算力云平台部署—SadTalker的AI数字人视频

选择算力

部署选择

选择镜像

 

机器管理

 

控制台

 

 通过平台工具进入服务器

认识管理系统

打开命令行

进入目录 stable-diffusion-webui#

cd

增加执行权限

chmod +x ./webui.sh

 运行命令

bash ./webui.sh

sudo apt install -y python3 python3-venv git

安装软件

1. Creating the env and install the requirements.

git clone https://github.com/OpenTalker/SadTalker.git

cd SadTalker 

conda create -n sadtalker python=3.8

conda activate sadtalker

pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113

conda install ffmpeg

pip install -r requirements.txt

 

运行安装环境

pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113

conda install ffmpeg

pip install -r requirements.txt

### Coqui TTS is optional for gradio demo. 
### pip install TTS

 系统盘不够用

目录结构

╔═════════════════╦════════╦════╦═════════════════════════════════════════════════════════════════════════╗
║目录             ║名称    ║速度║说明                                                                     ║
╠═════════════════╬════════╬════╬═════════════════════════════════════════════════════════════════════════╣
║/                ║系 统 盘║一般║实例关机数据不会丢失，可存放代码等。会随保存镜像一起保存。               ║
║/root/autodl-tmp ║数 据 盘║ 快 ║实例关机数据不会丢失，可存放读写IO要求高的数据。但不会随保存镜像一起保存 ║
║/root/autodl-nas ║网    盘║ 慢 ║可以实现多实例间的文件同步共享，不受实例开关机和保存镜像的影响。         ║
║/root/autodl-fs  ║文件存储║一般║可以实现多实例间的文件同步共享，不受实例开关机和保存镜像的影响。         ║
╚═════════════════╩════════╩════╩═════════════════════════════════════════════════════════════════════════╝
cat: /sys/fs/cgroup/cpu/cpu.cfs_quota_us: No such file or directory

移动数据到数据盘 

mv ./sadtalker/ /root/autodl-tmp/cyberwin/

查看目录

ls

迁移成功

 

资源和路径

 

