{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "collapsed_sections": [
        "tII_XRY-PJeo"
      ]
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# DiffSynth Studio\n",
        "\n",
        "Welcome to DiffSynth Studio! This is an example of Diffutoon."
      ],
      "metadata": {
        "id": "8ObdI5jCB8xy"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Install"
      ],
      "metadata": {
        "id": "XSkKX7O2BwuM"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "msCpt0pLnT8W",
        "outputId": "48e084bc-c5ad-4d99-e5d9-8be686a57675"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'DiffSynth-Studio'...\n",
            "remote: Enumerating objects: 259, done.\u001b[K\n",
            "remote: Counting objects: 100% (259/259), done.\u001b[K\n",
            "remote: Compressing objects: 100% (168/168), done.\u001b[K\n",
            "remote: Total 259 (delta 128), reused 203 (delta 81), pack-reused 0\u001b[K\n",
            "Receiving objects: 100% (259/259), 967.07 KiB | 3.58 MiB/s, done.\n",
            "Resolving deltas: 100% (128/128), done.\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m202.4/202.4 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.4/8.4 MB\u001b[0m \u001b[31m96.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m59.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m15.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.4/196.4 kB\u001b[0m \u001b[31m28.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.8/4.8 MB\u001b[0m \u001b[31m89.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m82.1/82.1 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Building wheel for controlnet-aux (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "/content/DiffSynth-Studio\n"
          ]
        }
      ],
      "source": [
        "!git clone https://github.com/Artiprocher/DiffSynth-Studio.git\n",
        "!pip install -q transformers controlnet-aux==0.0.7 streamlit streamlit-drawable-canvas imageio imageio[ffmpeg] safetensors einops\n",
        "%cd /content/DiffSynth-Studio"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Download Models"
      ],
      "metadata": {
        "id": "5eCu_rlKB3kK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import requests\n",
        "\n",
        "\n",
        "def download_model(url, file_path):\n",
        "  model_file = requests.get(url, allow_redirects=True)\n",
        "  with open(file_path, \"wb\") as f:\n",
        "    f.write(model_file.content)\n",
        "\n",
        "download_model(\"https://civitai.com/api/download/models/229575\", \"models/stable_diffusion/aingdiffusion_v12.safetensors\")\n",
        "download_model(\"https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v15_v2.ckpt\", \"models/AnimateDiff/mm_sd_v15_v2.ckpt\")\n",
        "download_model(\"https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11p_sd15_lineart.pth\", \"models/ControlNet/control_v11p_sd15_lineart.pth\")\n",
        "download_model(\"https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11f1e_sd15_tile.pth\", \"models/ControlNet/control_v11f1e_sd15_tile.pth\")\n",
        "download_model(\"https://huggingface.co/lllyasviel/Annotators/resolve/main/sk_model.pth\", \"models/Annotators/sk_model.pth\")\n",
        "download_model(\"https://huggingface.co/lllyasviel/Annotators/resolve/main/sk_model2.pth\", \"models/Annotators/sk_model2.pth\")\n",
        "download_model(\"https://civitai.com/api/download/models/25820?type=Model&format=PickleTensor&size=full&fp=fp16\", \"models/textual_inversion/verybadimagenegative_v1.3.pt\")"
      ],
      "metadata": {
        "id": "9znMkpVj3qZ1"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Run Diffutoon"
      ],
      "metadata": {
        "id": "iwOq2lWtKVYS"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Config Template"
      ],
      "metadata": {
        "id": "tII_XRY-PJeo"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "config_template = {\n",
        "    \"models\": {\n",
        "        \"model_list\": [\n",
        "            \"models/stable_diffusion/aingdiffusion_v12.safetensors\",\n",
        "            \"models/AnimateDiff/mm_sd_v15_v2.ckpt\",\n",
        "            \"models/ControlNet/control_v11f1e_sd15_tile.pth\",\n",
        "            \"models/ControlNet/control_v11p_sd15_lineart.pth\"\n",
        "        ],\n",
        "        \"textual_inversion_folder\": \"models/textual_inversion\",\n",
        "        \"device\": \"cuda\",\n",
        "        \"lora_alphas\": [],\n",
        "        \"controlnet_units\": [\n",
        "            {\n",
        "                \"processor_id\": \"tile\",\n",
        "                \"model_path\": \"models/ControlNet/control_v11f1e_sd15_tile.pth\",\n",
