Upload kohya_SD_PaperSpace.ipynb

kohya_SD_PaperSpace.ipynb

@@ -0,0 +1,621 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cd47645b-3a64-433e-89a0-25fa30217a2c",
+   "metadata": {},
+   "source": [
+    "## 説明"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "06077106-1f0b-406e-8c82-fb127574bebe",
+   "metadata": {},
+   "source": [
+    "Dreambooth-Loraの学習をPeperspaceで動かす為のNotebook  \n",
+    "本家sd-scripts(https://github.com/kohya-ss/sd-scripts)  \n",
+    "\n",
+    "以下ソースを参考に作成してるで。  \n",
+    "sd-scripts(https://github.com/kohya-ss/sd-scripts)  \n",
+    "colab用kohya-trainer(https://github.com/Linaqruf/kohya-trainer)  \n",
+    "Peperspace用webui(https://github.com/Engineer-of-Stuff/stable-diffusion-paperspace)  \n",
+    "\n",
+    "学習素材と正規化画像はあらかじめstorageかtmpにアップしてな。  \n",
+    "永続Storageがある事と一部ターミナル使う前提になってるから無課金では動かんかもしれんで  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b07c14b6-b67f-41f3-9a1b-02730b32becf",
+   "metadata": {},
+   "source": [
+    "<span style=\"color: red\">既知の不具合</span>  \n",
+    "学習実行時に以下の警告メッセージが表示されるで  \n",
+    "解決策わかったら教えてください  \n",
+    "- 「--use_8bit_adam 」を有効にすると別パッケージから参照の警告メッセージが表示される。(多分bitsandbytesのパスがおかしい)  \n",
+    "- 「Could not load dynamic library 'libnvinfer_plugin.so.7';」の警告メッセージが表示される。(libnvinfer_plugin.so.7がpython3.9に無い？)  \n",
+    "- 「Unable to register cuBLAS factory 」の警告メッセージが表示される。(xpaformer入れる為にcudnnのバージョン下げてるのが怪しい）  \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4eb1d725-e55c-41e9-8574-da6dfb641ff0",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## 1.SETTING"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d33d8e53-af14-4033-9ba2-0c4044541763",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 1-0 設定値保存\n",
+    "仮想マシン起動時毎回実行する"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e90d2a8f-f497-421d-9a7e-3921caff41c4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#リポジトリ　永続ストレー、一時領域ジシンボリックリンク作成\n",
+    "repo_dir = '/notebooks'    \n",
+    "!ln -s /storage/ /notebooks/\n",
+    "!ln -s /tmp/ /notebooks/\n",
+    "\n",
+    "#その他設定値\n",
+    "activate_xformers = True # Enables the xformers optimizations using pre-built wheels.\n",
+    "\n",
+    "%store repo_dir activate_xformers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8f1b1a2f-d1ab-4b84-87dc-c83190bf506d",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 1-1.Git Clone\n",
+    "導入時 更新時"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "114fc353-213a-4d91-afce-f733ba5a9de2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%cd {repo_dir}\n",
+    "\n",
+    "import os\n",
+    "\n",
+    "def clone_kohya_sd_scripts():\n",
+    "  # Check if the directory already exists\n",
+    "  if os.path.isdir('/notebooks/sd-scripts'):\n",
+    "    %cd /notebooks/sd-scripts\n",
+    "    print(\"This folder already exists, will do a !git pull instead\\n\")\n",
+    "    !git pull\n",
+    "  else:\n",
+    "    !git clone https://github.com/kohya-ss/sd-scripts\n",
+    "\n",
+    "# Clone or update the Kohya Trainer repository\n",
+    "clone_kohya_sd_scripts()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b52dd301-0ed2-4ae4-911e-643d39c0f1bf",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 1-2.Install and Setting\n",
+    "仮想マシン起動時毎回実行する"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85954927-9497-4a2c-995a-dc4e6ba4b16c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%store -r repo_dir activate_xformers\n",
+    "\n",
+    "appDir = f'{repo_dir}/sd-scripts'\n",
+    "%cd {appDir}\n",
+    "\n",
+    "!pip install --upgrade pip\n",
