Skip to content

Instantly share code, notes, and snippets.

@hathibelagal-dev

hathibelagal-dev/lipsync.ipynb

Last active September 9, 2025 14:30
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save hathibelagal-dev/fe393508fd1f3dd9d2c3066564325a7b to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save hathibelagal-dev/fe393508fd1f3dd9d2c3066564325a7b to your computer and use it in GitHub Desktop.
Download ZIP
LipsyncUpdated.ipynb
Display the source blob
Display the rendered blob
Raw
lipsync.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4",
"name": "LipsyncUpdated.ipynb",
"authorship_tag": "ABX9TyPk2aAHbbyVimvXednJCX9e",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/hathibelagal-dev/fe393508fd1f3dd9d2c3066564325a7b/lipsync.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"source": [
"!git clone https://github.com/bytedance/LatentSync.git"
],
"metadata": {
"id": "aercf7KTTSoF",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "f23fb171-3d07-45c6-bd35-1ff233a00eb2"
},
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'LatentSync'...\n",
"remote: Enumerating objects: 764, done.\u001b[K\n",
"remote: Counting objects: 100% (381/381), done.\u001b[K\n",
"remote: Compressing objects: 100% (109/109), done.\u001b[K\n",
"remote: Total 764 (delta 296), reused 272 (delta 272), pack-reused 383 (from 1)\u001b[K\n",
"Receiving objects: 100% (764/764), 9.41 MiB | 32.45 MiB/s, done.\n",
"Resolving deltas: 100% (428/428), done.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"%cd LatentSync\n",
"!pip install -r requirements.txt"
],
"metadata": {
"id": "QX2X7H7jWPgj",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "58caffa2-c270-42a4-bee5-3d085909456b"
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"/content/LatentSync\n",
"Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cu121\n",
"Collecting torch==2.5.1 (from -r requirements.txt (line 1))\n",
" Downloading https://download.pytorch.org/whl/cu121/torch-2.5.1%2Bcu121-cp312-cp312-linux_x86_64.whl (780.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m780.4/780.4 MB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting torchvision==0.20.1 (from -r requirements.txt (line 2))\n",
" Downloading https://download.pytorch.org/whl/cu121/torchvision-0.20.1%2Bcu121-cp312-cp312-linux_x86_64.whl (7.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.3/7.3 MB\u001b[0m \u001b[31m129.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting diffusers==0.32.2 (from -r requirements.txt (line 4))\n",
" Downloading diffusers-0.32.2-py3-none-any.whl.metadata (18 kB)\n",
"Collecting transformers==4.48.0 (from -r requirements.txt (line 5))\n",
" Downloading transformers-4.48.0-py3-none-any.whl.metadata (44 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.4/44.4 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting decord==0.6.0 (from -r requirements.txt (line 6))\n",
" Downloading decord-0.6.0-py3-none-manylinux2010_x86_64.whl.metadata (422 bytes)\n",
"Collecting accelerate==0.26.1 (from -r requirements.txt (line 7))\n",
" Downloading accelerate-0.26.1-py3-none-any.whl.metadata (18 kB)\n",
"Collecting einops==0.7.0 (from -r requirements.txt (line 8))\n",
" Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n",
"Requirement already satisfied: omegaconf==2.3.0 in /usr/local/lib/python3.12/dist-packages (from -r requirements.txt (line 9)) (2.3.0)\n",
"Collecting opencv-python==4.9.0.80 (from -r requirements.txt (line 10))\n",
" Downloading opencv_python-4.9.0.80-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)\n",
"\u001b[31mERROR: Could not find a version that satisfies the requirement mediapipe==0.10.11 (from versions: 0.10.13, 0.10.14, 0.10.15, 0.10.18, 0.10.20, 0.10.21)\u001b[0m\u001b[31m\n",
"\u001b[0m\u001b[31mERROR: No matching distribution found for mediapipe==0.10.11\u001b[0m\u001b[31m\n",
"\u001b[0m"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install -U accelerate==0.32.0"
],
"metadata": {
"id": "j7e1tPGYEKb4",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"outputId": "58e4103b-ea00-451a-8a6e-b8b36aa9aa65"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting accelerate==0.32.0\n",
" Downloading accelerate-0.32.0-py3-none-any.whl.metadata (18 kB)\n",
"Collecting numpy<2.0.0,>=1.17 (from accelerate==0.32.0)\n",
" Downloading numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.0/61.0 kB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from accelerate==0.32.0) (25.0)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.12/dist-packages (from accelerate==0.32.0) (5.9.5)\n",
"Requirement already satisfied: pyyaml in /usr/local/lib/python3.12/dist-packages (from accelerate==0.32.0) (6.0.2)\n",
"Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.12/dist-packages (from accelerate==0.32.0) (2.8.0+cu126)\n",
"Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.12/dist-packages (from accelerate==0.32.0) (0.34.4)\n",
"Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.12/dist-packages (from accelerate==0.32.0) (0.6.2)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (3.19.1)\n",
"Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (4.15.0)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (75.2.0)\n",
"Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (1.13.3)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (3.5)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (3.1.6)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (2025.3.0)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.6.77)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.6.77)\n",
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.6.80)\n",
"Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (9.10.2.21)\n",
"Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.6.4.1)\n",
"Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (11.3.0.4)\n",
"Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (10.3.7.77)\n",
"Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (11.7.1.2)\n",
"Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.5.4.2)\n",
"Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (0.7.1)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (2.27.3)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.6.77)\n",
"Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (12.6.85)\n",
"Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (1.11.1.6)\n",
"Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.10.0->accelerate==0.32.0) (3.4.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from huggingface-hub->accelerate==0.32.0) (2.32.4)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub->accelerate==0.32.0) (4.67.1)\n",
"Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub->accelerate==0.32.0) (1.1.9)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.10.0->accelerate==0.32.0) (1.3.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.10.0->accelerate==0.32.0) (3.0.2)\n",
"Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->huggingface-hub->accelerate==0.32.0) (3.4.3)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->huggingface-hub->accelerate==0.32.0) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->huggingface-hub->accelerate==0.32.0) (2.5.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->huggingface-hub->accelerate==0.32.0) (2025.8.3)\n",
"Downloading accelerate-0.32.0-py3-none-any.whl (314 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m314.0/314.0 kB\u001b[0m \u001b[31m28.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.0/18.0 MB\u001b[0m \u001b[31m109.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: numpy, accelerate\n",
" Attempting uninstall: numpy\n",
" Found existing installation: numpy 2.0.2\n",
" Uninstalling numpy-2.0.2:\n",
" Successfully uninstalled numpy-2.0.2\n",
" Attempting uninstall: accelerate\n",
" Found existing installation: accelerate 1.10.1\n",
" Uninstalling accelerate-1.10.1:\n",
" Successfully uninstalled accelerate-1.10.1\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",
"thinc 8.3.6 requires numpy<3.0.0,>=2.0.0, but you have numpy 1.26.4 which is incompatible.\n",
"opencv-python-headless 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\n",
"opencv-contrib-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\n",
"opencv-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0mSuccessfully installed accelerate-0.32.0 numpy-1.26.4\n"
]
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"numpy"
]
},
"id": "cdfffa9702a2416fa2c29618e00d3bbf"
}
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"!mkdir -p checkpoints"
],
"metadata": {
"id": "IC6b_b0KTnUy"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import os\n",
"os.environ[\"HF_HUB_HF_TRANSFER\"] = \"1\""
],
"metadata": {
"id": "cyNR1Dz0F09y"
},
"execution_count": 4,
"outputs": []
},
{
"cell_type": "code",
"source": [
"!hf download ByteDance/LatentSync-1.5 whisper/tiny.pt --local-dir checkpoints\n",
"!hf download ByteDance/LatentSync-1.5 latentsync_unet.pt --local-dir checkpoints"
],
"metadata": {
"id": "i2HIcr4-TYm2",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "7f22bd7e-7181-41c9-840c-8fe6899b32bf"
},
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading 'whisper/tiny.pt' to 'checkpoints/.cache/huggingface/download/whisper/2bXfceQet32ashONewwCNGFRC3E=.65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9.incomplete'\n",
"whisper/tiny.pt: 100% 75.6M/75.6M [00:01<00:00, 67.2MB/s]\n",
"Download complete. Moving file to checkpoints/whisper/tiny.pt\n",
"checkpoints/whisper/tiny.pt\n",
"Downloading 'latentsync_unet.pt' to 'checkpoints/.cache/huggingface/download/HrGktaY_kGnyhqDrRVde02cPk68=.6440b49a7ccceff56cdc001f5f17605216337f5bbd66fa360139768926e23f51.incomplete'\n",
"latentsync_unet.pt: 100% 5.07G/5.07G [01:20<00:00, 62.8MB/s]\n",
"Download complete. Moving file to checkpoints/latentsync_unet.pt\n",
"checkpoints/latentsync_unet.pt\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pwd"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VaD69ClfHRzz",
"outputId": "af41f817-5d37-4d73-a145-e53a6e0271f0"
},
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"/content/LatentSync\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"%cd /content/LatentSync\n",
"!ls .."