                                                                                       
# All requested packages already installed.                                             
                                                                                        
(sadtalker) root@autodl-container-a37840aad8-029fab27:~/autodl-tmp/cyberwin/SadTalker# pip install -r requirements.txt           
Looking in indexes: https://mirrors.aliyun.com/pypi/simple
Collecting numpy==1.23.4 (from -r requirements.txt (line 1))
  Downloading https://mirrors.aliyun.com/pypi/packages/56/df/2f6016171ebce9875e7de0292a2131bea86e0340607a313a04b332d35c8e/numpy-1.23.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.1/17.1 MB 13.3 MB/s eta 0:00:00
Collecting face_alignment==1.3.5 (from -r requirements.txt (line 2))
  Downloading https://mirrors.aliyun.com/pypi/packages/a1/d1/572b8580cfb026b508e8edbfdafca0e119dfd9b963cc0987db50fe0e5d11/face_alignment-1.3.5-py2.py3-none-any.whl (29 kB)
Collecting imageio==2.19.3 (from -r requirements.txt (line 3))
  Downloading https://mirrors.aliyun.com/pypi/packages/b6/78/3cf2f60ef319d253d71870c6cb00774bfc5bdccf9e06c319678388f58f41/imageio-2.19.3-py3-none-any.whl (3.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.4/3.4 MB 12.5 MB/s eta 0:00:00
Collecting imageio-ffmpeg==0.4.7 (from -r requirements.txt (line 4))
  Downloading https://mirrors.aliyun.com/pypi/packages/e5/3b/fdf3e75462e93b7806ffecad6c5aa35f2cc76b9f2faaedf5e43194ceff09/imageio_ffmpeg-0.4.7-py3-none-manylinux2010_x86_64.whl (26.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 26.9/26.9 MB 9.9 MB/s eta 0:00:00
Collecting librosa==0.9.2 (from -r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/e4/1c/23ef2fd02913d65d43dc7516fc829af709314a66c6f0bdc2e361fdcecc2d/librosa-0.9.2-py3-none-any.whl (214 kB)
Collecting numba (from -r requirements.txt (line 6))
  Downloading https://mirrors.aliyun.com/pypi/packages/6e/03/c658004b4b4d52dca7a74582e9fc3e20f94c17cb4b797eb3601876759540/numba-0.58.1-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (3.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.7/3.7 MB 12.0 MB/s eta 0:00:00
Collecting resampy==0.3.1 (from -r requirements.txt (line 7))
  Downloading https://mirrors.aliyun.com/pypi/packages/51/7e/7aec4c54c4b11ac8333dc01d0e910e692be7da944769e37f9e248537a3f1/resampy-0.3.1-py3-none-any.whl (3.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.1/3.1 MB 11.6 MB/s eta 0:00:00
Collecting pydub==0.25.1 (from -r requirements.txt (line 8))
  Downloading https://mirrors.aliyun.com/pypi/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl (32 kB)
Collecting scipy==1.10.1 (from -r requirements.txt (line 9))
  Downloading https://mirrors.aliyun.com/pypi/packages/69/f0/fb07a9548e48b687b8bf2fa81d71aba9cfc548d365046ca1c791e24db99d/scipy-1.10.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (34.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 34.5/34.5 MB 12.4 MB/s eta 0:00:00
Collecting kornia==0.6.8 (from -r requirements.txt (line 10))
  Downloading https://mirrors.aliyun.com/pypi/packages/99/03/3578e2f34d4ed63649bad6b15f9001d2d244e1f92c60a8dd5c5436e4402d/kornia-0.6.8-py2.py3-none-any.whl (551 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 551.1/551.1 kB 17.4 MB/s eta 0:00:00
Collecting tqdm (from -r requirements.txt (line 11))
  Downloading https://mirrors.aliyun.com/pypi/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl (78 kB)
Collecting yacs==0.1.8 (from -r requirements.txt (line 12))
  Downloading https://mirrors.aliyun.com/pypi/packages/38/4f/fe9a4d472aa867878ce3bb7efb16654c5d63672b86dc0e6e953a67018433/yacs-0.1.8-py3-none-any.whl (14 kB)
Collecting pyyaml (from -r requirements.txt (line 13))
