๐Ÿšฉ Report: Not working

#2
by holycowdude - opened

I've been trying for two days but it never produces a result, only an error after a few hours. Other people are also reporting issues with this project

Owner

Sorry for the inconvenience. Limited to the time cost, it cannot generate long video currently. You can set L below 60, and set step below 20 to speed up. I also change to ZERO GPU to shorten the waiting queue.
By the way, you can test on our demo cases. And ensure that your input image or video is square and contains human face.

I've also been trying for two days but it never produces a result, only an error after a few hours.

Owner

We have updated to a new version. You can test it later and let us know if it still doesn't work.

doesnt work

Unfortunately it still doesnt work

Same here..

Owner

Sorry for the inconvenience again. We have reviewed the code to remove all bugs. And our examples can be processed without issues. Most of the errors are due to the waiting queue or incorrect input data. And we are also sorry that we are unable to accommodate excessive visits. Utilize the source code will provide the best performance.

Owner

It should work now. Please give it a try.

perfect T H A N K YOU very much!

Hi, what is the minimum requirements for running this code? Will it work on huggingface Free plan?

Hi, what is the minimum requirements for running this code? Will it work on huggingface Free plan?

No. Needs at least 80gb storage, 10gb RAM and VRAM

I tried launching it on Google Colab but it doesn't work. ๐Ÿ˜…

2024-04-13 14:09:21.043640: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-04-13 14:09:21.043721: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-04-13 14:09:21.046556: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-04-13 14:09:22.918590: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Some weights of the model checkpoint at ./pretrained_model/wav2vec2-base-960h were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']

  • This IS expected if you are initializing Wav2Vec2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
  • This IS NOT expected if you are initializing Wav2Vec2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
    Some weights of Wav2Vec2Model were not initialized from the model checkpoint at ./pretrained_model/wav2vec2-base-960h and are newly initialized: ['wav2vec2.masked_spec_embed']
    You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
    Traceback (most recent call last):
    File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
    File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
    File "/content/drive/MyDrive/AIModel/FCAEmoPortrait/scripts/app.py", line 44, in
    a2m_model.load_state_dict(torch.load(audio_infer_config['pretrained_model']['a2m_ckpt'], map_location="cpu"), strict=False)
    File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 797, in load
    with _open_zipfile_reader(opened_file) as opened_zipfile:
    File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 283, in init
    super().init(torch._C.PyTorchFileReader(name_or_buffer))
    RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

I tried launching it on Google Colab but it doesn't work. ๐Ÿ˜…

2024-04-13 14:09:21.043640: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-04-13 14:09:21.043721: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-04-13 14:09:21.046556: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-04-13 14:09:22.918590: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Some weights of the model checkpoint at ./pretrained_model/wav2vec2-base-960h were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']

  • This IS expected if you are initializing Wav2Vec2Model from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
  • This IS NOT expected if you are initializing Wav2Vec2Model from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
    Some weights of Wav2Vec2Model were not initialized from the model checkpoint at ./pretrained_model/wav2vec2-base-960h and are newly initialized: ['wav2vec2.masked_spec_embed']
    You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
    Traceback (most recent call last):
    File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
    File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
    File "/content/drive/MyDrive/AIModel/FCAEmoPortrait/scripts/app.py", line 44, in
    a2m_model.load_state_dict(torch.load(audio_infer_config['pretrained_model']['a2m_ckpt'], map_location="cpu"), strict=False)
    File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 797, in load
    with _open_zipfile_reader(opened_file) as opened_zipfile:
    File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 283, in init
    super().init(torch._C.PyTorchFileReader(name_or_buffer))
    RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

try this one
https://github.com/camenduru/AniPortrait-jupyter

Sign up or log in to comment