],
"metadata": {
"id": "Qrb3BDr0YQom",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "7fe75933-1304-4fc8-f73e-3198f382c09d"
},
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"/content/LatentSync\n",
"LatentSync m3.wav mod3.mp4 sample_data\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install -q decord insightface kornia onnxruntime ffmpeg-python DeepCache"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "y5nLsd2J_z0Q",
"outputId": "f7898ccc-3dc7-4217-a22c-36b93437c6f0"
},
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/439.5 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m \u001b[32m430.1/439.5 kB\u001b[0m \u001b[31m13.8 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m439.5/439.5 kB\u001b[0m \u001b[31m9.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.6/13.6 MB\u001b[0m \u001b[31m94.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m41.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m16.5/16.5 MB\u001b[0m \u001b[31m76.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.9/190.9 kB\u001b[0m \u001b[31m17.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.8/2.8 MB\u001b[0m \u001b[31m80.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m26.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Building wheel for insightface (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!python -m scripts.inference \\\n",
" --unet_config_path \"configs/unet/stage2.yaml\" \\\n",
" --inference_ckpt_path \"checkpoints/latentsync_unet.pt\" \\\n",
" --inference_steps 18 \\\n",
" --guidance_scale 2.0 \\\n",
" --video_path \"../mod3.mp4\" \\\n",
" --audio_path \"../m3.wav\" \\\n",
" --video_out_path \"../out3.mp4\""
],
"metadata": {
"id": "pgHUsbAVVHws",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "1f3163ba-dbd2-42d4-924b-885851e6b43d"
},
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"2025-09-09 13:15:38.472439: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"E0000 00:00:1757423738.745910 1931 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"E0000 00:00:1757423738.819929 1931 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"W0000 00:00:1757423739.365968 1931 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1757423739.366007 1931 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1757423739.366012 1931 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"W0000 00:00:1757423739.366015 1931 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
"2025-09-09 13:15:39.419503: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"Input video path: ../mod3.mp4\n",
"Input audio path: ../m3.wav\n",
"Loaded checkpoint path: checkpoints/latentsync_unet.pt\n",
"config.json: 100% 547/547 [00:00<00:00, 2.65MB/s]\n",
"diffusion_pytorch_model.safetensors: 100% 335M/335M [00:03<00:00, 102MB/s]\n",
"Initial seed: 1247\n",
"download_path: checkpoints/auxiliary/models/buffalo_l\n",
"Downloading checkpoints/auxiliary/models/buffalo_l.zip from https://github.com/deepinsight/insightface/releases/download/v0.7/buffalo_l.zip...\n",
"100% 281857/281857 [00:02<00:00, 99579.47KB/s]\n",
"/usr/local/lib/python3.12/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py:121: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'\n",
" warnings.warn(\n",
"Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}\n",
"model ignore: checkpoints/auxiliary/models/buffalo_l/1k3d68.onnx landmark_3d_68\n",
"Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}\n",
"find model: checkpoints/auxiliary/models/buffalo_l/2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0\n",
"Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}\n",
"find model: checkpoints/auxiliary/models/buffalo_l/det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0\n",
"Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}\n",
"model ignore: checkpoints/auxiliary/models/buffalo_l/genderage.onnx genderage\n",
"Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}\n",
"model ignore: checkpoints/auxiliary/models/buffalo_l/w600k_r50.onnx recognition\n",
"set det-size: (512, 512)\n",
"video in 25 FPS, audio idx in 50FPS\n",
"Affine transforming 369 faces...\n",
"100% 369/369 [01:38<00:00, 3.76it/s]\n",
"Doing inference...: 0% 0/24 [00:00<?, ?it/s]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:44, 2.60s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:35, 2.22s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:31, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:08<00:28, 2.06s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:10<00:26, 2.03s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:12<00:24, 2.02s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:14<00:22, 2.01s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:16<00:20, 2.02s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:18<00:18, 2.02s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:20<00:16, 2.03s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:22<00:14, 2.04s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:24<00:12, 2.05s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:26<00:10, 2.07s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:28<00:08, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:33<00:04, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:35<00:02, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:37<00:00, 2.09s/it]\n",
"Doing inference...: 4% 1/24 [00:40<15:26, 40.27s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:50, 2.95s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:05<00:40, 2.52s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:35, 2.38s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:32, 2.30s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:29, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:26, 2.22s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:16<00:24, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:18<00:21, 2.18s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:20<00:19, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:22<00:17, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:24<00:14, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:26<00:12, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.07s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.17s/it]\n",
