BadToBest / EchoMimic

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
https://badtobest.github.io/echomimic.html
Apache License 2.0
2.26k stars 263 forks source link

motion_sync skipped. Please replace the pose dir with the driven video to enable it. #94

Closed nitinmukesh closed 1 month ago

nitinmukesh commented 1 month ago

I am trying to run the demo using pose still doesn't work. This is without making any changes.

(echomimic1) C:\usable\EchoMimic>python -u infer_audio2vid_pose_acc.py
C:\Users\nitin\miniconda3\envs\echomimic1\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
  torch.utils._pytree._register_pytree_node(
C:\Users\nitin\miniconda3\envs\echomimic1\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
  torch.utils._pytree._register_pytree_node(
[48, 41, 412, 481]
(48, 79, 412, 443)
motion_sync skipped. Please replace the pose dir with the driven video to enable it.
video in 24 FPS, audio idx in 50FPS
latents shape:torch.Size([1, 4, 243, 64, 64]), video_length:243

(echomimic1) C:\usable\EchoMimic>
JoeFannie commented 1 month ago

You should replace the pose dir to a driven video. Or just set motion_sync to 0.

nitinmukesh commented 1 month ago

@JoeFannie

I tried motion sync , no processing happens and no output produced. No errors

(echomimic1) C:\usable\EchoMimic>python -u infer_audio2vid_pose_acc.py --motion_sync 0
C:\Users\nitin\miniconda3\envs\echomimic1\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
  torch.utils._pytree._register_pytree_node(
C:\Users\nitin\miniconda3\envs\echomimic1\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
  torch.utils._pytree._register_pytree_node(
[48, 41, 412, 481]
(48, 79, 412, 443)
video in 24 FPS, audio idx in 50FPS
latents shape:torch.Size([1, 4, 243, 64, 64]), video_length:243

(echomimic1) C:\usable\EchoMimic>
nitinmukesh commented 1 month ago

You should replace the pose dir to a driven video.

Please explain what need to be done here, I am just trying to run using the default settings and assets

image