ali-vilab/dreamtalk

Issues

• An alternative project EchoMimicV2 is open-sourced

  #53 opened a month ago by lymhust
  0

• Training

  #44 opened 8 months ago by pranav-ap
  3

• Lip Sync

  #48 opened 7 months ago by Chechgroup
  1

• torchaudio C++ extension is not available.

  #52 opened 3 months ago by nitinmukesh
  0

• Error when using Nvidia GPU.

  #50 opened 5 months ago by Toolfolks
  2

• disable cropping in ui

  #46 opened 7 months ago by FitzWong100
  1

• RuntimeError: Expected 3-dimensional

  #25 opened a year ago by NolenBrolen
  1

• How do I use 512 X 512

  #51 opened 5 months ago by Toolfolks
  0

• how to redownload Voxceleb2

  #8 opened a year ago by Droliven
  2

• Some weights of the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']

  #31 opened 10 months ago by Yazdi9
  3

• RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

  #12 opened a year ago by spstrademark
  5

• RuntimeError: nvrtc: error: invalid value for --gpu-architecture (-arch) nvrtc compilation failed:

  #38 opened 9 months ago by b0b6a
  3

• 有没有可以使用全身照片的项目推荐？

  #47 opened 7 months ago by ygxdx
  1

• network issues

  #45 opened 8 months ago by lifeng5658
  0

• Training Script

  #43 opened 8 months ago by pranav-ap
  0

• TypeError: can only concatenate str (not "bool") to str

  #42 opened 9 months ago by Yazdi9
  0

• subprocess.CalledProcessError: Command '['python', 'inference_for_demo_video.py'

  #41 opened 9 months ago by Yazdi9
  0

• pose mat

  #40 opened 9 months ago by kackbob
  0

• Parameter function

  #39 opened 9 months ago by kackbob
  0

• What config required to run it real-time?

  #18 opened a year ago by shubham-dayma
  2

• nvrtc compilation failed

  #3 opened a year ago by StartHua
  5

• av.codec.codec.UnknownCodecError: libx264

  #37 opened 10 months ago by Yazdi9
  0

• TypeError: __call__(): incompatible function arguments. The following argument types are supported: 1. (self: _dlib_pybind11.fhog_object_detector, image: numpy.ndarray, upsample_num_times: int = 0) -> _dlib_pybind11.rectangles

  #36 opened 10 months ago by Yazdi9
  0

• av.error.FileNotFoundError: [Errno 2] No such file or directory

  #35 opened 10 months ago by Yazdi9
  0

• RuntimeError: Sizes of tensors must match except in dimension 2. Got 31 and 30 (The offending index is 0)

  #34 opened 10 months ago by developer-JingHSY
  0

• Error loading audio file: failed to open file.

  #17 opened a year ago by ikuboo
  2

• How to create a shared link or change the port number on LAN

  #33 opened 10 months ago by heroterryvan
  0

• gradio ?

  #19 opened a year ago by zachysaur
  2

• 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/lib/python3.10/dist-packages/cv2/../../lib64:/usr/lib64-nvidia

  #32 opened 10 months ago by Yazdi9
  0

• error: subprocess-exited-with-error

  #29 opened a year ago by Xiahussheng
  1

• Can DreamTalk be extended to use video as input instead of images

  #30 opened 10 months ago by gongmm
  0

• mayf18@mails.tsinghua.edu.cn无法发送邮件

  #28 opened a year ago by gongmm
  1

• What is this parameter "pose_path"?

  #27 opened a year ago by TranThuyy
  0

• not work

  #26 opened a year ago by unnunique
  0

• License

  #20 opened a year ago by fakerybakery
  4

• CUDA 12.3，安装后运行不了

  #7 opened a year ago by chaorenai
  5

• only audio inference

  #9 opened a year ago by mehmetsat
  2

• Will you support to generate full image size video？And the resulting video has no sound.

  #24 opened a year ago by yl17104265
  0

• failed when generating long video: `'numpy.ndarray' object has no attribute 'unsqueeze'`

  #23 opened a year ago by yoebet
  0

• how to generate the style 3dmm file?

  #21 opened a year ago by notedit
  0

• Meaning of the 73 coefficients generated

  #16 opened a year ago by vardanagarwal
  2

• 测试效果为什么如此抽象，必须是正脸吗，脸有点偏就一定会矫正过来吗？

  #14 opened a year ago by zhanghongyong123456
  1

• can not run it on window

  #15 opened a year ago by linhcentrio
  2

• Face in output not matching with the original face

  #11 opened a year ago by vardanagarwal
  4

• jonatasgrosman/wav2vec2-large-xlsr-53-english/resolve/main/preprocessor_config.json 这个库都不存在了

  #1 opened a year ago by shiyueGG
  1

• the pretrained checkpoint is 256, can you release a 512x512 pretrained version. thank you.

  #6 opened a year ago by zhangziliang04
  2

• where is the train code?

  #5 opened a year ago by zhangziliang04
  1

• eye blink support?

  #4 opened a year ago by hengtuibabai
  1

• No audio I/O backend is available

  #2 opened a year ago by StartHua
  2