dist-packages (4.8.0.76)\n",
            "Collecting diffusers\n",
            "  Downloading diffusers-0.27.2-py3-none-any.whl (2.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m13.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting controlnet_aux\n",
            "  Downloading controlnet_aux-0.0.8-py3-none-any.whl (274 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m274.6/274.6 kB\u001b[0m \u001b[31m17.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting mediapipe\n",
            "  Downloading mediapipe-0.10.14-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (35.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m35.7/35.7 MB\u001b[0m \u001b[31m13.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.25.2)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (24.0)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate) (6.0.1)\n",
            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.2.1+cu121)\n",
            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.20.3)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.14.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n",
            "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.1)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.4)\n",
            "Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.10/dist-packages (from diffusers) (7.1.0)\n",
            "Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from diffusers) (9.4.0)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from controlnet_aux) (1.11.4)\n",
            "Requirement already satisfied: opencv-python-headless in /usr/local/lib/python3.10/dist-packages (from controlnet_aux) (4.9.0.80)\n",
            "Collecting einops (from controlnet_aux)\n",
            "  Downloading einops-0.8.0-py3-none-any.whl (43 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.2/43.2 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from controlnet_aux) (0.17.1+cu121)\n",
            "Collecting timm<=0.6.7 (from controlnet_aux)\n",
            "  Downloading timm-0.6.7-py3-none-any.whl (509 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m510.0/510.0 kB\u001b[0m \u001b[31m34.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: scikit-image in /usr/local/lib/python3.10/dist-packages (from controlnet_aux) (0.19.3)\n",
            "Requirement already satisfied: absl-py in /usr/local/lib/python3.10/dist-packages (from mediapipe) (1.4.0)\n",
            "Requirement already satisfied: attrs>=19.1.0 in /usr/local/lib/python3.10/dist-packages (from mediapipe) (23.2.0)\n",
            "Requirement already satisfied: flatbuffers>=2.0 in /usr/local/lib/python3.10/dist-packages (from mediapipe) (24.3.25)\n",
            "Requirement already satisfied: jax in /usr/local/lib/python3.10/dist-packages (from mediapipe) (0.4.26)\n",
            "Requirement already satisfied: jaxlib in /usr/local/lib/python3.10/dist-packages (from mediapipe) (0.4.26+cuda12.cudnn89)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from mediapipe) (3.7.1)\n",
            "Requirement already satisfied: opencv-contrib-python in /usr/local/lib/python3.10/dist-packages (from mediapipe) (4.8.0.76)\n",
            "Collecting protobuf<5,>=4.25.3 (from mediapipe)\n",
            "  Downloading protobuf-4.25.3-cp37-abi3-manylinux2014_x86_64.whl (294 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m294.6/294.6 kB\u001b[0m \u001b[31m16.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting sounddevice>=0.4.4 (from mediapipe)\n",
            "  Downloading sounddevice-0.4.6-py3-none-any.whl (31 kB)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2023.6.0)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (4.11.0)\n",
            "Requirement already satisfied: CFFI>=1.0 in /usr/local/lib/python3.10/dist-packages (from sounddevice>=0.4.4->mediapipe) (1.16.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.3)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.4)\n",
            "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
            "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
            "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
            "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
            "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
            "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
            "Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
            "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
            "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
            "Collecting nvidia-nccl-cu12==2.19.3 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n",
            "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
            "Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.2.0)\n",
            "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate)\n",
            "  Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata->diffusers) (3.18.1)\n",
            "Requirement already satisfied: ml-dtypes>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from jax->mediapipe) (0.2.0)\n",
            "Requirement already satisfied: opt-einsum in /usr/local/lib/python3.10/dist-packages (from jax->mediapipe) (3.3.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->mediapipe) (1.2.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->mediapipe) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->mediapipe) (4.51.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->mediapipe) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->mediapipe) (3.1.2)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib->mediapipe) (2.8.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n",
            "Requirement already satisfied: imageio>=2.4.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->controlnet_aux) (2.31.6)\n",
            "Requirement already satisfied: tifffile>=2019.7.26 in /usr/local/lib/python3.10/dist-packages (from scikit-image->controlnet_aux) (2024.5.10)\n",
            "Requirement already satisfied: PyWavelets>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->controlnet_aux) (1.6.0)\n",
            "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from CFFI>=1.0->sounddevice>=0.4.4->mediapipe) (2.22)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib->mediapipe) (1.16.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.5)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n",
            "Installing collected packages: protobuf, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, einops, sounddevice, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, mediapipe, diffusers, accelerate, timm, controlnet_aux\n",