  Downloading https://mirrors.aliyun.com/pypi/packages/fd/7f/2c3697bba5d4aa5cc2afe81826d73dfae5f049458e44732c7a0938baa673/PyYAML-6.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (746 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 746.5/746.5 kB 16.7 MB/s eta 0:00:00
Collecting joblib==1.1.0 (from -r requirements.txt (line 14))
  Downloading https://mirrors.aliyun.com/pypi/packages/3e/d5/0163eb0cfa0b673aa4fe1cd3ea9d8a81ea0f32e50807b0c295871e4aab2e/joblib-1.1.0-py2.py3-none-any.whl (306 kB)
Collecting scikit-image==0.19.3 (from -r requirements.txt (line 15))
  Downloading https://mirrors.aliyun.com/pypi/packages/96/11/878ee6757f75835c396fbdd934ca8e1a1681553ac0925fbf77065c9618e5/scikit_image-0.19.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (14.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.0/14.0 MB 12.8 MB/s eta 0:00:00
Collecting basicsr==1.4.2 (from -r requirements.txt (line 16))
  Downloading https://mirrors.aliyun.com/pypi/packages/86/41/00a6b000f222f0fa4c6d9e1d6dcc9811a374cabb8abb9d408b77de39648c/basicsr-1.4.2.tar.gz (172 kB)
  Preparing metadata (setup.py) ... done
Collecting facexlib==0.3.0 (from -r requirements.txt (line 17))
  Downloading https://mirrors.aliyun.com/pypi/packages/36/7b/2147339dafe1c4800514c9c21ee4444f8b419ce51dfc7695220a8e0069a6/facexlib-0.3.0-py3-none-any.whl (59 kB)
Collecting gradio (from -r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/3f/6e/c0726e138f64cd98379a7bf95f4f3b15dd5a9f004b172540cee5653ec820/gradio-4.44.1-py3-none-any.whl (18.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 18.1/18.1 MB 12.3 MB/s eta 0:00:00
Collecting gfpgan (from -r requirements.txt (line 19))
  Downloading https://mirrors.aliyun.com/pypi/packages/80/a2/84bb50a2655fda1e6f35ae57399526051b8a8b96ad730aea82abeaac4de8/gfpgan-1.3.8-py3-none-any.whl (52 kB)
Collecting av (from -r requirements.txt (line 20))
  Downloading https://mirrors.aliyun.com/pypi/packages/b1/32/186d20f016c549e095c5cb2fb2ac5dbc7c89d4dc699b84b592f65cc1004b/av-12.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 33.7/33.7 MB 12.7 MB/s eta 0:00:00
Collecting safetensors (from -r requirements.txt (line 21))
  Downloading https://mirrors.aliyun.com/pypi/packages/a6/f8/dae3421624fcc87a89d42e1898a798bc7ff72c61f38973a65d60df8f124c/safetensors-0.5.3-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (471 kB)
Requirement already satisfied: torch in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from face_alignment==1.3.5->-r requirements.txt (line 2)) (1.12.1+cu113)
Collecting opencv-python (from face_alignment==1.3.5->-r requirements.txt (line 2))
  Downloading https://mirrors.aliyun.com/pypi/packages/2c/8b/90eb44a40476fa0e71e05a0283947cfd74a5d36121a11d926ad6f3193cc4/opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (63.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 63.0/63.0 MB 12.6 MB/s eta 0:00:00
Requirement already satisfied: pillow>=8.3.2 in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from imageio==2.19.3->-r requirements.txt (line 3)) (10.4.0)
Collecting audioread>=2.1.9 (from librosa==0.9.2->-r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/57/8d/30aa32745af16af0a9a650115fbe81bde7c610ed5c21b381fca0196f3a7f/audioread-3.0.1-py3-none-any.whl (23 kB)
Collecting scikit-learn>=0.19.1 (from librosa==0.9.2->-r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/3f/48/6fdd99f5717045f9984616b5c2ec683d6286d30c0ac234563062132b83ab/scikit_learn-1.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.1/11.1 MB 11.0 MB/s eta 0:00:00
Collecting decorator>=4.0.10 (from librosa==0.9.2->-r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/4e/8c/f3147f5c4b73e7550fe5f9352eaa956ae838d5c51eb58e7a25b9f3e2643b/decorator-5.2.1-py3-none-any.whl (9.2 kB)
