{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "8ObdI5jCB8xy"
},
"source": [
"# DiffSynth Studio\n",
"\n",
"Welcome to DiffSynth Studio! This is an example of Diffutoon."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "XSkKX7O2BwuM"
},
"source": [
"## Install"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "msCpt0pLnT8W",
"outputId": "35d93b35-451b-4760-d1ee-ef7ff190916e"
},
"outputs": [],
"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 cupy-cuda12x\n",
"%cd /content/DiffSynth-Studio"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "5eCu_rlKB3kK"
},
"source": [
"## Download Models"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "9znMkpVj3qZ1"
},
"outputs": [],
"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/ControlNet-v1-1/resolve/main/control_v11f1p_sd15_depth.pth\", \"models/ControlNet/control_v11f1p_sd15_depth.pth\")\n",
"download_model(\"https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11p_sd15_softedge.pth\", \"models/ControlNet/control_v11p_sd15_softedge.pth\")\n",
"download_model(\"https://huggingface.co/lllyasviel/Annotators/resolve/main/dpt_hybrid-midas-501f0c75.pt\", \"models/Annotators/dpt_hybrid-midas-501f0c75.pt\")\n",
"download_model(\"https://huggingface.co/lllyasviel/Annotators/resolve/main/ControlNetHED.pth\", \"models/Annotators/ControlNetHED.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\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iwOq2lWtKVYS"
},
"source": [
"## Run Diffutoon"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "tII_XRY-PJeo"
},
"source": [
"### Config Template"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "vsd2alA3PrGe"
},
"outputs": [],
"source": [
"config_stage_1_template = {\n",
" \"models\": {\n",
" \"model_list\": [\n",
" \"models/stable_diffusion/aingdiffusion_v12.safetensors\",\n",
" \"models/ControlNet/control_v11p_sd15_softedge.pth\",\n",
" \"models/ControlNet/control_v11f1p_sd15_depth.pth\"\n",
" ],\n",
" \"textual_inversion_folder\": \"models/textual_inversion\",\n",
" \"device\": \"cuda\",\n",
" \"lora_alphas\": [],\n",
" \"controlnet_units\": [\n",
" {\n",
" \"processor_id\": \"softedge\",\n",
" \"model_path\": \"models/ControlNet/control_v11p_sd15_softedge.pth\",\n",
" \"scale\": 0.5\n",
" },\n",
" {\n",
" \"processor_id\": \"depth\",\n",
" \"model_path\": \"models/ControlNet/control_v11f1p_sd15_depth.pth\",\n",
" \"scale\": 0.5\n",
" }\n",
" ]\n",
" },\n",
" \"data\": {\n",
" \"input_frames\": {\n",
" \"video_file\": \"/content/input_video.mp4\",\n",
" \"image_folder\": None,\n",
" \"height\": 512,\n",
" \"width\": 512,\n",
" \"start_frame_id\": 0,\n",
" \"end_frame_id\": 30\n",
" },\n",
" \"controlnet_frames\": [\n",
" {\n",
" \"video_file\": \"/content/input_video.mp4\",\n",
" \"image_folder\": None,\n",
" \"height\": 512,\n",
" \"width\": 512,\n",
" \"start_frame_id\": 0,\n",
" \"end_frame_id\": 30\n",
" },\n",
" {\n",
" \"video_file\": \"/content/input_video.mp4\",\n",
" \"image_folder\": None,\n",
" \"height\": 512,\n",
" \"width\": 512,\n",
" \"start_frame_id\": 0,\n",
" \"end_frame_id\": 30\n",
" }\n",
" ],\n",
" \"output_folder\": \"data/examples/diffutoon_edit/color_video\",\n",
" \"fps\": 25\n",
" },\n",
" \"smoother_configs\": [\n",
" {\n",
" \"processor_type\": \"FastBlend\",\n",
" \"config\": {}\n",
" }\n",
" ],\n",
" \"pipeline\": {\n",
" \"seed\": 0,\n",
" \"pipeline_inputs\": {\n",
" \"prompt\": \"best quality, perfect anime illustration, orange clothes, night, a girl is dancing, smile, solo, black silk stockings\",\n",
" \"negative_prompt\": \"verybadimagenegative_v1.3\",\n",
" \"cfg_scale\": 7.0,\n",
" \"clip_skip\": 1,\n",
" \"denoising_strength\": 0.9,\n",
" \"num_inference_steps\": 20,\n",
" \"animatediff_batch_size\": 8,\n",
" \"animatediff_stride\": 4,\n",
" \"unet_batch_size\": 8,\n",
" \"controlnet_batch_size\": 8,\n",
" \"cross_frame_attention\": True,\n",
" \"smoother_progress_ids\": [-1],\n",
" # The following parameters will be overwritten. You don't need to modify them.\n",
" \"input_frames\": [],\n",
" \"num_frames\": 30,\n",
" \"width\": 512,\n",
" \"height\": 512,\n",
" \"controlnet_frames\": []\n",
" }\n",
" }\n",
"}\n",
"\n",
"config_stage_2_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/input_video.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/input_video.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/input_video.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\": 25\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",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "113QAmNHP6T_"
},
"source": [
"### Upload Input Video\n",
"\n",