            "  Attempting uninstall: protobuf\n",
            "    Found existing installation: protobuf 3.20.3\n",
            "    Uninstalling protobuf-3.20.3:\n",
            "      Successfully uninstalled protobuf-3.20.3\n",
            "\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",
            "tensorflow-metadata 1.15.0 requires protobuf<4.21,>=3.20.3; python_version < \"3.11\", but you have protobuf 4.25.3 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed accelerate-0.30.1 controlnet_aux-0.0.8 diffusers-0.27.2 einops-0.8.0 mediapipe-0.10.14 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 protobuf-4.25.3 sounddevice-0.4.6 timm-0.6.7\n",
            "Collecting openai\n",
            "  Downloading openai-1.30.1-py3-none-any.whl (320 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m320.6/320.6 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement 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-0.27.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m10.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic<3,>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from openai) (2.7.1)\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) (4.66.4)\n",
            "Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai) (4.11.0)\n",
            "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (3.7)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (1.2.1)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2024.2.2)\n",
            "Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai)\n",
            "  Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m407.4 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting h11<0.15,>=0.13 (from httpcore==1.*->httpx<1,>=0.23.0->openai)\n",
            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m8.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1.9.0->openai) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.2 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=1.9.0->openai) (2.18.2)\n",
            "Installing collected packages: h11, httpcore, httpx, openai\n",
            "Successfully installed h11-0.14.0 httpcore-1.0.5 httpx-0.27.0 openai-1.30.1\n",
            "Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cpu\n",
            "Collecting carvekit\n",
            "  Downloading carvekit-4.1.2-py3-none-any.whl (76 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.1/76.1 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: requests>=2.31.0 in /usr/local/lib/python3.10/dist-packages (from carvekit) (2.31.0)\n",
            "Collecting torch>=2.2.2 (from carvekit)\n",
            "  Downloading https://download.pytorch.org/whl/cpu/torch-2.3.0%2Bcpu-cp310-cp310-linux_x86_64.whl (190.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.4/190.4 MB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting Pillow>=10.3.0 (from carvekit)\n",
            "  Downloading pillow-10.3.0-cp310-cp310-manylinux_2_28_x86_64.whl (4.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.5/4.5 MB\u001b[0m \u001b[31m18.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting typing>=3.7.4.3 (from carvekit)\n",
            "  Downloading typing-3.7.4.3.tar.gz (78 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.6/78.6 kB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting torchvision>=0.17.2 (from carvekit)\n",
            "  Downloading https://download.pytorch.org/whl/cpu/torchvision-0.18.0%2Bcpu-cp310-cp310-linux_x86_64.whl (1.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m77.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting opencv-python>=4.9.0.80 (from carvekit)\n",
            "  Downloading opencv_python-4.9.0.80-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (62.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.2/62.2 MB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting numpy>=1.26.4 (from carvekit)\n",
            "  Downloading numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m81.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting loguru>=0.7.2 (from carvekit)\n",
            "  Downloading loguru-0.7.2-py3-none-any.whl (62 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.5/62.5 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting uvicorn>=0.29.0 (from carvekit)\n",
            "  Downloading uvicorn-0.29.0-py3-none-any.whl (60 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m9.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting fastapi>=0.110.1 (from carvekit)\n",
            "  Downloading fastapi-0.111.0-py3-none-any.whl (91 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m14.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic>=2.6.4 in /usr/local/lib/python3.10/dist-packages (from carvekit) (2.7.1)\n",
            "Requirement already satisfied: click>=8.1.7 in /usr/local/lib/python3.10/dist-packages (from carvekit) (8.1.7)\n",
            "Requirement already satisfied: tqdm>=4.66.2 in /usr/local/lib/python3.10/dist-packages (from carvekit) (4.66.4)\n",
            "Collecting setuptools>=69.2.0 (from carvekit)\n",
            "  Using cached setuptools-69.5.1-py3-none-any.whl (894 kB)\n",
            "Collecting aiofiles>=23.2.1 (from carvekit)\n",
            "  Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
            "Collecting python-multipart>=0.0.9 (from carvekit)\n",
            "  Downloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
            "Collecting starlette<0.38.0,>=0.37.2 (from fastapi>=0.110.1->carvekit)\n",
            "  Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from fastapi>=0.110.1->carvekit) (4.11.0)\n",
            "Collecting fastapi-cli>=0.0.2 (from fastapi>=0.110.1->carvekit)\n",
            "  Downloading fastapi_cli-0.0.4-py3-none-any.whl (9.5 kB)\n",
            "Requirement already satisfied: httpx>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from fastapi>=0.110.1->carvekit) (0.27.0)\n",
            "Requirement already satisfied: jinja2>=2.11.2 in /usr/local/lib/python3.10/dist-packages (from fastapi>=0.110.1->carvekit) (3.1.4)\n",
            "Collecting ujson!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,>=4.0.1 (from fastapi>=0.110.1->carvekit)\n",
            "  Downloading ujson-5.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (53 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.6/53.6 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting orjson>=3.2.1 (from fastapi>=0.110.1->carvekit)\n",
            "  Downloading orjson-3.10.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (142 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m142.5/142.5 kB\u001b[0m \u001b[31m20.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting email_validator>=2.0.0 (from fastapi>=0.110.1->carvekit)\n",