Collecting soundfile>=0.10.2 (from librosa==0.9.2->-r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/57/5e/70bdd9579b35003a489fc850b5047beeda26328053ebadc1fb60f320f7db/soundfile-0.13.1-py2.py3-none-manylinux_2_28_x86_64.whl (1.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 10.9 MB/s eta 0:00:00
Collecting pooch>=1.0 (from librosa==0.9.2->-r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/a8/87/77cc11c7a9ea9fd05503def69e3d18605852cd0d4b0d3b8f15bbeb3ef1d1/pooch-1.8.2-py3-none-any.whl (64 kB)
Collecting packaging>=20.0 (from librosa==0.9.2->-r requirements.txt (line 5))
  Downloading https://mirrors.aliyun.com/pypi/packages/88/ef/eb23f262cca3c0c4eb7ab1933c3b1f03d021f2c48f54763065b6f0e321be/packaging-24.2-py3-none-any.whl (65 kB)
Collecting networkx>=2.2 (from scikit-image==0.19.3->-r requirements.txt (line 15))
  Downloading https://mirrors.aliyun.com/pypi/packages/a8/05/9d4f9b78ead6b2661d6e8ea772e111fc4a9fbd866ad0c81906c11206b55e/networkx-3.1-py3-none-any.whl (2.1 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.1/2.1 MB 10.0 MB/s eta 0:00:00
Collecting tifffile>=2019.7.26 (from scikit-image==0.19.3->-r requirements.txt (line 15))
  Downloading https://mirrors.aliyun.com/pypi/packages/06/a3/68d17088a4f09565bc7341fd20490da8191ec4cddde479daaabbe07bb603/tifffile-2023.7.10-py3-none-any.whl (220 kB)
Collecting PyWavelets>=1.1.1 (from scikit-image==0.19.3->-r requirements.txt (line 15))
  Downloading https://mirrors.aliyun.com/pypi/packages/88/4b/b2b2a6f51e47c091c221bfde976a01a7e5f20e7e5e6341b2b9c4db73d2ed/PyWavelets-1.4.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (6.9 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.9/6.9 MB 10.9 MB/s eta 0:00:00
Collecting addict (from basicsr==1.4.2->-r requirements.txt (line 16))
  Downloading https://mirrors.aliyun.com/pypi/packages/6a/00/b08f23b7d7e1e14ce01419a467b583edbb93c6cdb8654e54a9cc579cd61f/addict-2.4.0-py3-none-any.whl (3.8 kB)
Collecting future (from basicsr==1.4.2->-r requirements.txt (line 16))
  Downloading https://mirrors.aliyun.com/pypi/packages/da/71/ae30dadffc90b9006d77af76b393cb9dfbfc9629f339fc1574a1c52e6806/future-1.0.0-py3-none-any.whl (491 kB)
Collecting lmdb (from basicsr==1.4.2->-r requirements.txt (line 16))
  Downloading https://mirrors.aliyun.com/pypi/packages/cc/3f/4695cd583487ff24637987526099c0ce5543afb1e48dfacd9d498bc0d16b/lmdb-1.6.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (294 kB)
Requirement already satisfied: requests in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from basicsr==1.4.2->-r requirements.txt (line 16)) (2.32.3)
Collecting tb-nightly (from basicsr==1.4.2->-r requirements.txt (line 16))
  Downloading https://mirrors.aliyun.com/pypi/packages/76/b6/d68769a2f0304c7442712fbde8aced9e03f403bc26c958f3fbf3996d68b7/tb_nightly-2.14.0a20230808-py3-none-any.whl (5.5 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.5/5.5 MB 9.3 MB/s eta 0:00:00
Requirement already satisfied: torchvision in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from basicsr==1.4.2->-r requirements.txt (line 16)) (0.13.1+cu113)
Collecting yapf (from basicsr==1.4.2->-r requirements.txt (line 16))
  Downloading https://mirrors.aliyun.com/pypi/packages/37/81/6acd6601f61e31cfb8729d3da6d5df966f80f374b78eff83760714487338/yapf-0.43.0-py3-none-any.whl (256 kB)
Collecting filterpy (from facexlib==0.3.0->-r requirements.txt (line 17))
  Downloading https://mirrors.aliyun.com/pypi/packages/f6/1d/ac8914360460fafa1990890259b7fa5ef7ba4cd59014e782e4ab3ab144d8/filterpy-1.4.5.zip (177 kB)
  Preparing metadata (setup.py) ... done
Collecting llvmlite<0.42,>=0.41.0dev0 (from numba->-r requirements.txt (line 6))
