{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "k0FwyGoq7Te7"
},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sE22UQtQ9YYi"
},
"source": [
"# **Welcome to Wav2Lip colab mod by Ten Deepfake**\n",
"\n",
"# **There is no need for colab pro to use it.**\n",
"[Youtube](https://www.youtube.com/user/zabique) [Discord](https://discord.gg/dhfTaR7W88) [E-mail](mailto:tendeepfake@gmail.com\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "dT9AQwdf8sJK"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9cA_SNxHxT0P"
},
"source": [
"# **Check GPU**\n",
"\n",
"* Google Colab can provide you with one of Tesla graphics cards: K80, T4, P4, P100 and V100\n",
"* Here you can check the model of GPU before using Wav2Lip"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "oTiJ1TJKNj_J",
"outputId": "7b76697b-97be-488a-e437-3f9c5de836d2",
"vscode": {
"languageId": "python"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Sat Apr 30 20:17:03 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 K80 Off | 00000000:00:04.0 Off | 0 |\n",
"| N/A 36C P8 28W / 149W | 0MiB / 11441MiB | 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": [
"#@title Start\n",
"!nvidia-smi"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NuvzGmXC8v0Y"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4XCqT2ITN-In"
},
"source": [
"# **Mount your Google drive**\n",
"\n",
"1. Connect to your google drive to be able to import previously saved Wave2lip model files.\n",
"2. Ctrl+v auth key and hit ENTER\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "qciH4PsUazL_",
"outputId": "f5e7fdf3-37d1-468c-8467-db980db51213",
"vscode": {
"languageId": "python"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mounted at /content/gdrive\n"
]
}
],
"source": [
"#@title Start\n",
"from google.colab import drive\n",
"drive.mount('/content/gdrive')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vhprRkXl82oh"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yJ5taGmPcWV-"
},
"source": [
"# **Get the code and models**"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ekFHoZJS26tt"
},
"source": [
"# **Add this shortcut of my wav2lip folder to your drive (skip if already got model files on your gdrive):**\n",
"[Click here to add shortcut](https://drive.google.com/drive/folders/1cxf6ywJZGWX_fuFbgyxTCEDiLn-BJgr9?usp=sharing)\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "w3bfz-Iozq71"
},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MH1m608OymLH"
},
"source": [
"# **Alternatively download both files from here and put them in root of your google drive inside of /Wav2Lip/ folder.**\n",
"1. [Wav2Lip\tHighly accurate lip-sync](https://iiitaphyd-my.sharepoint.com/:u:/g/personal/radrabha_m_research_iiit_ac_in/Eb3LEzbfuKlJiR600lQWRxgBIY27JZg80f7V9jtMfbNDaQ?e=TBFBVW)\n",
"2. [Wav2Lip + GAN\tSlightly inferior lip-sync, but better visual quality](https://iiitaphyd-my.sharepoint.com/:u:/g/personal/radrabha_m_research_iiit_ac_in/EdjI7bZlgApMqsVoEUUXpLsBxqXbn5z8VTmoxp55YNDcIA?e=n9ljGW)\n",
"\n",
"**If none of the links work, go to official wav2lip github to find them.**\n",
"[HERE](https://github.com/Rudrabha/Wav2Lip#training-on-datasets-other-than-lrs2)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9W8_hlcH8mMz"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "P3LihClHbUd3",
"outputId": "7ec20058-e915-4f4d-d1b7-ff79ac787d70",
"vscode": {
"languageId": "python"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cloning into 'Wav2Lip'...\n",
"remote: Enumerating objects: 360, done.\u001b[K\n",
"remote: Total 360 (delta 0), reused 0 (delta 0), pack-reused 360\u001b[K\n",
"Receiving objects: 100% (360/360), 522.32 KiB | 1.51 MiB/s, done.\n",
"Resolving deltas: 100% (198/198), done.\n"
]
}
],
"source": [
"#@title Clone Wav2Lip github repo\n",
"!git clone https://github.com/Rudrabha/Wav2Lip.git"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "Ooh28vw-Uvd3",
"outputId": "f630217c-02a3-4fda-fc10-f0fddf6abc26",
"vscode": {
"languageId": "python"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting tensorflow\n",
" Downloading tensorflow-2.8.0-cp37-cp37m-manylinux2010_x86_64.whl (497.5 MB)\n",
"\u001b[K |████████████████████████████████| 497.5 MB 26 kB/s \n",
"\u001b[?25hCollecting tensorflow-gpu\n",
" Downloading tensorflow_gpu-2.8.0-cp37-cp37m-manylinux2010_x86_64.whl (497.5 MB)\n",
"\u001b[K |████████████████████████████████| 497.5 MB 31 kB/s \n",
"\u001b[?25hRequirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.1.0)\n",
"Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.44.0)\n",
"Collecting tf-estimator-nightly==2.8.0.dev2021122109\n",
" Downloading tf_estimator_nightly-2.8.0.dev2021122109-py2.py3-none-any.whl (462 kB)\n",
"\u001b[K |████████████████████████████████| 462 kB 51.7 MB/s \n",
"\u001b[?25hRequirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.14.0)\n",