+    "!pip install --upgrade -r requirements.txt\n",
+    "!pip uninstall -y torch  torchvision torchaudio # Remove existing pytorch install.\n",
+    "!pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113 # Install pytorch for cuda 11.3\n",
+    "\n",
+    "import os\n",
+    "if activate_xformers:\n",
+    "    print('Installing xformers...')\n",
+    "    import subprocess\n",
+    "    def download_release(url):\n",
+    "        binary = 'xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl' # have to save the binary as a specific name that pip likes\n",
+    "        tmp_dir = subprocess.check_output(['mktemp', '-d']).decode('ascii').strip('\\n')\n",
+    "        !wget \"{url}\" -O \"{tmp_dir}/{binary}\"\n",
+    "        return os.path.join(tmp_dir, binary)\n",
+    "\n",
+    "    # Set up pip packages\n",
+    "    s = subprocess.getoutput('nvidia-smi')\n",
+    "    if 'A4000' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/A4000-Oct-28-2022/a4000-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'A5000' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/A5000-Nov-1-2022/a5000-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'A6000' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/A6000-Nov-1-2022/a6000-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'P5000' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/P5000-Nov-1-2022/p5000-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'RTX 4000' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/RTX-4000-Nov-1-2022/rtx4000-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'RTX 5000' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/RTX-5000-Nov-1-2022/rtx5000-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'A100' in s:\n",
+    "        xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/A100-Nov-1-2022/a100-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    elif 'M4000' in s:\n",
+    "        print('xformers for M4000 hasn\\'t been built yet.')\n",
+    "        # xformers_whl = download_release('https://github.com/Cyberes/xformers-compiled/releases/download/A100-Nov-1-2022/a100-xformers-0.0.14.dev0-cp39-cp39-linux_x86_64.whl')\n",
+    "    else:\n",
+    "        print('GPU not matched to xformers binary so a one-size-fits-all binary was installed. If you have any issues, please build xformers using the Tools block below.')\n",
+    "        xformers_whl = download_release('https://raw.githubusercontent.com/Cyberes/xformers-compiled/main/various/xformers-0.0.14.dev0-cp37-cp37m-linux_x86_64.whl')\n",
+    "    !pip install --force-reinstall \"{xformers_whl}\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7076d849-dd45-491d-9e6c-473ed1bdbc6e",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 1-3.Accelerate config作成  \n",
+    "導入時初回のみターミナルから実行する。  \n",
+    "対話型で選択肢に回答する形式なのでターミナルから実行  \n",
+    " cd /notebooks/sd-scripts  \n",
+    " accelerate config  \n",
+    "質問回答後下記メッセージが出たら完了  \n",
+    "accelerate configuration saved at /root/.cache/huggingface/accelerate/default_config.yaml "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bf57b0ce-882c-415c-9d80-a923a7026124",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 1-4.accelerate configファイルをsd-scriptsディレクトリにコピーする\n",
+    "導入時初回のみ実行する  \n",
+    "1.3で作ったコンフィグファイルを永続ストレージにコピーする"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9bbd243b-75d3-4492-9bac-196faf55ee97",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!cp -r /root/.cache/huggingface/accelerate/ /notebooks/sd-scripts/accelerate/"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "648e5671-b153-4549-96c8-88afb204b3e4",