            "  Downloading email_validator-2.1.1-py3-none-any.whl (30 kB)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.6.4->carvekit) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.2 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.6.4->carvekit) (2.18.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->carvekit) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->carvekit) (3.7)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->carvekit) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->carvekit) (2024.2.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=2.2.2->carvekit) (3.14.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=2.2.2->carvekit) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=2.2.2->carvekit) (3.3)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=2.2.2->carvekit) (2023.6.0)\n",
            "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.29.0->carvekit) (0.14.0)\n",
            "Collecting dnspython>=2.0.0 (from email_validator>=2.0.0->fastapi>=0.110.1->carvekit)\n",
            "  Downloading dnspython-2.6.1-py3-none-any.whl (307 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m307.7/307.7 kB\u001b[0m \u001b[31m40.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting typer>=0.12.3 (from fastapi-cli>=0.0.2->fastapi>=0.110.1->carvekit)\n",
            "  Downloading typer-0.12.3-py3-none-any.whl (47 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m47.2/47.2 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.23.0->fastapi>=0.110.1->carvekit) (3.7.1)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx>=0.23.0->fastapi>=0.110.1->carvekit) (1.0.5)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.23.0->fastapi>=0.110.1->carvekit) (1.3.1)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2>=2.11.2->fastapi>=0.110.1->carvekit) (2.1.5)\n",
            "Collecting httptools>=0.5.0 (from uvicorn>=0.29.0->carvekit)\n",
            "  Downloading httptools-0.6.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (341 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m43.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting python-dotenv>=0.13 (from uvicorn>=0.29.0->carvekit)\n",
            "  Downloading python_dotenv-1.0.1-py3-none-any.whl (19 kB)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.29.0->carvekit) (6.0.1)\n",
            "Collecting uvloop!=0.15.0,!=0.15.1,>=0.14.0 (from uvicorn>=0.29.0->carvekit)\n",
            "  Downloading uvloop-0.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m103.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting watchfiles>=0.13 (from uvicorn>=0.29.0->carvekit)\n",
            "  Downloading watchfiles-0.21.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m82.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting websockets>=10.4 (from uvicorn>=0.29.0->carvekit)\n",
            "  Downloading websockets-12.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=2.2.2->carvekit) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx>=0.23.0->fastapi>=0.110.1->carvekit) (1.2.1)\n",
            "Collecting shellingham>=1.3.0 (from typer>=0.12.3->fastapi-cli>=0.0.2->fastapi>=0.110.1->carvekit)\n",
            "  Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n",
            "Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer>=0.12.3->fastapi-cli>=0.0.2->fastapi>=0.110.1->carvekit) (13.7.1)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer>=0.12.3->fastapi-cli>=0.0.2->fastapi>=0.110.1->carvekit) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer>=0.12.3->fastapi-cli>=0.0.2->fastapi>=0.110.1->carvekit) (2.16.1)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer>=0.12.3->fastapi-cli>=0.0.2->fastapi>=0.110.1->carvekit) (0.1.2)\n",
            "Building wheels for collected packages: typing\n",
            "  Building wheel for typing (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for typing: filename=typing-3.7.4.3-py3-none-any.whl size=26306 sha256=f659f6b59d342b6222332faf8937e08a59cb13eb82f4fc583bf94d4c6317f0dc\n",
            "  Stored in directory: /root/.cache/pip/wheels/7c/d0/9e/1f26ebb66d9e1732e4098bc5a6c2d91f6c9a529838f0284890\n",
            "Successfully built typing\n",
            "Installing collected packages: websockets, uvloop, uvicorn, ujson, typing, shellingham, setuptools, python-multipart, python-dotenv, Pillow, orjson, numpy, loguru, httptools, dnspython, aiofiles, watchfiles, torch, starlette, opencv-python, email_validator, typer, torchvision, fastapi-cli, fastapi, carvekit\n",
            "  Attempting uninstall: setuptools\n",
            "    Found existing installation: setuptools 67.7.2\n",
            "    Uninstalling setuptools-67.7.2:\n",
            "      Successfully uninstalled setuptools-67.7.2\n",
            "  Attempting uninstall: Pillow\n",
            "    Found existing installation: Pillow 9.4.0\n",
            "    Uninstalling Pillow-9.4.0:\n",
            "      Successfully uninstalled Pillow-9.4.0\n",
            "  Attempting uninstall: numpy\n",
            "    Found existing installation: numpy 1.25.2\n",
            "    Uninstalling numpy-1.25.2:\n",
            "      Successfully uninstalled numpy-1.25.2\n",
            "  Attempting uninstall: torch\n",
            "    Found existing installation: torch 2.2.1+cu121\n",
            "    Uninstalling torch-2.2.1+cu121:\n",
            "      Successfully uninstalled torch-2.2.1+cu121\n",
            "  Attempting uninstall: opencv-python\n",
            "    Found existing installation: opencv-python 4.8.0.76\n",
            "    Uninstalling opencv-python-4.8.0.76:\n",
            "      Successfully uninstalled opencv-python-4.8.0.76\n",
            "  Attempting uninstall: typer\n",
            "    Found existing installation: typer 0.9.4\n",
            "    Uninstalling typer-0.9.4:\n",
            "      Successfully uninstalled typer-0.9.4\n",
            "  Attempting uninstall: torchvision\n",
            "    Found existing installation: torchvision 0.17.1+cu121\n",
            "    Uninstalling torchvision-0.17.1+cu121:\n",
            "      Successfully uninstalled torchvision-0.17.1+cu121\n",
            "\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",
            "ipython 7.34.0 requires jedi>=0.16, which is not installed.\n",
            "imageio 2.31.6 requires pillow<10.1.0,>=8.3.2, but you have pillow 10.3.0 which is incompatible.\n",
            "spacy 3.7.4 requires typer<0.10.0,>=0.3.0, but you have typer 0.12.3 which is incompatible.\n",
            "torchaudio 2.2.1+cu121 requires torch==2.2.1, but you have torch 2.3.0+cpu which is incompatible.\n",
            "torchtext 0.17.1 requires torch==2.2.1, but you have torch 2.3.0+cpu which is incompatible.\n",
