Pose workflow

[Tobe2d]

I have tested pose workflow with 125 frames based on 25fps and it work and now testing on 870 frames and comfy crash Press any key to continue . . .

Any idea how to fix this?

Here is the full log:

Starting server
To see the GUI go to: http://127.0.0.1:8188
To see the GUI go to: https://127.0.0.1:8189
FETCH DATA from: D:\Ai__Project\ComfyUI_00\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE]
got prompt
D:\Ai__Project\ComfyUI_00\venv\Lib\site-packages\diffusers\configuration_utils.py:245: FutureWarning: It is deprecated to pass a pretrained model name or path to `from_config`.If you were trying to load a model, please use <class 'ComfyUI_EchoMimic.src.models.unet_2d_condition.UNet2DConditionModel'>.load_config(...) followed by <class 'ComfyUI_EchoMimic.src.models.unet_2d_condition.UNet2DConditionModel'>.from_config(...) instead. Otherwise, please make sure to pass a configuration dictionary instead. This functionality will be removed in v1.0.0.
  deprecate("config-passed-as-path", "1.0.0", deprecation_message, standard_warn=False)

loaded temporal unet's pretrained weights from D:\Ai__Project\ComfyUI_00\models\echo_mimic\unet ...
Load motion module params from D:\Ai__Project\ComfyUI_00\models\echo_mimic\motion_module_pose.pth
Loaded 453.20928M-parameter motion module
video in 25 FPS, audio idx in 50FPS
D:\Ai__Project\ComfyUI_00\custom_nodes\ComfyUI_EchoMimic\src\pipelines\pipeline_echo_mimic_pose.py:446: FutureWarning: Accessing config attribute `in_channels` directly via 'EchoUNet3DConditionModel' object attribute is deprecated. Please access 'in_channels' over 'EchoUNet3DConditionModel's config object instead, e.g. 'unet.config.in_channels'.
  num_channels_latents = self.denoising_unet.in_channels

latents shape:torch.Size([1, 4, 875, 64, 64]), video_length:875
D:\Ai__Project\ComfyUI_00\venv\Lib\site-packages\diffusers\models\attention_processor.py:1584: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263.)
  hidden_states = F.scaled_dot_product_attention(

  0%|                                                                                                                                                                                                                                                     | 0/25 [00:00<?, ?it/s]D:\Ai__Project\ComfyUI_00\venv\Lib\site-packages\diffusers\models\resnet.py:323: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.
  deprecate("scale", "1.0.0", deprecation_message)

D:\Ai__Project\ComfyUI_00\venv\Lib\site-packages\diffusers\models\downsampling.py:135: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.
  deprecate("scale", "1.0.0", deprecation_message)

D:\Ai__Project\ComfyUI_00\venv\Lib\site-packages\diffusers\models\upsampling.py:144: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.
  deprecate("scale", "1.0.0", deprecation_message)

Press any key to continue . . .

[smthemex]

The current pose can only use the default built-in single frame action, as an additional “motion_stync” function is needed to convert videos into single frame actions, which will be launched in the next two days.

[Tobe2d]

Thanks for the reply, cant wait to test it ;-)