        "                \"scale\": 0.5\n",
        "            },\n",
        "            {\n",
        "                \"processor_id\": \"lineart\",\n",
        "                \"model_path\": \"models/ControlNet/control_v11p_sd15_lineart.pth\",\n",
        "                \"scale\": 0.5\n",
        "            }\n",
        "        ]\n",
        "    },\n",
        "    \"data\": {\n",
        "        \"input_frames\": {\n",
        "            \"video_file\": \"/content/video_guide.mp4\",\n",
        "            \"image_folder\": None,\n",
        "            \"height\": 1024,\n",
        "            \"width\": 1024,\n",
        "            \"start_frame_id\": 0,\n",
        "            \"end_frame_id\": 30\n",
        "        },\n",
        "        \"controlnet_frames\": [\n",
        "            {\n",
        "                \"video_file\": \"/content/video_guide.mp4\",\n",
        "                \"image_folder\": None,\n",
        "                \"height\": 1024,\n",
        "                \"width\": 1024,\n",
        "                \"start_frame_id\": 0,\n",
        "                \"end_frame_id\": 30\n",
        "            },\n",
        "            {\n",
        "                \"video_file\": \"/content/video_guide.mp4\",\n",
        "                \"image_folder\": None,\n",
        "                \"height\": 1024,\n",
        "                \"width\": 1024,\n",
        "                \"start_frame_id\": 0,\n",
        "                \"end_frame_id\": 30\n",
        "            }\n",
        "        ],\n",
        "        \"output_folder\": \"/content/output\",\n",
        "        \"fps\": 30\n",
        "    },\n",
        "    \"pipeline\": {\n",
        "        \"seed\": 0,\n",
        "        \"pipeline_inputs\": {\n",
        "            \"prompt\": \"best quality, perfect anime illustration, light, a girl is dancing, smile, solo\",\n",
        "            \"negative_prompt\": \"verybadimagenegative_v1.3\",\n",
        "            \"cfg_scale\": 7.0,\n",
        "            \"clip_skip\": 2,\n",
        "            \"denoising_strength\": 1.0,\n",
        "            \"num_inference_steps\": 10,\n",
        "            \"animatediff_batch_size\": 16,\n",
        "            \"animatediff_stride\": 8,\n",
        "            \"unet_batch_size\": 1,\n",
        "            \"controlnet_batch_size\": 1,\n",
        "            \"cross_frame_attention\": False,\n",
        "            # The following parameters will be overwritten. You don't need to modify them.\n",
        "            \"input_frames\": [],\n",
        "            \"num_frames\": 30,\n",
        "            \"width\": 1536,\n",
        "            \"height\": 1536,\n",
        "            \"controlnet_frames\": []\n",
        "        }\n",
        "    }\n",
        "}"
      ],
      "metadata": {
        "id": "vsd2alA3PrGe"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Run\n",
        "\n",
        "Before you run the following code, please upload your input video.\n",
        "\n",
        "We highly recommend you to use a higher resolution for better visual quality. The default resolution of Diffutoon is 1536x1536, which requires 22GB VRAM. If you don't have enough VRAM, 1024x1024 is also acceptable."
      ],
      "metadata": {
        "id": "113QAmNHP6T_"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from diffsynth import SDVideoPipelineRunner\n",
        "\n",
        "\n",
        "config = config_template.copy()\n",
        "config[\"data\"][\"input_frames\"] = {\n",
        "    \"video_file\": \"/content/input_video.mp4\",\n",
        "    \"image_folder\": None,\n",
        "    \"height\": 1024,\n",
        "    \"width\": 1024,\n",
        "    \"start_frame_id\": 0,\n",
        "    \"end_frame_id\": 16\n",
        "}\n",
        "config[\"data\"][\"controlnet_frames\"] = [config[\"data\"][\"input_frames\"], config[\"data\"][\"input_frames\"]]\n",
        "config[\"data\"][\"output_folder\"] = \"/content/output\"\n",
        "config[\"data\"][\"fps\"] = 30\n",
        "\n",
        "runner = SDVideoPipelineRunner()\n",
        "runner.run(config)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "761nbrgeKMvj",
        "outputId": "aea6f1fe-8485-4eb1-ac23-9c1023b3b9cd"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 16/16 [00:00<00:00, 82.74it/s]\n",
            "100%|██████████| 16/16 [00:04<00:00,  3.71it/s]\n",
            "100%|██████████| 10/10 [05:17<00:00, 31.78s/it]\n",
            "Saving images: 100%|██████████| 16/16 [00:06<00:00,  2.38it/s]\n",
            "Saving video: 100%|██████████| 16/16 [00:00<00:00, 31.93it/s]\n"
          ]
        }
      ]
    }
  ]
}