  Downloading https://mirrors.aliyun.com/pypi/packages/46/a5/de824aba87a62e0da43f9b590ac91709d460a61e03f1b430b83ca64b76dc/llvmlite-0.41.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (43.6 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 43.6/43.6 MB 9.9 MB/s eta 0:00:00
Collecting importlib-metadata (from numba->-r requirements.txt (line 6))
  Downloading https://mirrors.aliyun.com/pypi/packages/a0/d9/a1e041c5e7caa9a05c925f4bdbdfb7f006d1f74996af53467bc394c97be7/importlib_metadata-8.5.0-py3-none-any.whl (26 kB)
Collecting aiofiles<24.0,>=22.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/c5/19/5af6804c4cc0fed83f47bff6e413a98a36618e7d40185cd36e69737f3b0e/aiofiles-23.2.1-py3-none-any.whl (15 kB)
Collecting anyio<5.0,>=3.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/1b/b4/f7e396030e3b11394436358ca258a81d6010106582422f23443c16ca1873/anyio-4.5.2-py3-none-any.whl (89 kB)
Collecting fastapi<1.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/50/b3/b51f09c2ba432a576fe63758bddc81f78f0c6309d9e5c10d194313bf021e/fastapi-0.115.12-py3-none-any.whl (95 kB)
Collecting ffmpy (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/53/5d/65f40bd333463b3230b3a72d93873caaf49b0cbb5228598fafb75fcc5357/ffmpy-0.5.0-py3-none-any.whl (6.0 kB)
Collecting gradio-client==1.3.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/de/fe/7e9cb4d0e6aa74268fa31089189e4855882a0f2a36c45d359336946d4ae1/gradio_client-1.3.0-py3-none-any.whl (318 kB)
Collecting httpx>=0.24.1 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl (73 kB)
Collecting huggingface-hub>=0.19.3 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/93/27/1fb384a841e9661faad1c31cbfa62864f59632e876df5d795234da51c395/huggingface_hub-0.30.2-py3-none-any.whl (481 kB)
Collecting importlib-resources<7.0,>=1.3 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/e1/6a/4604f9ae2fa62ef47b9de2fa5ad599589d28c9fd1d335f32759813dfa91e/importlib_resources-6.4.5-py3-none-any.whl (36 kB)
Collecting jinja2<4.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl (134 kB)
Collecting markupsafe~=2.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/c7/bd/50319665ce81bb10e90d1cf76f9e1aa269ea6f7fa30ab4521f14d122a3df/MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (26 kB)
Collecting matplotlib~=3.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/30/33/cc27211d2ffeee4fd7402dca137b6e8a83f6dcae3d4be8d0ad5068555561/matplotlib-3.7.5-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (9.2 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 9.2/9.2 MB 9.5 MB/s eta 0:00:00
Collecting orjson~=3.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/72/3c/2e26157d69d127c5663cdaa53a31860ca0df0a9a89ece81c81800ef99490/orjson-3.10.15-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)
Collecting pandas<3.0,>=1.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/f8/7f/5b047effafbdd34e52c9e2d7e44f729a0655efafb22198c45cf692cdc157/pandas-2.0.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.4/12.4 MB 6.5 MB/s eta 0:00:00
Collecting pydantic>=2.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/f4/3c/8cc1cc84deffa6e25d2d0c688ebb80635dfdbf1dbea3e30c541c8cf4d860/pydantic-2.10.6-py3-none-any.whl (431 kB)
Collecting python-multipart>=0.0.9 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/45/58/38b5afbc1a800eeea951b9285d3912613f2603bdf897a4ab0f4bd7f405fc/python_multipart-0.0.20-py3-none-any.whl (24 kB)
Collecting ruff>=0.2.2 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/79/89/0af10c8af4363304fd8cb833bd407a2850c760b71edf742c18d5a87bb3ad/ruff-0.11.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.4 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.4/11.4 MB 10.7 MB/s eta 0:00:00
