ali-vilab / dreamtalk

Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

https://dreamtalk-project.github.io/

Repository from Github https://github.comali-vilab/dreamtalk

ali-vilab/dreamtalk Issues

the pretrained checkpoint is 256, can you release a 512x512 pretrained version. thank you.
Updated 9 months ago3
error: subprocess-exited-with-error
Updated 10 months ago2
An alternative project EchoMimicV2 is open-sourced
Updated 10 months ago
Training
Updated a year ago3
Lip Sync
Updated a year ago1
torchaudio C++ extension is not available.
Closed a year ago
Error when using Nvidia GPU.
Updated a year ago2
disable cropping in ui
Updated a year ago1
RuntimeError: Expected 3-dimensional
Updated a year ago1
How do I use 512 X 512
Updated a year ago
how to redownload Voxceleb2
Updated a year ago2
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']
Updated a year ago3
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
Updated a year ago5
RuntimeError: nvrtc: error: invalid value for --gpu-architecture (-arch) nvrtc compilation failed:
Updated a year ago3
有没有可以使用全身照片的项目推荐？
Updated a year ago1
network issues
Updated a year ago
Training Script
Closed a year ago
TypeError: can only concatenate str (not "bool") to str
Updated a year ago
subprocess.CalledProcessError: Command '['python', 'inference_for_demo_video.py'
Updated a year ago
pose mat
Updated a year ago
Parameter function
Updated 2 years ago
What config required to run it real-time?
Updated 2 years ago2
nvrtc compilation failed
Updated 2 years ago5
av.codec.codec.UnknownCodecError: libx264
Updated 2 years ago
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
Updated 2 years ago
av.error.FileNotFoundError: [Errno 2] No such file or directory
Updated 2 years ago
RuntimeError: Sizes of tensors must match except in dimension 2. Got 31 and 30 (The offending index is 0)
Updated 2 years ago
Error loading audio file: failed to open file.
Updated 2 years ago2
How to create a shared link or change the port number on LAN
Updated 2 years ago
gradio ?
Updated 2 years ago2
'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
Updated 2 years ago
Can DreamTalk be extended to use video as input instead of images
Updated 2 years ago
mayf18@mails.tsinghua.edu.cn无法发送邮件
Closed 2 years ago1
What is this parameter "pose_path"?
Updated 2 years ago
not work
Updated 2 years ago
License
Updated 2 years ago4
CUDA 12.3，安装后运行不了
Updated 2 years ago5
only audio inference
Updated 2 years ago2
Will you support to generate full image size video？And the resulting video has no sound.
Updated 2 years ago
failed when generating long video: `'numpy.ndarray' object has no attribute 'unsqueeze'`
Updated 2 years ago
how to generate the style 3dmm file?
Updated 2 years ago
Meaning of the 73 coefficients generated
Closed 2 years ago2
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？
Updated 2 years ago1
can not run it on window
Updated 2 years ago2
Face in output not matching with the original face
Closed 2 years ago4
jonatasgrosman/wav2vec2-large-xlsr-53-english/resolve/main/preprocessor_config.json 这个库都不存在了
Closed 2 years ago1
where is the train code?
Updated 2 years ago1
eye blink support?
Updated 2 years ago1
No audio I/O backend is available
Updated 2 years ago2