            "weasel 0.3.4 requires typer<0.10.0,>=0.3.0, but you have typer 0.12.3 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed Pillow-10.3.0 aiofiles-23.2.1 carvekit-4.1.2 dnspython-2.6.1 email_validator-2.1.1 fastapi-0.111.0 fastapi-cli-0.0.4 httptools-0.6.1 loguru-0.7.2 numpy-1.26.4 opencv-python-4.9.0.80 orjson-3.10.3 python-dotenv-1.0.1 python-multipart-0.0.9 setuptools-69.5.1 shellingham-1.5.4 starlette-0.37.2 torch-2.3.0+cpu torchvision-0.18.0+cpu typer-0.12.3 typing-3.7.4.3 ujson-5.10.0 uvicorn-0.29.0 uvloop-0.19.0 watchfiles-0.21.0 websockets-12.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "PIL",
                  "_distutils_hack",
                  "pkg_resources",
                  "setuptools",
                  "typing"
                ]
              },
              "id": "29888309a7954d87a09bec43bef82655"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "!pip install accelerate transformers safetensors opencv-python diffusers controlnet_aux mediapipe\n",
        "!pip install openai\n",
        "!pip install carvekit --extra-index-url https://download.pytorch.org/whl/cpu\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Connecting to GPT-Vision w/API Key"
      ],
      "metadata": {
        "id": "dVZc1MpZXGv0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from openai import OpenAI\n",
        "\n",
        "client = OpenAI(api_key=\"sk-proj-0cD3oLBfTMTsUGnvkwNyT3BlbkFJKC4h3kc1hAwukFVC3JkQ\")\n"
      ],
      "metadata": {
        "id": "WGuBiWQyWh31"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from IPython.display import display, Image\n",
        "\n",
        "image1_url = \"https://ca-times.brightspotcdn.com/dims4/default/99f1c3a/2147483647/strip/true/crop/2000x1405+0+0/resize/1200x843!/format/webp/quality/75/?url=https%3A%2F%2Fcalifornia-times-brightspot.s3.amazonaws.com%2Fc9%2Fa9%2F68435d41cf690e0c019e87278361%2F1f764b198a42470189b99b4084be6cf0\"\n",
        "\n",
        "# Display Image\n",
        "display(Image(url=image1_url))\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 864
        },
        "id": "_nDu-LYDWlI4",
        "outputId": "78f82097-aab3-41bc-c972-7ce53ff618cd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<img src=\"https://ca-times.brightspotcdn.com/dims4/default/99f1c3a/2147483647/strip/true/crop/2000x1405+0+0/resize/1200x843!/format/webp/quality/75/?url=https%3A%2F%2Fcalifornia-times-brightspot.s3.amazonaws.com%2Fc9%2Fa9%2F68435d41cf690e0c019e87278361%2F1f764b198a42470189b99b4084be6cf0\"/>"
            ],
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import PIL.Image\n",
        "import requests\n",
        "from PIL import Image\n",
        "from io import BytesIO\n",
        "from carvekit.api.interface import Interface\n",
        "from carvekit.ml.wrap.fba_matting import FBAMatting\n",
        "from carvekit.ml.wrap.tracer_b7 import TracerUniversalB7\n",
        "from carvekit.pipelines.postprocessing import MattingMethod\n",
        "from carvekit.pipelines.preprocessing import PreprocessingStub\n",
        "from carvekit.trimap.generator import TrimapGenerator\n",
        "\n",
        "# Check doc strings for more information\n",
        "seg_net = TracerUniversalB7(device='cpu',\n",
        "              batch_size=1)\n",
        "\n",
        "fba = FBAMatting(device='cpu',\n",
        "                 input_tensor_size=2048,\n",
        "                 batch_size=1)\n",
        "\n",
        "trimap = TrimapGenerator()\n",
        "\n",
        "preprocessing = PreprocessingStub()\n",
        "\n",
        "postprocessing = MattingMethod(matting_module=fba,\n",
        "                               trimap_generator=trimap,\n",
        "                               device='cpu')\n",
        "\n",
        "interface = Interface(pre_pipe=preprocessing,\n",
        "                      post_pipe=postprocessing,\n",
        "                      seg_pipe=seg_net)\n",
        "\n",
        "# 图片的URL\n",
        "url = 'https://i.ibb.co/vQjy8qC/2024-05-21-090635.png'\n",
        "\n",
        "response = requests.get(url)\n",
        "response.raise_for_status()  # 检查请求是否成功\n",
        "\n",
        "image = Image.open(BytesIO(response.content))\n",
        "\n",
        "\n",
        "cat_wo_bg = interface([image])[0]\n",
        "cat_wo_bg.save('2.png')\n"
      ],
      "metadata": {
        "id": "f3dkr15i459W"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "file_path = '/content/2.png'\n",
        "image = Image.open(file_path)\n",
        "display(image)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 378
        },
        "id": "lKULvdk82sYK",
        "outputId": "121479af-62b7-4980-c365-9206dd3dae35"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.PngImagePlugin.PngImageFile image mode=RGBA size=640x361>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from openai import OpenAI\n",
        "\n",
        "client = OpenAI(api_key=\"sk-proj-0cD3oLBfTMTsUGnvkwNyT3BlbkFJKC4h3kc1hAwukFVC3JkQ\")\n"
      ],
      "metadata": {
        "id": "0utULX-psoiy"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import requests\n",
        "\n",
        "def upload_image_to_imgbb(image_path, api_key):\n",
        "    with open(image_path, 'rb') as file:\n",
        "        response = requests.post(\n",
        "            'https://api.imgbb.com/1/upload',\n",
        "            data={'key': api_key},\n",
        "            files={'image': file}\n",
        "        )\n",
        "    return response.json()['data']['url']\n",
        "\n",
        "api_key = 'c18450c786749500447fe5fc6f072418'\n",
        "image_path = '/content/2.png'\n",
        "\n",
        "url = upload_image_to_imgbb(image_path, api_key)\n",
        "print('Image URL:', url)\n",
        "from IPython.display import display, Image\n",
        "\n",
        "image1_url = url\n",
        "\n",
        "# Display Image\n",
        "display(Image(url=image1_url))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 399
        },
        "id": "oPvv-1UbuPQ4",
        "outputId": "baebbbf3-b7d3-4447-897a-965f560c1f6e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Image URL: https://i.ibb.co/QvT3Shp/2.png\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<img src=\"https://i.ibb.co/QvT3Shp/2.png\"/>"
            ],
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def prompt_animal(image_url):\n",
        "  response = client.chat.completions.create(\n",
        "    model=\"gpt-4-turbo\",\n",
        "    messages=[\n",
        "      {\n",
        "        \"role\": \"user\",\n",
        "        \"content\": [\n",