Collecting semantic-version~=2.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/6a/23/8146aad7d88f4fcb3a6218f41a60f6c2d4e3a72de72da1825dc7c8f7877c/semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)
Collecting tomlkit==0.12.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/68/4f/12207897848a653d03ebbf6775a29d949408ded5f99b2d87198bc5c93508/tomlkit-0.12.0-py3-none-any.whl (37 kB)
Collecting typer<1.0,>=0.12 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/7f/fc/5b29fea8cee020515ca82cc68e3b8e1e34bb19a3535ad854cac9257b414c/typer-0.15.2-py3-none-any.whl (45 kB)
Requirement already satisfied: typing-extensions~=4.0 in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from gradio->-r requirements.txt (line 18)) (4.13.2)
Requirement already satisfied: urllib3~=2.0 in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from gradio->-r requirements.txt (line 18)) (2.2.3)
Collecting uvicorn>=0.14.0 (from gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/98/79/2e2620337ef1e4ef7a058b351603b765f59ac28e6e3ac7c5e7cdee9ea1ab/uvicorn-0.33.0-py3-none-any.whl (62 kB)
Collecting fsspec (from gradio-client==1.3.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/56/53/eb690efa8513166adef3e0669afd31e95ffde69fb3c52ec2ac7223ed6018/fsspec-2025.3.0-py3-none-any.whl (193 kB)
Collecting websockets<13.0,>=10.0 (from gradio-client==1.3.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/e9/bc/646bfbd9badbf59efb48db7265b097e9f626c3530c9d1329a826ef4db6a0/websockets-12.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)
Requirement already satisfied: idna>=2.8 in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from anyio<5.0,>=3.0->gradio->-r requirements.txt (line 18)) (3.10)
Collecting sniffio>=1.1 (from anyio<5.0,>=3.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl (10 kB)
Collecting exceptiongroup>=1.0.2 (from anyio<5.0,>=3.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/02/cc/b7e31358aac6ed1ef2bb790a9746ac2c69bcb3c8588b41616914eb106eaf/exceptiongroup-1.2.2-py3-none-any.whl (16 kB)
Collecting starlette<0.47.0,>=0.40.0 (from fastapi<1.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/b6/c5/7ae467eeddb57260c8ce17a3a09f9f5edba35820fc022d7c55b7decd5d3a/starlette-0.44.0-py3-none-any.whl (73 kB)
Requirement already satisfied: certifi in /root/miniconda3/envs/sadtalker/lib/python3.8/site-packages (from httpx>=0.24.1->gradio->-r requirements.txt (line 18)) (2025.1.31)
Collecting httpcore==1.* (from httpx>=0.24.1->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/18/8d/f052b1e336bb2c1fc7ed1aaed898aa570c0b61a09707b108979d9fc6e308/httpcore-1.0.8-py3-none-any.whl (78 kB)
Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/95/04/ff642e65ad6b90db43e668d70ffb6736436c7ce41fcc549f4e9472234127/h11-0.14.0-py3-none-any.whl (58 kB)
Collecting filelock (from huggingface-hub>=0.19.3->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/b9/f8/feced7779d755758a52d1f6635d990b8d98dc0a29fa568bbe0625f18fdf3/filelock-3.16.1-py3-none-any.whl (16 kB)
Collecting zipp>=3.1.0 (from importlib-resources<7.0,>=1.3->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/62/8b/5ba542fa83c90e09eac972fc9baca7a88e7e7ca4b221a89251954019308b/zipp-3.20.2-py3-none-any.whl (9.2 kB)
Collecting contourpy>=1.0.1 (from matplotlib~=3.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/8e/71/7f20855592cc929bc206810432b991ec4c702dc26b0567b132e52c85536f/contourpy-1.1.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB)
Collecting cycler>=0.10 (from matplotlib~=3.0->gradio->-r requirements.txt (line 18))
  Downloading https://mirrors.aliyun.com/pypi/packages/e7/05/c19819d5e3d95294a6f5947fb9b9629efb316b96de511b418c53d245aae6/cycler-0.12.1-py3-none-any.whl (8.3 kB)

