yerfor
The video generation was killed. with 55 second wav
o create a public link, set share=True in launch().
args ('/tmp/gradio/4659f9a53f90af1cfac2c7e0990384bb1fe25590/aud.wav', 'none', 0, 0, 0.4, 0.01, False, '/root/GeneFacePlusPlus/checkpoints/audio2motion_vae/model_ckpt_steps_400000.ckpt', None, None, '/root/GeneFacePlusPlus/checkpoints/motion2video_nerf/may_torso/model_ckpt_steps_250000.ckpt', False)
Changes of a2m_ckpt detected, reloading model
Changes of torso_ckpt detected, reloading model
infer inputs : {'drv_audio_name': '/tmp/gradio/4659f9a53f90af1cfac2c7e0990384bb1fe25590/aud.wav', 'blink_mode': 'none', 'temperature': 0, 'lle_percent': 0, 'mouth_amp': 0.4, 'raymarching_end_threshold': 0.01, 'fp16': False, 'a2m_ckpt': '/root/GeneFacePlusPlus/checkpoints/audio2motion_vae/model_ckpt_steps_400000.ckpt', 'postnet_ckpt': '', 'head_ckpt': '', 'torso_ckpt': '/root/GeneFacePlusPlus/checkpoints/motion2video_nerf/may_torso/model_ckpt_steps_250000.ckpt', 'low_memory_usage': False, 'drv_pose': 'nearest', 'debug': False, 'out_name': 'temp/out_bFUxPNBuqVqRfXvK.mp4'}
| WARN: egs/egs_bases/audio2motion/vae.yaml not exist.
| WARN: /root/GeneFacePlusPlus/checkpoints/th1kh_512_audio2motion/base.yaml not exist.
| load 'model' from '/root/GeneFacePlusPlus/checkpoints/audio2motion_vae/model_ckpt_steps_400000.ckpt', strict=True
| WARN: /root/GeneFacePlusPlus/checkpoints/motion2video_nerf/may_torso/lm3d_radnerf_torso.yaml not exist.
| load 'model' from '/root/GeneFacePlusPlus/checkpoints/motion2video_nerf/may_torso/model_ckpt_steps_250000.ckpt', strict=True
trainval: Smooth head trajectory (rotation and translation) with a window size of 7
/root/GeneFacePlusPlus/tasks/radnerfs/dataset_utils.py:266: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
self.lm68s = torch.tensor(self.lm2ds[:, index_lm68_from_lm478, :])
/root/GeneFacePlusPlus/inference/genefacepp_infer.py:184: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
eye_area_percents = torch.tensor(self.dataset.eye_area_percents)
Extracted wav file (16khz) from /tmp/gradio/4659f9a53f90af1cfac2c7e0990384bb1fe25590/aud.wav to /tmp/gradio/4659f9a53f90af1cfac2c7e0990384bb1fe25590/aud_16k.wav.
Loading the HuBERT Model...
/root/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/_utils.py:776: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
return self.fget.get(instance, owner)()
Loading the Wav2Vec2 Processor...
GeneFace++ is rendering... : 0%| | 0/1360 [00:00<?, ?it/s]Setting up PyTorch plugin "bias_act_plugin"... Done.
Setting up PyTorch plugin "upfirdn2d_plugin"... Done.
GeneFace++ is rendering... : 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 1360/1360 [01:25<00:00, 15.85it/s]
Killed
Does anyone know why? How to solve it？