"Requirement already satisfied: tensorboard<2.9,>=2.8 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.8.0)\n",
"Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (4.2.0)\n",
"Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (3.17.3)\n",
"Requirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (14.0.1)\n",
"Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (0.25.0)\n",
"Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.15.0)\n",
"Requirement already satisfied: flatbuffers>=1.12 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.0)\n",
"Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.1.2)\n",
"Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.6.3)\n",
"Requirement already satisfied: absl-py>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.0.0)\n",
"Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (0.2.0)\n",
"Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (3.1.0)\n",
"Requirement already satisfied: gast>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (0.5.3)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from tensorflow) (57.4.0)\n",
"Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (3.3.0)\n",
"Requirement already satisfied: keras<2.9,>=2.8.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.8.0)\n",
"Collecting numpy>=1.20\n",
" Downloading numpy-1.21.6-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (15.7 MB)\n",
"\u001b[K |████████████████████████████████| 15.7 MB 35.1 MB/s \n",
"\u001b[?25hRequirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.7/dist-packages (from astunparse>=1.6.0->tensorflow) (0.37.1)\n",
"Requirement already satisfied: cached-property in /usr/local/lib/python3.7/dist-packages (from h5py>=2.9.0->tensorflow) (1.5.2)\n",
"Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (1.35.0)\n",
"Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (3.3.6)\n",
"Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (0.4.6)\n",
"Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (2.23.0)\n",
"Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (0.6.1)\n",
"Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (1.0.1)\n",
"Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (1.8.1)\n",
"Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (4.2.4)\n",
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (0.2.8)\n",
"Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (4.8)\n",
"Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow) (1.3.1)\n",
"Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow) (4.11.3)\n",
"Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow) (3.8.0)\n",
"Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.7/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (0.4.8)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (2.10)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (1.24.3)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (3.0.4)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (2021.10.8)\n",
"Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow) (3.2.0)\n",
"Installing collected packages: numpy, tf-estimator-nightly, tensorflow-gpu, tensorflow\n",
" Attempting uninstall: numpy\n",
" Found existing installation: numpy 1.17.1\n",
" Uninstalling numpy-1.17.1:\n",
" Successfully uninstalled numpy-1.17.1\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"torchtext 0.12.0 requires torch==1.11.0, but you have torch 1.1.0 which is incompatible.\n",
"kapre 0.3.7 requires librosa>=0.7.2, but you have librosa 0.7.0 which is incompatible.\n",
"datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible.\n",
"albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.\u001b[0m\n",
"Successfully installed numpy-1.21.6 tensorflow-2.8.0 tensorflow-gpu-2.8.0 tf-estimator-nightly-2.8.0.dev2021122109\n"
]
},
{
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"numpy"
]
}
}
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#@title Uninstall tensorflow - Confirm with y [ enter ]\n",
"!pip install tensorflow tensorflow-gpu\n",
"torchtext 0.12.0"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "1j4u8Kk3fqc9",
"outputId": "eae2a7ae-c0a9-47b2-82a0-2c46277e51ec",
"vscode": {
"languageId": "python"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cp: overwrite '/content/Wav2Lip/checkpoints/wav2lip_gan.pth'? y\n",
"cp: overwrite '/content/Wav2Lip/checkpoints/wav2lip.pth'? y\n",
"Requirement already satisfied: librosa==0.7.0 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 1)) (0.7.0)\n",
"Collecting numpy==1.17.1\n",
" Using cached numpy-1.17.1-cp37-cp37m-manylinux1_x86_64.whl (20.3 MB)\n",
"Requirement already satisfied: opencv-contrib-python>=4.2.0.34 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 3)) (4.5.5.64)\n",
"Requirement already satisfied: opencv-python==4.1.0.25 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 4)) (4.1.0.25)\n",
"Requirement already satisfied: torch==1.1.0 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 5)) (1.1.0)\n",
