numz/sd-wav2lip-uhq

Issues

• 出售一份自己人工手动下载人脸数字人的数据集原始视频 ，视频分辨率1080-4k口播视频，可用于训练wav2lip-192，wav2lip-288，wav2lip-384，wav2lip-512，DINet-256，NeRF等模型。微信douzijun1999 请注明来意

  #133 opened 3 months ago by dousang1999
  0

• OSError: [WinError 126]

  #132 opened 4 months ago by kengao022
  0

• RuntimeError

  #131 opened 5 months ago by Battlecraft369
  0

• does not work in the normal resolution of the video result

  #130 opened 5 months ago by Mrfrize1
  1

• Number of frames available for inference: 936 then no run

  #99 opened a year ago by aistarman
  3

• Always getting IndexError

  #129 opened 6 months ago by javascriptdotexe
  0

• SD菜单栏没有显示wave2lip

  #128 opened 6 months ago by ZYOhub
  2

• cannot import name undefined from pydantic.fields

  #126 opened 7 months ago by aryansid
  2

• The Fix for Torch and GPU problem

  #86 opened a year ago by APCOTech
  31

• How to use the wav2lip studio through command line or the API ? The API's on automatic111 show only the built-in scripts. How can we add wav2lip in the API's ?

  #125 opened 7 months ago by shrangideqode
  0

• RuntimeError: Couldn't load custom C++ ops.

  #94 opened a year ago by itsmikepowers
  6

• What is the point in abusing the wav2lip open source project by listing this repo if you are hiding the real application behind a paywall on patreon?

  #123 opened 7 months ago by cantonalex
  0

• this extension killed my A1111 i have to install it again (maybe)

  #110 opened 10 months ago by mostafablender
  2

• upload timeout，file size：27.6M

  #122 opened 7 months ago by eMei0
  0

• Pay for stand alone version

  #121 opened 7 months ago by VitaliyAT
  0

• Automatic1111 Ext not work

  #114 opened 9 months ago by hoanghohotel
  3

• "Usage: Choose a video..." - but were is it at all ?

  #120 opened 7 months ago by VitaliyAT
  0

• Stuck in faceswap

  #119 opened 7 months ago by schauhan592
  0

• Who needs high-quality lip sync - contact me!

  #118 opened 7 months ago by Chechgroup
  0

• hi

  #117 opened 8 months ago by HASAN3DG
  0

• Suggestion to Extend Support for Comfy UI

  #96 opened a year ago by Iteravse
  2

• Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check

  #112 opened 9 months ago by hotdogarea
  7

• 是缺少模型吗？下载链接有吗

  #116 opened 8 months ago by 576196565
  0

• The mouth does not match on the X-axis. How can I fix this?

  #115 opened 9 months ago by Dipsio
  0

• TypeError: unsupported operand type(s) for -: 'NoneType' and 'int'

  #113 opened 9 months ago by hotdogarea
  0

• What is the required CUDA version to run this repo reliably?

  #106 opened a year ago by aerinkim
  1

• Torch not compiled with CUDA enabled

  #111 opened 9 months ago by hotdogarea
  3

• No module named 'scripts.wav2lip_uhq_extend_paths'

  #109 opened 10 months ago by emourdavid
  1

• 现在可以命令行运行吗？

  #108 opened 10 months ago by a614349007
  0

• What does this do?

  #107 opened 10 months ago by Sora233
  0

• Stable Diffusion WEBUI stop working after installing "sd-wav2lip-uhq". CUDA TorchAudio issue. On clean- new virtual env.

  #98 opened a year ago by 0Core
  7

• ValueError: max() arg is an empty sequence

  #105 opened a year ago by enragedshoe
  3

• timers just continue, never processes.

  #102 opened a year ago by JustCann
  3

• ImportError: numpy.core.multiarray failed to import

  #104 opened a year ago by NC17z
  0

• RuntimeError: Detected that PyTorch and TorchAudio were compiled with different CUDA versions. PyTorch has CUDA version 11.8 whereas TorchAudio has CUDA version 11.7.

  #103 opened a year ago by AK51
  1

• 希望作者能出一个版本 脱离sd的，只想要这一个功能 sd 又特别笨重

  #82 opened a year ago by 1229064537
  7

• conda Conflict

  #100 opened a year ago by chaorenai
  7

• wav2lip_gan model error

  #101 opened a year ago by U-DI-Page
  0

• moov atom not found / float division by zero

  #97 opened a year ago by GsHeri
  2

• 期待支持 wav2lip-288

  #95 opened a year ago by tailangjun
  0

• RuntimeError: Couldn't load custom C++ ops. This can happen if your PyTorch and torchvision versions are incompatible, or if you had errors while compiling torchvision from source.

  #84 opened a year ago by ABZig
  2

• Is it possible to not use/install bark at all???? It's causing problems and errors: (ValueError: need at least one array to concatenate)

  #87 opened a year ago by AIhasArrived
  2

• issue withe the colab version

  #92 opened a year ago by Sadrahel
  0

• The video went blurry after the face swap

  #91 opened a year ago by wang-ba-ba
  0

• RuntimeError: unexpected EOF, expected 45345 more bytes. The file might be corrupted.

  #90 opened a year ago by Song367
  0

• How much time do you need to lip sync a 10 sec or 1 minute video?

  #89 opened a year ago by AIhasArrived
  2

• Can I install an older version that does not have BARK?

  #88 opened a year ago by AIhasArrived
  3

• RuntimeError: Torch is not able to use GPU

  #81 opened a year ago by prezofpizza
  9

• fatal: unable to access 'https://github.com/numz/sd-wav2lip-uhq/': Recv failure: Connection was reset '

  #83 opened a year ago by Pancat007
  3

• Time out uploading data to server

  #85 opened a year ago by enterprisium
  0