        "          {\"type\": \"text\", \"text\": \"RESPOND IN 1 WORD. Imagine you're an animal sorter aiding in spiritual discovery. Based on the image provided, what animal resonates with the person's essence? Please offer a single-word response. This animal should embody traits or qualities that align with the individual's character or aspirations. Avoid animals with negative connotations. Example responses include dog, cat, tiger, lion, bear, fish, shark, deer. snake YOUR RESPONSE SHOULD BE 1 WORD, RESEMBLING ONE OF THESE ANIMALS\"},\n",
        "          {\n",
        "            \"type\": \"image_url\",\n",
        "            \"image_url\": {\n",
        "              \"url\": image_url,\n",
        "            },\n",
        "          },\n",
        "        ],\n",
        "      }\n",
        "    ],\n",
        "    max_tokens=300,\n",
        "  )\n",
        "\n",
        "  return response.choices[0].message.content\n",
        "\n",
        "animal = prompt_animal(image1_url)\n",
        " # Fill the blank to what animal you want to generate.\n",
        "print(animal)\n"
      ],
      "metadata": {
        "id": "vhYNAgUlabWr",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7d49c3d4-9cb7-4ec7-b2bc-b994cf257a41"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Lion\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "qDD0JVAq4pxc"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Below is Part 2 of the project that takes in the input"
      ],
      "metadata": {
        "id": "3hqPGYUyW0fo"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# 安装 pillow 的兼容版本\n",
        "!pip install pillow\n",
        "!pip install typer\n",
        "!pip install torch\n",
        "!pip install diffusers\n",
        "!pip install numpy\n",
        "\n",
        "try:\n",
        "    from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler\n",
        "    print(\"Libraries imported successfully!\")\n",
        "except ImportError as e:\n",
        "    print(f\"Failed to import libraries: {e}\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WXNVO9ed4So4",
        "outputId": "75ae946f-530a-477e-81a6-8435c2be339e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (10.3.0)\n",
            "Requirement already satisfied: typer in /usr/local/lib/python3.10/dist-packages (0.12.3)\n",
            "Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer) (8.1.7)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from typer) (4.11.0)\n",
            "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer) (1.5.4)\n",
            "Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer) (13.7.1)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer) (2.16.1)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer) (0.1.2)\n",
            "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.3.0+cpu)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.14.0)\n",
            "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch) (4.11.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.12)\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) (2023.6.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.5)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install --upgrade numpy\n",
        "!pip install --upgrade diffusers\n",
        "\n",
        "from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler\n",
        "from diffusers.utils import load_image\n",
        "from controlnet_aux import OpenposeDetector\n",
        "from PIL import Image\n",
        "import torch\n",
        "import numpy as np\n",
        "import cv2\n",
        "\n",
        "\n",
        "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "3-duQbvU5e-h",
        "outputId": "b8392d62-9330-46da-a432-42ca352547ad"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.26.4)\n",
            "Requirement already satisfied: diffusers in /usr/local/lib/python3.10/dist-packages (0.27.2)\n",
            "Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.10/dist-packages (from diffusers) (7.1.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from diffusers) (3.14.0)\n",
            "Requirement already satisfied: huggingface-hub>=0.20.2 in /usr/local/lib/python3.10/dist-packages (from diffusers) (0.20.3)\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) (2023.12.25)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from diffusers) (2.31.0)\n",
            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from diffusers) (0.4.3)\n",
            "Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from diffusers) (10.0.0)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.20.2->diffusers) (2023.6.0)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.20.2->diffusers) (4.66.4)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.20.2->diffusers) (6.0.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.20.2->diffusers) (4.11.0)\n",
            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.20.2->diffusers) (24.0)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata->diffusers) (3.18.1)\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) (3.7)\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) (2024.2.2)\n"
          ]
        },
        {
          "output_type": "error",
          "ename": "RuntimeError",
          "evalue": "Failed to import diffusers.pipelines.controlnet.pipeline_controlnet because of the following error (look up to see its traceback):\nFailed to import diffusers.loaders.single_file because of the following error (look up to see its traceback):\nFailed to import diffusers.schedulers.scheduling_lms_discrete because of the following error (look up to see its traceback):\nmodule 'numpy.linalg._umath_linalg' has no attribute '_ilp64'",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m_get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m    717\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 718\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mimportlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimport_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\".