"Doing inference...: 8% 2/24 [01:21<15:00, 40.92s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:46, 2.73s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.33s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:08<00:29, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:10<00:27, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:12<00:25, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:22, 2.07s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.07s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.06s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.06s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.06s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.06s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.07s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.07s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:33<00:04, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:35<00:02, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:37<00:00, 2.10s/it]\n",
"Doing inference...: 12% 3/24 [02:01<14:12, 40.58s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.81s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.40s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:33, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.15s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.14s/it]\n",
"Doing inference...: 17% 4/24 [02:42<13:33, 40.69s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.81s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.38s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.25s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.19s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 21% 5/24 [03:23<12:52, 40.65s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.78s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.37s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.24s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.18s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 25% 6/24 [04:03<12:11, 40.66s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.82s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.40s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:33, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.19s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 29% 7/24 [04:44<11:31, 40.65s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.78s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.37s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.23s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.12s/it]\n",
"Doing inference...: 33% 8/24 [05:25<10:50, 40.63s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.81s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.39s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:33, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.15s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.14s/it]\n",
"Doing inference...: 38% 9/24 [06:05<10:10, 40.69s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.79s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.38s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.24s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.18s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.12s/it]\n",
"Doing inference...: 42% 10/24 [06:46<09:28, 40.64s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.81s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.39s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.19s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.14s/it]\n",
"Doing inference...: 46% 11/24 [07:27<08:49, 40.71s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.79s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.38s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.24s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.18s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:33<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.12s/it]\n",
"Doing inference...: 50% 12/24 [08:07<08:07, 40.64s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.80s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.39s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:33, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.15s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:26<00:12, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.15s/it]\n",
"Doing inference...: 54% 13/24 [08:48<07:28, 40.74s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.79s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.37s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.24s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:33<00:04, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.12s/it]\n",
"Doing inference...: 58% 14/24 [09:29<06:46, 40.66s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.81s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.39s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.25s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.19s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.14s/it]\n",
"Doing inference...: 62% 15/24 [10:10<06:06, 40.70s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.78s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.37s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.24s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.12s/it]\n",