"Requirement already satisfied: torchvision==0.3.0 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 6)) (0.3.0)\n",
"Requirement already satisfied: tqdm==4.45.0 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 7)) (4.45.0)\n",
"Requirement already satisfied: numba==0.48 in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 8)) (0.48.0)\n",
"Requirement already satisfied: resampy>=0.2.0 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (0.2.2)\n",
"Requirement already satisfied: scipy>=1.0.0 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (1.4.1)\n",
"Requirement already satisfied: six>=1.3 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (1.15.0)\n",
"Requirement already satisfied: joblib>=0.12 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (1.1.0)\n",
"Requirement already satisfied: soundfile>=0.9.0 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (0.10.3.post1)\n",
"Requirement already satisfied: audioread>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (2.1.9)\n",
"Requirement already satisfied: decorator>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (4.4.2)\n",
"Requirement already satisfied: scikit-learn!=0.19.0,>=0.14.0 in /usr/local/lib/python3.7/dist-packages (from librosa==0.7.0->-r requirements.txt (line 1)) (1.0.2)\n",
"Requirement already satisfied: pillow>=4.1.1 in /usr/local/lib/python3.7/dist-packages (from torchvision==0.3.0->-r requirements.txt (line 6)) (7.1.2)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from numba==0.48->-r requirements.txt (line 8)) (57.4.0)\n",
"Requirement already satisfied: llvmlite<0.32.0,>=0.31.0dev0 in /usr/local/lib/python3.7/dist-packages (from numba==0.48->-r requirements.txt (line 8)) (0.31.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn!=0.19.0,>=0.14.0->librosa==0.7.0->-r requirements.txt (line 1)) (3.1.0)\n",
"Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.7/dist-packages (from soundfile>=0.9.0->librosa==0.7.0->-r requirements.txt (line 1)) (1.15.0)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.7/dist-packages (from cffi>=1.0->soundfile>=0.9.0->librosa==0.7.0->-r requirements.txt (line 1)) (2.21)\n",
"Installing collected packages: numpy\n",
" Attempting uninstall: numpy\n",
" Found existing installation: numpy 1.21.6\n",
" Uninstalling numpy-1.21.6:\n",
" Successfully uninstalled numpy-1.21.6\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"torchtext 0.12.0 requires torch==1.11.0, but you have torch 1.1.0 which is incompatible.\n",
"tensorflow 2.8.0 requires numpy>=1.20, but you have numpy 1.17.1 which is incompatible.\n",
"tensorflow-gpu 2.8.0 requires numpy>=1.20, but you have numpy 1.17.1 which is incompatible.\n",
"tables 3.7.0 requires numpy>=1.19.0, but you have numpy 1.17.1 which is incompatible.\n",
"pywavelets 1.3.0 requires numpy>=1.17.3, but you have numpy 1.17.1 which is incompatible.\n",
"pandas 1.3.5 requires numpy>=1.17.3; platform_machine != \"aarch64\" and platform_machine != \"arm64\" and python_version < \"3.10\", but you have numpy 1.17.1 which is incompatible.\n",
"kapre 0.3.7 requires librosa>=0.7.2, but you have librosa 0.7.0 which is incompatible.\n",
"kapre 0.3.7 requires numpy>=1.18.5, but you have numpy 1.17.1 which is incompatible.\n",
"jaxlib 0.3.2+cuda11.cudnn805 requires numpy>=1.19, but you have numpy 1.17.1 which is incompatible.\n",
"jax 0.3.4 requires numpy>=1.19, but you have numpy 1.17.1 which is incompatible.\n",
"datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible.\n",
"albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.\u001b[0m\n",
"Successfully installed numpy-1.17.1\n",
"--2022-04-30 20:53:10-- https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth\n",
"Resolving www.adrianbulat.com (www.adrianbulat.com)... 45.136.29.207\n",
"Connecting to www.adrianbulat.com (www.adrianbulat.com)|45.136.29.207|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 89843225 (86M) [application/octet-stream]\n",
"Saving to: ‘Wav2Lip/face_detection/detection/sfd/s3fd.pth’\n",
"\n",
"Wav2Lip/face_detect 100%[===================>] 85.68M 9.03MB/s in 11s \n",
"\n",
"2022-04-30 20:53:23 (7.71 MB/s) - ‘Wav2Lip/face_detection/detection/sfd/s3fd.pth’ saved [89843225/89843225]\n",
"\n"
]
}
],
"source": [
"#@title Copy wav2lip_gan.pth, wav2lip.pth, face detection models & Requirements.txt\n",
"!cp -ri \"/content/gdrive/MyDrive/Wav2lip/wav2lip_gan.pth\" /content/Wav2Lip/checkpoints/\n",
"!cp -ri \"/content/gdrive/MyDrive/Wav2lip/wav2lip.pth\" /content/Wav2Lip/checkpoints/\n",
"!cd Wav2Lip && pip install -r requirements.txt\n",
"!wget \"https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth\" -O \"Wav2Lip/face_detection/detection/sfd/s3fd.pth\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vzokJMO19IyY"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RgjaWJFs8B38"
},
"source": [