\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mmodule_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    719\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/__init__.py\u001b[0m in \u001b[0;36mimport_module\u001b[0;34m(name, package)\u001b[0m\n\u001b[1;32m    125\u001b[0m             \u001b[0mlevel\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 126\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_bootstrap\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_gcd_import\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mlevel\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpackage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    127\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_gcd_import\u001b[0;34m(name, package, level)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_find_and_load\u001b[0;34m(name, import_)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_find_and_load_unlocked\u001b[0;34m(name, import_)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_load_unlocked\u001b[0;34m(spec)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap_external.py\u001b[0m in \u001b[0;36mexec_module\u001b[0;34m(self, module)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_call_with_frames_removed\u001b[0;34m(f, *args, **kwds)\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/schedulers/scheduling_lms_discrete.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     20\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 21\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mscipy\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mintegrate\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     22\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/integrate/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     95\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_ode\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 96\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_bvp\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msolve_bvp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     97\u001b[0m from ._ivp import (solve_ivp, OdeSolution, DenseOutput,\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/integrate/_bvp.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mscipy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msparse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinalg\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msplu\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mscipy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptimize\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mOptimizeResult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/optimize/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m    409\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_optimize\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 410\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_minimize\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    411\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_root\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/optimize/_minimize.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_trustregion_exact\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_minimize_trustregion_exact\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 27\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_trustregion_constr\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_minimize_trustregion_constr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     28\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/optimize/_trustregion_constr/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mminimize_trustregion_constr\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_minimize_trustregion_constr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/optimize/_trustregion_constr/minimize_trustregion_constr.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_differentiable_functions\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mVectorFunction\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m from .._constraints import (\n\u001b[0m\u001b[1;32m      6\u001b[0m     NonlinearConstraint, LinearConstraint, PreparedConstraint, Bounds, strict_bounds)\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/scipy/optimize/_constraints.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mwarnings\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mwarn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcatch_warnings\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msimplefilter\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mnumpy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtesting\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0msuppress_warnings\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      9\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mscipy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msparse\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0missparse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/numpy/testing/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_private\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_private\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     12\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_private\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0m_assert_valid_refcount\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_gen_alignment_data\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/numpy/testing/_private/utils.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     56\u001b[0m \u001b[0mHAS_REFCOUNT\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msys\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'getrefcount'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mIS_PYSTON\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 57\u001b[0;31m \u001b[0mHAS_LAPACK64\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnumpy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinalg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_umath_linalg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_ilp64\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     58\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mAttributeError\u001b[0m: module 'numpy.linalg._umath_linalg' has no attribute '_ilp64'",
            "\nThe above exception was the direct cause of the following exception:\n",