+   "metadata": {},
+   "source": [
+    "## RUNNING"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "730c4e1b-308f-438c-95a8-e26c671055f5",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# 2-0.Dataset Setting"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "569d34de-15db-46f4-9af4-7acbfc98e5c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#起動時。学習素材変更時実行する\n",
+    "#Learning checkpointName .ckpt\n",
+    "model_file_name = \"wd-1-4-anime_e1.ckpt\" #@param {'type' : 'string'}  \n",
+    "\n",
+    "model_storage_dir =\"/notebooks/storage/models\"\n",
+    "\n",
+    "model_file_path = f\"{model_storage_dir}/{model_file_name}\"\n",
+    "\n",
+    "# ===================================================================================================\n",
+    "# 正規化データ クラス名\n",
+    "reg_count = 1 #@param {type: \"integer\"}\n",
+    "reg_class =\"girl\" #@param {type: \"string\"}\n",
+    "\n",
+    "#学習元データ トークン(インスタンス)名、クラス名\n",
+    "train_count = 20 #@param {type: \"integer\"} 1epoch=学習素材 × カウント数のステップを回す（webui版で10の部分）\n",
+    "train_token = \"nahida\" #@param {type: \"string\"}\n",
+    "train_class = \"girl\" #@param {type: \"string\"}\n",
+    "\n",
+    "storage_train_dir = \"/notebooks/storage/atelier/dataset/1024_nahidav3\" #@param {type: \"string\"}\n",
+    "storage_class_dir = \"/notebooks/storage/atelier/dataset/Classification\" #@param {type: \"string\"}\n",
+    "\n",
+    "# ===================================================================================================\n",
+    "# Save variables to Jupiter's temp storage so we can access it even if the kernel restarts.\n",
+    "%store model_storage_dir model_file_path reg_count reg_class train_count train_token train_class storage_train_dir storage_class_dir"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b017ace2-cd08-427a-89d5-28ad8f7dbfc5",
+   "metadata": {},
+   "source": [
+    "# 2-1 Dreambooth フォルダ削除  \n",
+    "学習結果を消すので注意  \n",
+    "※学習画像データは消さない  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5aa4b00-b54d-4f5f-a0da-5153a86c1f87",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 学習結果を消すので注意\n",
+    "%cd /notebooks/\n",
+    "\n",
+    "import os\n",
+    "\n",
+    "def delete_dreambooth_folder():\n",
+    "  # Check if the directory already exists\n",
+    "  if os.path.isdir('/notebooks/dreambooth'):\n",
+    "    %rm -r /notebooks/dreambooth\n",
+    "    print(\"dreambooth dataset folder deleted done!!\")\n",
+    "  else:\n",
+    "    print(\"dreambooth dataset folder none\")\n",
+    "\n",
+    "# Delete Dreamboothe Dataset folder\n",
+    "delete_dreambooth_folder()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a27b535-ccd3-40cc-86b0-cab5cd3d63b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 起動時、学習素材変更時実行する\n",
+    "#@title Create train and reg folder based on description above\n",
+    "%store -r model_storage_dir model_file_path  reg_count reg_class train_count train_token train_class storage_train_dir storage_class_dir\n",
+    "\n",
+    "# Import the os and shutil modules\n",
+    "import os\n",
+    "import shutil\n",
+    "\n",
+    "# Change the current working directory to /content\n",
+    "%cd /notebooks\n",
+    "\n",
+    "# Define the dreambooth_directory variable\n",
+    "dreambooth_directory = \"/notebooks/dreambooth\"\n",
+    "\n",
+    "# Check if the dreambooth directory already exists\n",
+    "if os.path.isdir(dreambooth_directory):\n",
+    "  # If the directory exists, do nothing\n",
+    "  pass\n",
+    "else:\n",
+    "  # If the directory does not exist, create it\n",