"Before you run the following code, please upload your input video to `/content/input_video.mp4`."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CyqAsj1o5U9B"
},
"source": [
"### Toon Shading\n",
"\n",
"Render your video in an anime style.\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.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "761nbrgeKMvj",
"outputId": "c0d47d5f-16e9-4a65-e664-9bd5fc491111"
},
"outputs": [],
"source": [
"from diffsynth import SDVideoPipelineRunner\n",
"\n",
"\n",
"config = config_stage_2_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\": 30\n",
"}\n",
"config[\"data\"][\"controlnet_frames\"] = [config[\"data\"][\"input_frames\"], config[\"data\"][\"input_frames\"]]\n",
"config[\"data\"][\"output_folder\"] = \"/content/toon_video\"\n",
"config[\"data\"][\"fps\"] = 25\n",
"\n",
"runner = SDVideoPipelineRunner()\n",
"runner.run(config)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9wujhGUmDIwY"
},
"source": [
"Let's see the video!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 420
},
"id": "TBNAigacAq6h",
"outputId": "8f57c3b4-982b-4643-f3dc-53c51bd85a4b"
},
"outputs": [],
"source": [
"from IPython.display import HTML\n",
"from base64 import b64encode\n",
"\n",
"mp4 = open(\"/content/toon_video/video.mp4\", \"rb\").read()\n",
"data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n",
"HTML(\"\"\"\n",
"\n",
"\"\"\" % data_url)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "48hQfX--5YGi"
},
"source": [
"### Toon Shading with Editing Signals"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "bAQ9Zq-3-MH6"
},
"source": [
"In stage 1, input your prompt, and diffutoon will generate the editing signals in the format of low-resolution color video."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "BtDzYgIq5bgg",
"outputId": "bb27b7b9-7979-4409-f476-f25f0a164ef4"
},
"outputs": [],
"source": [
"from diffsynth import SDVideoPipelineRunner\n",
"\n",
"\n",
"config_stage_1 = config_stage_1_template.copy()\n",
"config_stage_1[\"data\"][\"input_frames\"] = {\n",
" \"video_file\": \"/content/input_video.mp4\",\n",
" \"image_folder\": None,\n",
" \"height\": 512,\n",
" \"width\": 512,\n",
" \"start_frame_id\": 0,\n",
" \"end_frame_id\": 30\n",
"}\n",
"config_stage_1[\"data\"][\"controlnet_frames\"] = [config_stage_1[\"data\"][\"input_frames\"], config_stage_1[\"data\"][\"input_frames\"]]\n",
"config_stage_1[\"data\"][\"output_folder\"] = \"/content/color_video\"\n",
"config_stage_1[\"data\"][\"fps\"] = 25\n",
"config_stage_1[\"pipeline\"][\"pipeline_inputs\"][\"prompt\"] = \"best quality, perfect anime illustration, orange clothes, night, a girl is dancing, smile, solo, black silk stockings\"\n",
"\n",
"runner = SDVideoPipelineRunner()\n",
"runner.run(config_stage_1)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "D9_AWwhi-pA9"
},
"source": [
"In stage 2, diffutoon will rerender the whole video according to the editing signals."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JFysCk7y51i_",
"outputId": "475050d3-c72e-4e08-b55c-d59ed86b5497"
},
"outputs": [],
"source": [
"from diffsynth import SDVideoPipelineRunner\n",
"\n",
"\n",
"config_stage_2 = config_stage_2_template.copy()\n",
"config_stage_2[\"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\": 30\n",
"}\n",
"config_stage_2[\"data\"][\"controlnet_frames\"][0] = {\n",
" \"video_file\": \"/content/color_video/video.mp4\",\n",
" \"image_folder\": None,\n",
" \"height\": config_stage_2[\"data\"][\"input_frames\"][\"height\"],\n",
" \"width\": config_stage_2[\"data\"][\"input_frames\"][\"width\"],\n",
" \"start_frame_id\": None,\n",
" \"end_frame_id\": None\n",
"}\n",
"config_stage_2[\"data\"][\"controlnet_frames\"][1] = config[\"data\"][\"input_frames\"]\n",
"config_stage_2[\"data\"][\"output_folder\"] = \"/content/edit_video\"\n",
"config_stage_2[\"data\"][\"fps\"] = 25\n",
"\n",
"runner = SDVideoPipelineRunner()\n",
"runner.run(config)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HIPrCAIS_Im0"
},
"source": [
"Let's see the video!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 420
},
"id": "Y2nz7rew-7VI",
"outputId": "fbcbadc6-4045-4aac-dfb0-80bacec003bf"
},
"outputs": [],
"source": [
"from IPython.display import HTML\n",
"from base64 import b64encode\n",
"\n",
"mp4 = open(\"/content/edit_video/video.mp4\", \"rb\").read()\n",
"data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n",
"HTML(\"\"\"\n",
"\n",
"\"\"\" % data_url)"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [
"tII_XRY-PJeo"
],
"gpuType": "T4",
"provenance": [],
"toc_visible": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}