            "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m_get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m    717\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 718\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mimportlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimport_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\".\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mmodule_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    719\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/__init__.py\u001b[0m in \u001b[0;36mimport_module\u001b[0;34m(name, package)\u001b[0m\n\u001b[1;32m    125\u001b[0m             \u001b[0mlevel\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 126\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_bootstrap\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_gcd_import\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mlevel\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpackage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    127\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_gcd_import\u001b[0;34m(name, package, level)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_find_and_load\u001b[0;34m(name, import_)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_find_and_load_unlocked\u001b[0;34m(name, import_)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_load_unlocked\u001b[0;34m(spec)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap_external.py\u001b[0m in \u001b[0;36mexec_module\u001b[0;34m(self, module)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_call_with_frames_removed\u001b[0;34m(f, *args, **kwds)\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/loaders/single_file.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     17\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mis_transformers_available\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogging\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m from .single_file_utils import (\n\u001b[0m\u001b[1;32m     19\u001b[0m     \u001b[0mcreate_diffusers_unet_model_from_ldm\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/loaders/single_file_utils.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodels\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodeling_utils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mload_state_dict\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 27\u001b[0;31m from ..schedulers import (\n\u001b[0m\u001b[1;32m     28\u001b[0m     \u001b[0mDDIMScheduler\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_handle_fromlist\u001b[0;34m(module, fromlist, import_, recursive)\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m    707\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 708\u001b[0;31m             \u001b[0mmodule\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    709\u001b[0m             \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodule\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m_get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m    719\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 720\u001b[0;31m             raise RuntimeError(\n\u001b[0m\u001b[1;32m    721\u001b[0m                 \u001b[0;34mf\"Failed to import {self.__name__}.{module_name} because of the following error (look up to see its\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mRuntimeError\u001b[0m: Failed to import diffusers.schedulers.scheduling_lms_discrete because of the following error (look up to see its traceback):\nmodule 'numpy.linalg._umath_linalg' has no attribute '_ilp64'",
            "\nThe above exception was the direct cause of the following exception:\n",
            "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m_get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m    717\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 718\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mimportlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimport_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\".\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mmodule_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    719\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/__init__.py\u001b[0m in \u001b[0;36mimport_module\u001b[0;34m(name, package)\u001b[0m\n\u001b[1;32m    125\u001b[0m             \u001b[0mlevel\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 126\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_bootstrap\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_gcd_import\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mlevel\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpackage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlevel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    127\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_gcd_import\u001b[0;34m(name, package, level)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_find_and_load\u001b[0;34m(name, import_)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_find_and_load_unlocked\u001b[0;34m(name, import_)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_load_unlocked\u001b[0;34m(spec)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap_external.py\u001b[0m in \u001b[0;36mexec_module\u001b[0;34m(self, module)\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_call_with_frames_removed\u001b[0;34m(f, *args, **kwds)\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/pipelines/controlnet/pipeline_controlnet.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     25\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m...\u001b[0m\u001b[0mimage_processor\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mPipelineImageInput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mVaeImageProcessor\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 26\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m...\u001b[0m\u001b[0mloaders\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mFromSingleFileMixin\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mIPAdapterMixin\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mLoraLoaderMixin\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mTextualInversionLoaderMixin\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     27\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m...\u001b[0m\u001b[0mmodels\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mAutoencoderKL\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mControlNetModel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mImageProjection\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mUNet2DConditionModel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_handle_fromlist\u001b[0;34m(module, fromlist, import_, recursive)\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m    707\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 708\u001b[0;31m             \u001b[0mmodule\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    709\u001b[0m             \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodule\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m_get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m    719\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 720\u001b[0;31m             raise RuntimeError(\n\u001b[0m\u001b[1;32m    721\u001b[0m                 \u001b[0;34mf\"Failed to import {self.__name__}.{module_name} because of the following error (look up to see its\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mRuntimeError\u001b[0m: Failed to import diffusers.loaders.single_file because of the following error (look up to see its traceback):\nFailed to import diffusers.schedulers.scheduling_lms_discrete because of the following error (look up to see its traceback):\nmodule 'numpy.linalg._umath_linalg' has no attribute '_ilp64'",
