GGBo

使用wav2lip生成数字人模型

1

第一次在使用python genavatar.py --video_path 133.mp4 --img_size 256 --avatar_id wav2lip256_avatar2后，提示让我在LiveTalking-main\wav2lip\face_detection\detection\sfd目录的sfd_detector.py文件第24行加入一个参数，我修改成model_weights = torch.load(path_to_detector, weights_only=True)后，运行，在第二步的时候一直卡着不动，但内存的占用率特别高，请问是还有什么需要修改的吗？

使用musetalk训练数字人模型报错

4

命令：python genavatar_musetalk.py --avatar_id musetalk_avatar1 --file E:\1.mp4 报错： E:\anaconda3\envs\nerfstream\lib\site-packages\mmengine\optim\optimizer\zero_optimizer.py:11: DeprecationWarning: `TorchScript` support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the `torch.compile` optimizer...

使用mu生成形象时无错误反馈，但并未完成形象生成

3

(nerfstream) E:\1yiji\LiveTalking-main>python genavatar_musetalk.py --avatar_id musetalk_avatar2 --file E:\1yiji\1.mp4 E:\anaconda3\envs\nerfstream\lib\site-packages\torch\cuda_init_.py:129: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading...

提示RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'，我的PyTorch的版本是11.8要更换到多少版本呢？