+    "  os.mkdir(dreambooth_directory)\n",
+    "\n",
+    "#@markdown ### Define the reg_folder variable\n",
+    "#reg_count = 1 #@param {type: \"integer\"}\n",
+    "#reg_class =\"kasakai_hikaru\" #@param {type: \"string\"}\n",
+    "reg_folder = str(reg_count) + \"_\" + reg_class\n",
+    "\n",
+    "# Define the reg_directory variable\n",
+    "reg_directory = f\"{dreambooth_directory}/reg_{reg_class}\"\n",
+    "\n",
+    "# Check if the reg directory already exists\n",
+    "if os.path.isdir(reg_directory):\n",
+    "  # If the directory exists, do nothing\n",
+    "  pass\n",
+    "else:\n",
+    "  # If the directory does not exist, create it\n",
+    "  os.mkdir(reg_directory)\n",
+    "\n",
+    "# Define the reg_folder_directory variable\n",
+    "reg_folder_directory = f\"{reg_directory}/{reg_folder}\"\n",
+    "\n",
+    "# Check if the reg_folder directory already exists\n",
+    "if os.path.isdir(reg_folder_directory):\n",
+    "  # If the directory exists, do nothing\n",
+    "  pass\n",
+    "else:\n",
+    "  # If the directory does not exist, create it\n",
+    "  #os.mkdir(reg_folder_directory)\n",
+    "  os.symlink(storage_class_dir, reg_folder_directory)\n",
+    "\n",
+    "#@markdown ### Define the train_folder variable\n",
+    "#train_count = 3300 #@param {type: \"integer\"}\n",
+    "#train_token = \"sls\" #@param {type: \"string\"}\n",
+    "#train_class = \"kasakai_hikaru\" #@param {type: \"string\"}\n",
+    "train_folder = str(train_count) + \"_\" + train_token + \"_\" + train_class\n",
+    "\n",
+    "# Define the train_directory variable\n",
+    "train_directory = f\"{dreambooth_directory}/train_{train_class}\"\n",
+    "\n",
+    "# Check if the train directory already exists\n",
+    "if os.path.isdir(train_directory):\n",
+    "  # If the directory exists, do nothing\n",
+    "  pass\n",
+    "else:\n",
+    "  # If the directory does not exist, create it\n",
+    "  os.mkdir(train_directory)\n",
+    "    \n",
+    "# Define the train_folder_directory variable\n",
+    "train_folder_directory = f\"{train_directory}/{train_folder}\"\n",
+    "\n",
+    "# Check if the train_folder directory already exists\n",
+    "if os.path.isdir(train_folder_directory):\n",
+    "  # If the directory exists, do nothing\n",
+    "  pass\n",
+    "else:\n",
+    "  # If the directory does not exist, create it\n",
+    "  #os.mkdir(train_folder_directory)\n",
+    "  os.symlink(storage_train_dir, train_folder_directory)\n",
+    "  \n",
+    "%store train_directory train_folder_directory reg_directory  reg_folder_directory"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1bb54f2f-66a8-4a4f-80c3-a38f6eacd9fe",
+   "metadata": {},
+   "source": [
+    "# Lora Train Start\n",
+    "Dreambooth-Loraの学習を実行する  \n",
+    "引数の詳細情報は「sd-scripts/train_network.py」のソースを参照　　"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e0b13039-fec7-4002-998a-64429599baca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#@title Training begin Lora\n",
+    "%store -r model_storage_dir model_file_path train_directory reg_directory \n",
+    "accelerate_config = \"/notebooks/sd-scripts/accelerate/default_config.yaml\"\n",
+    "num_cpu_threads_per_process = 8 #@param {'type':'integer'}\n",
+    "pre_trained_model_path =model_file_path #@param {'type':'string'}\n",
+    "train_data_dir = train_directory #@param {'type':'string'}\n",
+    "reg_data_dir = reg_directory #@param {'type':'string'}\n",
+    "\n",
+    "output_dir =\"/notebooks/dreambooth\" #@param {'type':'string'}\n",