            "\nThe above exception was the direct cause of the following exception:\n",
            "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-26-7ec02ac58852>\u001b[0m in \u001b[0;36m<cell line: 4>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msystem\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'pip install --upgrade diffusers'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mdiffusers\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mStableDiffusionControlNetPipeline\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mControlNetModel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mUniPCMultistepScheduler\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mdiffusers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mload_image\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mcontrolnet_aux\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mOpenposeDetector\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.10/importlib/_bootstrap.py\u001b[0m in \u001b[0;36m_handle_fromlist\u001b[0;34m(module, fromlist, import_, recursive)\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m    707\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    708\u001b[0m             \u001b[0mmodule\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 709\u001b[0;31m             \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodule\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    710\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    711\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mAttributeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"module {self.__name__} has no attribute {name}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m    707\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    708\u001b[0m             \u001b[0mmodule\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 709\u001b[0;31m             \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodule\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    710\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    711\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mAttributeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"module {self.__name__} has no attribute {name}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m    706\u001b[0m             \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    707\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 708\u001b[0;31m             \u001b[0mmodule\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_class_to_module\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    709\u001b[0m             \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodule\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    710\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/diffusers/utils/import_utils.py\u001b[0m in \u001b[0;36m_get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m    718\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mimportlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimport_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\".\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mmodule_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    719\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 720\u001b[0;31m             raise RuntimeError(\n\u001b[0m\u001b[1;32m    721\u001b[0m                 \u001b[0;34mf\"Failed to import {self.__name__}.{module_name} because of the following error (look up to see its\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    722\u001b[0m                 \u001b[0;34mf\" traceback):\\n{e}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mRuntimeError\u001b[0m: Failed to import diffusers.pipelines.controlnet.pipeline_controlnet because of the following error (look up to see its traceback):\nFailed to import diffusers.loaders.single_file because of the following error (look up to see its traceback):\nFailed to import diffusers.schedulers.scheduling_lms_discrete because of the following error (look up to see its traceback):\nmodule 'numpy.linalg._umath_linalg' has no attribute '_ilp64'"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "fH7SnIPjt1rt"
      },
      "outputs": [],
      "source": [
        "openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')\n",
        "\n",
        "controlnet_conditioning_scale = 0.5  # recommended for good generalization\n",
        "\n",
        "controlnet = ControlNetModel.from_pretrained(\n",
        "    \"lllyasviel/sd-controlnet-openpose\", torch_dtype=torch.float16\n",
        ")\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "image = load_image(image1_url)\n",
        "image = openpose(image)\n",
        "\n",
        "display(image)\n"
      ],
      "metadata": {
        "id": "MZDspgRdHd4g"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "q0uUM322t3LA"
      },
      "outputs": [],
      "source": [
        "pipe = StableDiffusionControlNetPipeline.from_pretrained(\n",
        "    \"runwayml/stable-diffusion-v1-5\", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16\n",
        ")\n",
        "\n",
        "\n",
        "pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)\n",
        "\n",
        "\n",
        "#pipe.enable_xformers_memory_efficient_attention()\n",
        "\n",
        "pipe.enable_model_cpu_offload()\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113"
      ],
      "metadata": {
        "id": "O21Bu95FCoBb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "nvidia-smi"
      ],
      "metadata": {
        "id": "H-UzF_0MC5wO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "print(torch.cuda.is_available())"
      ],
      "metadata": {
        "id": "Jw44F39uCw1x"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "rTqVhmt-gwum"
      },
      "outputs": [],
      "source": [
        "prompt = f'{animal}, ultra realistic, NO HUMAN, Replace BUT NOT ADD OR DELETE the human with a {animal}. Some emotion'\n",
        "negative_prompt = 'medium quality, unrealastic, distortion, unreasonable lighting, sketches, human'\n",
        "\n",
        "images = pipe(\n",
        "    prompt, negative_prompt=negative_prompt, image=image, controlnet_conditioning_scale=controlnet_conditioning_scale, num_inference_steps=30\n",
        "    ).images\n",
        "\n",
        "images[0].save(f\"hug_lab.png\")\n"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": [],
      "machine_shape": "hm"
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}