LivePortrait Upgraded Latest Version Human and Animal Version 1-Click Installers for Windows, RunPod, Massed Compute and a Free Kaggle Account Notebook

Furkan Gözükara

hi i just made a fresh install and it works. probably your downloads failed for some reason. run installer again and email me all logs : monstermmorpg@gmail.com

Kevin Treman

I am getting the following error? Please select an option: 1. Human Live Portrait 2. Animal Live Portrait Enter your choice (1 or 2): 1 Starting Human Live Portrait... Traceback (most recent call last): File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\app_secourses.py", line 55, in gradio_pipeline = GradioPipeline( File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\src\gradio_pipeline.py", line 42, in __init__ super().__init__(inference_cfg, crop_cfg) File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\src\live_portrait_pipeline.py", line 38, in __init__ self.live_portrait_wrapper: LivePortraitWrapper = LivePortraitWrapper(inference_cfg=inference_cfg) File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\src\live_portrait_wrapper.py", line 45, in __init__ self.appearance_feature_extractor = load_model(inference_cfg.checkpoint_F, model_config, self.device, 'appearance_feature_extractor') File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\src\utils\helper.py", line 170, in load_model model.load_state_dict(torch.load(ckpt_path, map_location=lambda storage, loc: storage)) File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\venv\lib\site-packages\torch\serialization.py", line 1479, in load with _open_file_like(f, "rb") as opened_file: File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\venv\lib\site-packages\torch\serialization.py", line 759, in _open_file_like return _open_file(name_or_buffer, mode) File "C:\Users\kevin\Downloads\LP_V21\LivePortrait\venv\lib\site-packages\torch\serialization.py", line 740, in __init__ super().__init__(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\kevin\\Downloads\\LP_V21\\LivePortrait\\src\\config\\../../pretrained_weights/liveportrait/base_models/appearance_feature_extractor.pth' Press any key to continue . . .

Furkan Gözükara

you have to setup your linux machine exactly as in windows tutorial. if you are not pro user please use windows : https://youtu.be/DrhUHnYfwC0

eyal giron

~/AI/LP_V21/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops on  main ⌚ 10:34:50 $ python3 setup.py build install Traceback (most recent call last): File "/home/eyal/AI/LP_V21/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/setup.py", line 71, in ext_modules=get_extensions(), File "/home/eyal/AI/LP_V21/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/setup.py", line 49, in get_extensions raise NotImplementedError('Cuda is not availabel') NotImplementedError: Cuda is not availabel it's fail at the last step in the installation

Furkan Gözükara

hi this video is still up to date when you follow its patreon source links : https://youtu.be/DrhUHnYfwC0

Taiga

I went all the way through your cuda/python/c++ video. I performed the live portrait install. when I ran it, I got this: To create a public link, set `share=True` in `launch()`. Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call last): File "C:\Python310\lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "C:\Python310\lib\asyncio\proactor_events.py", line 165, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call last): File "C:\Python310\lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "C:\Python310\lib\asyncio\proactor_events.py", line 165, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

Furkan Gözükara

make a fresh install.

Tobe2d

I have LP_V15 and when I run Windows_Update_Version.bat I get: Already up to date. Version updated. Please restart the running app In some cases if there are new library updates you need to reinstall To do that you can delete venv and run installer again or completely reinstall Press any key to continue . . . Cant I update to V18 from 15?

Furkan Gözükara

hi first follow this video every step. then first run install to install. looks like you didnt install or you dont have even git installed : https://youtu.be/DrhUHnYfwC0

Ander Vazquez

After installing live portrait and running windows_start_app.bat I am receiveing the following error and Live portrait is not running, any clues: Please select an option: 1. Human Live Portrait 2. Animal Live Portrait Enter your choice (1 or 2): 1 Starting Human Live Portrait... C:\Python310\python.exe: can't open file 'C:\\LP_V16\\LivePortrait\\app_secourses.py': [Errno 2] No such file or directory Press any key to continue . . .

Furkan Gözükara

hi what is your question? sorry for late reply

John Paschal

Furkan Gözükara

great

The AI Diva

yay! all working thnks

Furkan Gözükara

just updated to live share please download v16

The AI Diva

Ok will re try this it looked the same as the January LP Kaggle? It still uses ngrok…I thought you had a way to public launch with no ngrok in another post? Thx

Furkan Gözükara

i updated kaggle notebook you will see :) it works perfect

The AI Diva

hi - is there any change to the kaggle notebook or is the same as Jan? thanks

Furkan Gözükara

currently we are using official repo. they keep adding new stuff. can you make a request post here? https://github.com/KwaiVGI/LivePortrait/issues

Dmitry

Please add the save emotion settings on photos option. So that they can be loaded as styles. For different photos, and if you add the ability to batch process photos according to the selected style of emotions, it will be great in general)

Furkan Gözükara

this new version download new models so i recommend make fresh install

Dmitry

Hello, is it enough to delete the old "venv" folder of the previous version and run a new installation script to update the application? Or I need to update it in a different way. I don't want to download all the models again

Furkan Gözükara

yes we have : https://youtu.be/FPtpNrmuwXk newest app has more features but it is rather easy to use check above screenshots too

Mehmet Atakan Çavuşlu

Is there youtube tutorial for this?

Furkan Gözükara

you mean hugging face spaces? i recommend massed compute

The AI Diva

hey great work! would love to see a hugging face install guide for this

Furkan Gözükara

this error shouldn't happen. you have missing pieces in your requirements : https://youtu.be/DrhUHnYfwC0

Anshul Gupta

no soultion for this error is not in this video

Furkan Gözükara

yep solution easy. follow this tutorial every single step. after that reinstall and will work. it happens when you have error due to missing requirements during install : https://youtu.be/DrhUHnYfwC0

Anshul Gupta

Live portrait v14 Throwing error No module named 'MultiScaleDeformableAttention' when running with option 2 of the animal version. live portrait. i tried to install this module in virtual environment but could not