+    "train_batch_size = 6 #@param {type: \"slider\", min: 1, max: 10}\n",
+    "resolution = \"768,768\" #@param [\"512,512\", \"768,768\"] {allow-input: false}\n",
+    "learning_rate =\"1e-4\" #@param {'type':'string'}\n",
+    "mixed_precision = \"bf16\" #@param [\"fp16\", \"bf16\"] {allow-input: false}\n",
+    "max_train_steps = 3200 #@param {'type':'integer'}\n",
+    "save_precision = \"fp16\" #@param [\"float\", \"fp16\", \"bf16\"] {allow-input: false}\n",
+    "save_every_n_epochs = 5 #@param {'type':'integer'}\n",
+    "use_network_module = \"networks.lora\" #@param {'type':'string'}\n",
+    "caption_extension =\".txt\" #@param {'type':'string'}\n",
+    "#resme_path ='/notebooks/dreambooth/last-state' #学習再開する場合フォルダを指定する\n",
+    "resme_path ='' #学習再開する場合フォルダを指定する\n",
+    "resume = f'--resume={resme_path}' if resme_path else '' #@param {'type':'string'}\n",
+    "max_token_length = 225 #@param {'type':'integer'}\n",
+    "\n",
+    "%cd /notebooks/sd-scripts/\n",
+    "!accelerate launch --config_file {accelerate_config} --num_cpu_threads_per_process {num_cpu_threads_per_process} train_network.py \\\n",
+    "    --v2 \\\n",
+    "    --max_token_length={max_token_length} \\\n",
+    "    --pretrained_model_name_or_path={pre_trained_model_path} \\\n",
+    "    --train_data_dir={train_data_dir} \\\n",
+    "    --reg_data_dir={reg_data_dir} \\\n",
+    "    --output_dir={output_dir} \\\n",
+    "    --prior_loss_weight=1.0 \\\n",
+    "    --resolution={resolution} \\\n",
+    "    --train_batch_size={train_batch_size}\\\n",
+    "    --learning_rate={learning_rate}\\\n",
+    "    --max_train_steps={max_train_steps}  \\\n",
+    "    --use_8bit_adam \\\n",
+    "    --xformers \\\n",
+    "    --cache_latents \\\n",
+    "    --mixed_precision={mixed_precision} \\\n",
+    "    --gradient_checkpointing \\\n",
+    "    --save_every_n_epochs={save_every_n_epochs} \\\n",
+    "    --enable_bucket \\\n",
+    "    --network_module={use_network_module} \\\n",
+    "    --caption_extension={caption_extension} \\\n",
+    "    --save_state {resume}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "371b43fe-9293-4f1e-a026-72b3f94df6e2",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true,
+    "tags": []
+   },
+   "source": [
+    "# 3.Dataset Labeling （おまけ）\n",
+    "FineTune用 Lora学習には使わない。WD14taggerは使うかも"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "05528d73-883e-4365-a1e7-d82cf61eee6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3-1.BLIPでキャプションファイル(.caption)を学習素材と同じ場所に作成する\n",
+    "%store -r storage_train_dir\n",
+    "%cd /notebooks/sd-scripts/\n",
+    "batch_size = 8 #@param {'type':'integer'}\n",
+    "\n",
+    "!python finetune/make_captions.py --batch_size {batch_size} {storage_train_dir}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c58ed68-fc08-4d1a-9630-d14c6b0b3db8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3-2 WD1.4 taggerでタグテキスト(.txt)を学習素材と同じ場所に作成する\n",
+    "#@title Start WD 1.4 Tagger\n",
+    "%store -r storage_train_dir\n",
+    "%cd /notebooks/sd-scripts/\n",
+    "\n",
+    "batch_size = 8 #@param {'type':'integer'}\n",
+    "caption_extension = \".txt\" #@param [\".txt\",\".caption\"]\n",
+    "\n",
+    "!python finetune/tag_images_by_wd14_tagger.py \\\n",
+    "  {storage_train_dir} \\\n",
+    "  --batch_size {batch_size} \\\n",
+    "  --caption_extension {caption_extension}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4aef070-b6f2-4346-a553-888bb4404e83",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3-3 キャプションとタグを結合して1つのファイルにまとめる(meta_clean.json作成)\n",