"# **Quick guide**\n",
"1. Create video file input_video.mp4\n",
"2. Create audio file input_audio.wav\n",
"3. Both files have to be exact same length\n",
"4. Target face in the input_video.mp4, must be in ALL videoframes (So no black or blurry frames etc)\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qdIQfY2Kswcb"
},
"source": [
"# **Now lets try!**"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9bDRYsfXTzXD"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "2OhT0w2uT4rQ",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 1-4. Batch processing - Upload -> process -> download -> play result\n",
"%cd sample_data/\n",
"%rm input_audio.wav\n",
"%rm input_video.mp4\n",
"from google.colab import files\n",
"uploaded = files.upload()\n",
"%cd ..\n",
"!cd Wav2Lip && python inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face \"/content/sample_data/input_video.mp4\" --audio \"/content/sample_data/input_audio.wav\"\n",
"from google.colab import files\n",
"files.download('/content/Wav2Lip/results/result_voice.mp4') \n",
"from IPython.display import HTML\n",
"from base64 import b64encode\n",
"mp4 = open('/content/Wav2Lip/results/result_voice.mp4','rb').read()\n",
"data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n",
"HTML(f\"\"\"\n",
"\"\"\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BgMkHOFqT2fK"
},
"source": [
"\n",
"\n",
"---\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "vsphzJawLF-f",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 1.Upload input_video.mp4 & input_audio.wav files\n",
"%cd sample_data/\n",
"from google.colab import files\n",
"uploaded = files.upload()\n",
"%cd .."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "jR5utmDMcSZY",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 2.Create Wav2Lip video (using wav2lip_gan.pth) GAN\n",
"!cd Wav2Lip && python inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face \"/content/sample_data/input_video.mp4\" --audio \"/content/sample_data/input_audio.wav\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "WxbzXZvLliiA",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 3.Play result video - 50% scaling\n",
"from IPython.display import HTML\n",
"from base64 import b64encode\n",
"mp4 = open('/content/Wav2Lip/results/result_voice.mp4','rb').read()\n",
"data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n",
"HTML(f\"\"\"\n",
"\"\"\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "1kt-krsEbz5j",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 4.Download Result.mp4 to your computer\n",
"from google.colab import files\n",
"files.download('/content/Wav2Lip/results/result_voice.mp4') \n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "d7zgfrQqbKom"
},
"source": [
"# **Variations to try**\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "-4PqQrDcphU4",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 1.Create Wav2Lip video (using wav2lip.pth) NON-GAN\n",
"!cd Wav2Lip && python inference.py --checkpoint_path checkpoints/wav2lip.pth --face \"/content/sample_data/input_video.mp4\" --audio \"/content/sample_data/input_audio.wav\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "xw0xFtZ2bsx8",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 2.Use resize_factor to reduce the video resolution, as there is a change you might get better results for lower resolution videos. Why? Because the model was trained on low resolution faces.\n",
"!cd Wav2Lip && python inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face \"/content/sample_data/input_video.mp4\" --audio \"/content/sample_data/input_audio.wav\" --resize_factor 2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "45XW4SZAzIz5",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 3.Use more padding to include the chin region (u can manually edit pads dimensions viewing and changing the code)\n",
"!cd Wav2Lip && python inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face \"/content/sample_data/input_video.mp4\" --audio \"/content/sample_data/input_audio.wav\" --pads 0 20 0 0"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "X1Z0zRdZR5BZ",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 4.Play result video - 50% scaling\n",
"from IPython.display import HTML\n",
"from base64 import b64encode\n",
"mp4 = open('/content/Wav2Lip/results/result_voice.mp4','rb').read()\n",
"data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n",
"HTML(f\"\"\"\n",
"\"\"\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "gfXFOpAmR_dh",
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"#@title 5.Download Result.mp4 to your computer\n",
"from google.colab import files\n",
"files.download('/content/Wav2Lip/results/result_voice.mp4') \n"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"name": "Wav2Lip TenDeepfake eng.ipynb",
"provenance": [],
"toc_visible": true
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}