安装网页

Install script for SadTalker + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on root user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launcher.py...
################################################################
Python 3.8.20 (default, Oct  3 2024, 15:24:27) 
[GCC 11.2.0]
Commit hash: cd4c0465ae0b54a6f85af57f5c65fec9fe23e7f8
Installing torch and torchvision
Looking in indexes: https://mirrors.aliyun.com/pypi/simple, https://download.pytorch.org/whl/cu113
Collecting torch==1.12.1+cu113
  Downloading https://download.pytorch.org/whl/cu113/torch-1.12.1%2Bcu113-cp38-cp38-linux_x86_64.whl (1837.7 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╸━━━━━━━ 1.5/1.8 GB 16.5 MB/s eta 0:00:20ERROR: Could not install packages due to an OSError: [Errno 28] No space left on device

下载模型

Windows

A video tutorial in chinese is available here. You can also follow the following instructions:

1. Install Python 3.8 and check "Add Python to PATH".
2. Install git manually or using Scoop: scoop install git.
3. Install ffmpeg, following this tutorial or using scoop: scoop install ffmpeg.
4. Download the SadTalker repository by running git clone https://github.com/Winfredy/SadTalker.git.
5. Download the checkpoints and gfpgan models in the downloads section.
6. Run start.bat from Windows Explorer as normal, non-administrator, user, and a Gradio-powered WebUI demo will be started.

macOS

A tutorial on installing SadTalker on macOS can be found here.

Docker, WSL, etc

Please check out additional tutorials here.

2. Download Models

You can run the following script on Linux/macOS to automatically download all the models:

bash scripts/download_models.sh

We also provide an offline patch (gfpgan/), so no model will be downloaded when generating.

Pre-Trained Models

• Google Drive
• GitHub Releases
• Baidu (百度云盘) (Password: sadt)

GFPGAN Offline Patch

• Google Drive
• GitHub Releases
• Baidu (百度云盘) (Password: sadt)

Model Details

Model explains:

New version

Model	Description
checkpoints/mapping_00229-model.pth.tar	Pre-trained MappingNet in Sadtalker.
checkpoints/mapping_00109-model.pth.tar	Pre-trained MappingNet in Sadtalker.
checkpoints/SadTalker_V0.0.2_256.safetensors	packaged sadtalker checkpoints of old version, 256 face render).
checkpoints/SadTalker_V0.0.2_512.safetensors	packaged sadtalker checkpoints of old version, 512 face render).
gfpgan/weights	Face detection and enhanced models used in facexlib and gfpgan.

Old version

Model	Description
checkpoints/auido2exp_00300-model.pth	Pre-trained ExpNet in Sadtalker.
checkpoints/auido2pose_00140-model.pth	Pre-trained PoseVAE in Sadtalker.
checkpoints/mapping_00229-model.pth.tar	Pre-trained MappingNet in Sadtalker.
checkpoints/mapping_00109-model.pth.tar	Pre-trained MappingNet in Sadtalker.
checkpoints/facevid2vid_00189-model.pth.tar	Pre-trained face-vid2vid model from the reappearance of face-vid2vid.
checkpoints/epoch_20.pth	Pre-trained 3DMM extractor in Deep3DFaceReconstruction.
checkpoints/wav2lip.pth	Highly accurate lip-sync model in Wav2lip.
checkpoints/shape_predictor_68_face_landmarks.dat	Face landmark model used in dilb.
checkpoints/BFM	3DMM library file.
checkpoints/hub	Face detection models used in face alignment.
gfpgan/weights	Face detection and enhanced models used in facexlib and gfpgan.

The final folder will be shown as:

3. Quick Start

Please read our document on best practices and configuration tips

WebUI Demos

Online Demo: HuggingFace | SDWebUI-Colab | Colab

Local WebUI extension: Please refer to WebUI docs.

Local gradio demo (recommanded): A Gradio instance similar to our Hugging Face demo can be run locally:

## you need manually install TTS(https://github.com/coqui-ai/TTS) via `pip install tts` in advanced.
python app_sadtalker.py

You can also start it more easily:

• windows: just double click webui.bat, the requirements will be installed automatically.
• Linux/Mac OS: run bash webui.sh to start the webui.

CLI usage

Animating a portrait image from default config:

python inference.py --driven_audio <audio.wav> \
                    --source_image <video.mp4 or picture.png> \
                    --enhancer gfpgan 

The results will be saved in results/$SOME_TIMESTAMP/*.mp4.

Full body/image Generation:

Using --still to generate a natural full body video. You can add enhancer to improve the quality of the generated video.

python inference.py --driven_audio <audio.wav> \
                    --source_image <video.mp4 or picture.png> \
                    --result_dir <a file to store results> \
                    --still \
                    --preprocess full \
                    --enhancer gfpgan