+    "#@title Create meta_clean.json \n",
+    "# Change the working directory\n",
+    "%store -r storage_train_dir\n",
+    "%cd /notebooks/sd-scripts/\n",
+    "\n",
+    "#@markdown ### Define Parameters\n",
+    "meta_cap_dd = \"/notebooks/dreambooth/meta_cap_dd.json\" \n",
+    "meta_cap = \"/notebooks/dreambooth/meta_cap.json\" \n",
+    "meta_clean = \"/notebooks/dreambooth/meta_clean.json\" #@param {'type':'string'}\n",
+    "\n",
+    "# Check if the train_data_dir exists and is a directory\n",
+    "if os.path.isdir(storage_train_dir):\n",
+    "  # Check if there are any .caption files in the train_data_dir\n",
+    "  if any(file.endswith('.caption') for file in os.listdir(storage_train_dir)):\n",
+    "    # Create meta_cap.json from captions\n",
+    "    !python finetune/merge_captions_to_metadata.py \\\n",
+    "      {storage_train_dir} \\\n",
+    "      {meta_cap}\n",
+    "\n",
+    "  # Check if there are any .txtn files in the train_data_dir\n",
+    "  if any(file.endswith('.txt') for file in os.listdir(storage_train_dir)):\n",
+    "    # Create meta_cap_dd.json from tags\n",
+    "    !python finetune/merge_dd_tags_to_metadata.py \\\n",
+    "      {storage_train_dir} \\\n",
+    "      {meta_cap_dd}\n",
+    "else:\n",
+    "  print(\"train_data_dir does not exist or is not a directory.\")\n",
+    "\n",
+    "# Merge meta_cap.json to meta_cap_dd.json\n",
+    "if os.path.exists(meta_cap) and os.path.exists(meta_cap_dd):\n",
+    "  !python finetune/merge_dd_tags_to_metadata.py \\\n",
+    "    {storage_train_dir} \\\n",
+    "    --in_json {meta_cap} \\\n",
+    "    {meta_cap_dd}\n",
+    "\n",
+    "# Clean meta_cap_dd.json and store it to meta_clean.json\n",
+    "if os.path.exists(meta_cap_dd):\n",
+    "  # Clean captions and tags in meta_cap_dd.json and store the result in meta_clean.json\n",
+    "  !python finetune/clean_captions_and_tags.py \\\n",
+    "    {meta_cap_dd} \\\n",
+    "    {meta_clean}\n",
+    "elif os.path.exists(meta_cap):\n",
+    "  # If meta_cap_dd.json does not exist, clean meta_cap.json and store the result in meta_clean.json\n",
+    "  !python finetune/clean_captions_and_tags.py \\\n",
+    "    {meta_cap} \\\n",
+    "    {meta_clean}\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "067d56ab-cc17-4acf-af5c-3913c56c722a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 3-4 latentsの事前取得\n",
+    "#@title Aspect Ratio Bucketing\n",
+    "%store -r storage_train_dir model_file_path\n",
+    "\n",
+    "# Change working directory\n",
+    "%cd /notebooks/sd-scripts/\n",
+    "\n",
+    "#@markdown ### Define parameters\n",
+    "\n",
+    "#model_dir = \"runwayml/stable-diffusion-v1-5\" #@param {'type' : 'string'} \n",
+    "model_dir = model_file_path #@param {'type' : 'string'} \n",
+    "batch_size = 4 #@param {'type':'integer'}\n",
+    "max_resolution = \"768,768\" #@param [\"512,512\", \"768,768\"] {allow-input: false}\n",
+    "mixed_precision = \"bf16\" #@param [\"no\", \"fp16\", \"bf16\"] {allow-input: false}\n",
+    "meta_clean = \"/notebooks/dreambooth/meta_clean.json\"\n",
+    "meta_lat = \"/notebooks/dreambooth/meta_lat.json\"\n",
+    "\n",
+    "\n",
+    "# Run script to prepare buckets and latents\n",
+    "!python finetune/prepare_buckets_latents.py \\\n",
+    "  {storage_train_dir} \\\n",
+    "  {meta_clean} \\\n",
+    "  {meta_lat} \\\n",
+    "  {model_dir} \\\n",
+    "  --batch_size {batch_size} \\\n",
+    "  --max_resolution {max_resolution} \\\n",
+    "  --mixed_precision {mixed_precision}\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}