"Doing inference...: 67% 16/24 [10:50<05:25, 40.65s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.82s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.40s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:34, 2.27s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.14s/it]\n",
"Doing inference...: 71% 17/24 [11:31<04:44, 40.71s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.78s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.36s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.23s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 75% 18/24 [12:12<04:04, 40.67s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.82s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.40s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:33, 2.26s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.15s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:28<00:10, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.14s/it]\n",
"Doing inference...: 79% 19/24 [12:52<03:23, 40.72s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.78s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.37s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.23s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:20, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:31<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.12s/it]\n",
"Doing inference...: 83% 20/24 [13:33<02:42, 40.68s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.82s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.40s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:33, 2.27s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.13s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:19, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:30<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 88% 21/24 [14:14<02:02, 40.69s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:47, 2.77s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:37, 2.36s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:06<00:33, 2.23s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.17s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:27, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 92% 22/24 [14:54<01:21, 40.69s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:02<00:48, 2.84s/it]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:04<00:38, 2.41s/it]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:07<00:34, 2.27s/it]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:09<00:30, 2.20s/it]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:11<00:28, 2.16s/it]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:13<00:25, 2.14s/it]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:15<00:23, 2.12s/it]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:17<00:21, 2.11s/it]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:19<00:18, 2.10s/it]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:21<00:16, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:23<00:14, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:25<00:12, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:27<00:10, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:29<00:08, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:32<00:06, 2.08s/it]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:34<00:04, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:36<00:02, 2.09s/it]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:38<00:00, 2.13s/it]\n",
"Doing inference...: 96% 23/24 [15:35<00:40, 40.69s/it]\n",
"Sample frames: 16: 0% 0/18 [00:00<?, ?it/s]\u001b[A\n",
"Sample frames: 16: 6% 1/18 [00:00<00:08, 1.99it/s]\u001b[A\n",
"Sample frames: 16: 11% 2/18 [00:00<00:07, 2.25it/s]\u001b[A\n",
"Sample frames: 16: 17% 3/18 [00:01<00:06, 2.35it/s]\u001b[A\n",
"Sample frames: 16: 22% 4/18 [00:01<00:05, 2.42it/s]\u001b[A\n",
"Sample frames: 16: 28% 5/18 [00:02<00:05, 2.45it/s]\u001b[A\n",
"Sample frames: 16: 33% 6/18 [00:02<00:04, 2.47it/s]\u001b[A\n",
"Sample frames: 16: 39% 7/18 [00:02<00:04, 2.49it/s]\u001b[A\n",
"Sample frames: 16: 44% 8/18 [00:03<00:04, 2.49it/s]\u001b[A\n",
"Sample frames: 16: 50% 9/18 [00:03<00:03, 2.49it/s]\u001b[A\n",
"Sample frames: 16: 56% 10/18 [00:04<00:03, 2.49it/s]\u001b[A\n",
"Sample frames: 16: 61% 11/18 [00:04<00:02, 2.50it/s]\u001b[A\n",
"Sample frames: 16: 67% 12/18 [00:04<00:02, 2.50it/s]\u001b[A\n",
"Sample frames: 16: 72% 13/18 [00:05<00:02, 2.50it/s]\u001b[A\n",
"Sample frames: 16: 78% 14/18 [00:05<00:01, 2.50it/s]\u001b[A\n",
"Sample frames: 16: 83% 15/18 [00:06<00:01, 2.51it/s]\u001b[A\n",
"Sample frames: 16: 89% 16/18 [00:06<00:00, 2.50it/s]\u001b[A\n",
"Sample frames: 16: 94% 17/18 [00:06<00:00, 2.49it/s]\u001b[A\n",
"Sample frames: 16: 100% 18/18 [00:07<00:00, 2.47it/s]\n",
"Doing inference...: 100% 24/24 [15:43<00:00, 39.30s/it]\n",
"Restoring 370 faces...\n",
"100% 370/370 [00:04<00:00, 91.08it/s]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!cat requirements.txt"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "E_RXZYL1AEAd",
"outputId": "a7dcb2b3-2626-4c6c-e85f-3174067dd0cc"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"torch==2.5.1\n",
"torchvision==0.20.1\n",
"--extra-index-url https://download.pytorch.org/whl/cu121\n",
"diffusers==0.32.2\n",
"transformers==4.48.0\n",
"decord==0.6.0\n",
"accelerate==0.26.1\n",
"einops==0.7.0\n",
"omegaconf==2.3.0\n",
"opencv-python==4.9.0.80\n",
"mediapipe==0.10.11\n",
"python_speech_features==0.6\n",
"librosa==0.10.1\n",
"scenedetect==0.6.1\n",
"ffmpeg-python==0.2.0\n",
"imageio==2.31.1\n",
"imageio-ffmpeg==0.5.1\n",
"lpips==0.1.4\n",
"face-alignment==1.4.1\n",
"gradio==5.24.0\n",
"huggingface-hub==0.30.2\n",
"numpy==1.26.4\n",
"kornia==0.8.0\n",
"insightface==0.7.3\n",
"onnxruntime-gpu==1.21.0\n",
"DeepCache==0.1.1"
]
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment