{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "Stable_Diffusion_AI_Notebook.ipynb", "provenance": [], "collapsed_sections": [], "private_outputs": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU", "gpuClass": "standard" }, "cells": [ { "cell_type": "markdown", "source": [ "# Stable Diffusion AI Notebook\n", "\n", "\"stable-diffusion-ai\"
\n", "#### Instructions:\n", "1. Execute each cell in order to mount a Dream bot and create images from text.
\n", "2. Once cells 1-8 were run correctly you'll be executing a terminal in cell #9, you'll to enter `pipenv run scripts/dream.py` command to run Dream bot.
\n", "3. After launching dream bot, you'll see:
`Dream > ` in terminal.
Insert a command, eg. `Dream > Astronaut floating in a distant galaxy`, or type `-h` for help.\n", "3. After completion you'll see your generated images in path `stable-diffusion/outputs/img-samples/`, you can also display images in cell #10.\n", "4. To quit Dream bot use `q` command.
\n", "---\n", "Note: It takes some time to load, but after installing all dependencies you can use the bot all time you want while colab instance is up.
\n", "Requirements: For this notebook to work you need to have [Stable-Diffusion-v-1-4](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) stored in your Google Drive, it will be needed in cell #6\n", "##### For more details visit Github repository: [lstein/stable-diffusion](https://github.com/lstein/stable-diffusion)\n", "---\n" ], "metadata": { "id": "ycYWcsEKc6w7" } }, { "cell_type": "code", "source": [ "#@title 1. Check current GPU assigned\n", "!nvidia-smi -L\n", "!nvidia-smi" ], "metadata": { "cellView": "form", "id": "a2Z5Qu_o8VtQ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "cellView": "form", "id": "vbI9ZsQHzjqF" }, "outputs": [], "source": [ "#@title 2. Download stable-diffusion Repository\n", "from os.path import exists\n", "\n", "if exists(\"/content/stable-diffusion/\")==True:\n", " print(\"Already downloaded repo\")\n", "else:\n", " !git clone --quiet https://github.com/lstein/stable-diffusion.git # Original repo\n", " %cd stable-diffusion/\n", " !git checkout --quiet tags/release-1.09\n", " " ] }, { "cell_type": "code", "source": [ "#@title 3. Install Python 3.8 \n", "%%capture --no-stderr\n", "import gc\n", "!apt-get -qq install python3.8\n", "gc.collect()" ], "metadata": { "id": "daHlozvwKesj", "cellView": "form" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 4. Install dependencies from file in a VirtualEnv\n", "#@markdown Be patient, it takes ~ 5 - 7min
\n", "%%capture --no-stderr\n", "#Virtual environment\n", "!pip install pipenv -q\n", "!pip install colab-xterm\n", "%load_ext colabxterm\n", "!pipenv --python 3.8\n", "!pipenv install -r requirements.txt --skip-lock\n", "gc.collect()\n" ], "metadata": { "cellView": "form", "id": "QbXcGXYEFSNB" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 5. Mount google Drive\n", "from google.colab import drive\n", "drive.mount('/content/drive')" ], "metadata": { "cellView": "form", "id": "YEWPV-sF1RDM" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 6. Drive Path to model\n", "#@markdown Path should start with /content/drive/path-to-your-file
\n", "#@markdown Note: Model should be downloaded from https://huggingface.co
\n", "#@markdown Lastest release: [Stable-Diffusion-v-1-4](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)\n", "from os.path import exists\n", "\n", "model_path = \"\" #@param {type:\"string\"}\n", "if exists(model_path)==True:\n", " print(\"✅ Valid directory\")\n", "else: \n", " print(\"❌ File doesn't exist\")" ], "metadata": { "cellView": "form", "id": "zRTJeZ461WGu" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 7. Symlink to model\n", "\n", "from os.path import exists\n", "import os \n", "\n", "# Folder creation if it doesn't exist\n", "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1\")==True:\n", " print(\"❗ Dir stable-diffusion-v1 already exists\")\n", "else:\n", " %mkdir /content/stable-diffusion/models/ldm/stable-diffusion-v1\n", " print(\"✅ Dir stable-diffusion-v1 created\")\n", "\n", "# Symbolic link if it doesn't exist\n", "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt\")==True:\n", " print(\"❗ Symlink already created\")\n", "else: \n", " src = model_path\n", " dst = '/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt'\n", " os.symlink(src, dst) \n", " print(\"✅ Symbolic link created successfully\")" ], "metadata": { "id": "UY-NNz4I8_aG", "cellView": "form" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 8. Load small ML models required\n", "%%capture --no-stderr\n", "!pipenv run scripts/preload_models.py\n", "gc.collect()" ], "metadata": { "cellView": "form", "id": "ChIDWxLVHGGJ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 9. Run Terminal and Execute Dream bot\n", "#@markdown Steps:
\n", "#@markdown 1. Execute command `pipenv run scripts/dream.py` to run dream bot.
\n", "#@markdown 2. After initialized you'll see `Dream>` line.
\n", "#@markdown 3. Example text: `Astronaut floating in a distant galaxy`
\n", "#@markdown 4. To quit Dream bot use: `q` command.
\n", "\n", "#Run from virtual env\n", "\n", "%xterm\n", "gc.collect()" ], "metadata": { "id": "ir4hCrMIuUpl", "cellView": "form" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "#@title 10. Show generated images\n", "\n", "import glob\n", "import matplotlib.pyplot as plt\n", "import matplotlib.image as mpimg\n", "%matplotlib inline\n", "\n", "images = []\n", "for img_path in glob.glob('/content/stable-diffusion/outputs/img-samples/*.png'):\n", " images.append(mpimg.imread(img_path))\n", "\n", "# Remove ticks and labels on x-axis and y-axis both\n", "\n", "plt.figure(figsize=(20,10))\n", "\n", "columns = 5\n", "for i, image in enumerate(images):\n", " ax = plt.subplot(len(images) / columns + 1, columns, i + 1)\n", " ax.axes.xaxis.set_visible(False)\n", " ax.axes.yaxis.set_visible(False)\n", " ax.axis('off')\n", " plt.imshow(image)\n", " gc.collect()\n", "\n" ], "metadata": { "cellView": "form", "id": "qnLohSHmKoGk" }, "execution_count": null, "outputs": [] } ] }