Prog Rock Stable.ipynb

prog-rock-stable.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Prog Rock Stable.ipynb",
      "provenance": [],
      "collapsed_sections": [
        "aZn37_DUwGC2",
        "A6y98K_6-n0A",
        "hYb6lkTB_S5N"
      ],
      "authorship_tag": "ABX9TyPXfB8iNlA4qk0T8APc1hfD",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/putuoka/572c57c0a3844bcee0377924d0e6eb91/prog-rock-stable.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Learn to try writing colab for Prog Rock Stable https://github.com/lowfuel/progrock-stable"
      ],
      "metadata": {
        "id": "GYwwW17GHvrJ"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 412
        },
        "id": "fJdYQupujee7",
        "outputId": "961f03e9-3236-4162-ecac-02164f1faa02"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "<h2>you have a tesla T4, use free training options</h2>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Sat Aug 27 01:51:48 2022       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   40C    P8     9W /  70W |      0MiB / 15109MiB |      0%      Default |\n",
            "|                               |                      |                  N/A |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ]
        }
      ],
      "source": [
        "#@markdown select best GPU to be used\n",
        "# restart runtime until it gets better gpu\n",
        "from IPython.display import HTML\n",
        "from subprocess import getoutput\n",
        "s = getoutput('nvidia-smi')\n",
        "if 'K80' in s:\n",
        "  gpu = 'you have a K80, try different kinds of settings'\n",
        "elif 'T4' in s:\n",
        "  gpu = 'you have a tesla T4, use free training options'\n",
        "elif 'P100' in s:\n",
        "  gpu = 'you have a P100, try different kinds of settings'\n",
        "display(HTML(f\"<h2>{gpu}</h2>\"))\n",
        "print(s)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "###Download CKPT File From Gdrive(Fastest)"
      ],
      "metadata": {
        "id": "aZn37_DUwGC2"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "You can create a shortcut to your google drive in main folder\n",
        "https://drive.google.com/file/d/1wHFgl0ivCmIZv88hVZXkb8oy9qCuaBGA/view?usp=sharing\n",
        "\n",
        "**The weights must be in the google drive root folder**"
      ],
      "metadata": {
        "id": "TYsNj6_wwzYy"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/gdrive')"
      ],
      "metadata": {
        "id": "eBTg1XfmxEMs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!cp '/gdrive/My Drive/model.ckpt' /content/sd-v1-4.ckpt"
      ],
      "metadata": {
        "id": "RGssr3mOxKm5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Download CKPT file from torrent"
      ],
      "metadata": {
        "id": "A6y98K_6-n0A"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!python -m pip install --upgrade pip setuptools wheel\n",
        "!python -m pip install lbry-libtorrent\n",
        "!apt install python3-libtorrent"
      ],
      "metadata": {
        "id": "Sm3aXDNv-ezW"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import libtorrent as lt\n",
        "import time\n",
        "import datetime\n",
        "\n",
        "ses = lt.session()\n",
        "ses.listen_on(6881, 6891)\n",
        "params = {\n",
        "    'save_path': '/content/'}\n",
        "link = \"magnet:?xt=urn:btih:3a4a612d75ed088ea542acac52f9f45987488d1c&dn=sd-v1-4.ckpt&tr=udp%3a%2f%2ftracker.openbittorrent.com%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.opentrackr.org%3a1337\" # PASTE TORRENT/MAGNET LINK HERE\n",
        "print(link)\n",
        "\n",
        "handle = lt.add_magnet_uri(ses, link, params)\n",
        "ses.start_dht()\n",
        "\n",
        "begin = time.time()\n",
        "print(datetime.datetime.now())\n",
        "\n",
        "print ('Downloading Metadata...')\n",
        "while (not handle.has_metadata()):\n",
        "    time.sleep(1)\n",
        "print ('Got Metadata, Starting Torrent Download...')\n",
        "\n",
        "print(\"Starting\", handle.name())\n",
        "\n",
        "while (handle.status().state != lt.torrent_status.seeding):\n",
        "    s = handle.status()\n",
        "    state_str = ['queued', 'checking', 'downloading metadata', \\\n",
        "            'downloading', 'finished', 'seeding', 'allocating']\n",
        "    print ('%.2f%% complete (down: %.1f kb/s up: %.1f kB/s peers: %d) %s ' % \\\n",
        "            (s.progress * 100, s.download_rate / 1000, s.upload_rate / 1000, \\\n",
        "            s.num_peers, state_str[s.state]))\n",
        "    time.sleep(5)\n",
        "\n",
        "end = time.time()\n",
        "print(handle.name(), \"COMPLETE\")\n",
        "\n",
        "print(\"Elapsed Time: \",int((end-begin)//60),\"min :\", int((end-begin)%60), \"sec\")\n",
        "\n",
        "print(datetime.datetime.now())"
      ],
      "metadata": {
        "id": "sY4mHcZ0_Lxs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "###Set Up & Run"
      ],
      "metadata": {
        "id": "hYb6lkTB_S5N"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!git clone https://github.com/lowfuel/progrock-stable prs\n",
        "%cd prs"
      ],
      "metadata": {
        "id": "9qeb4IU__iC8"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install torch numpy omegaconf clean-fid json5\n",
        "!pip install -e git+https://github.com/openai/CLIP.git@main#egg=clip \n",
        "!pip install -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers"
      ],
      "metadata": {
        "id": "Um7V2q7RDobo"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "!pip install pytorch-lightning torch-fidelity\n",
        "!pip install numpy omegaconf einops kornia pytorch-lightning\n",
        "!pip install albumentations transformers\n",
        "!pip install ftfy jsonmerge resize-right torchdiffeq tqdm"
      ],
      "metadata": {
        "id": "PoZNL5hzEJqs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!mv /content/sd-v1-4.ckpt ./models/sd-v1-4.ckpt"
      ],
      "metadata": {
        "id": "ZvdGhkbPFhr7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!python prs.py -p \"beautiful island in pacific\" --gobig"
      ],
      "metadata": {
        "id": "ST8hgkjwDk3b"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}