Hello,
I am trying to test the node in my setup. When I try to run the prompt the following errors appear in the console at some point:
...
C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: 'rcond' parameter will change to the default of machine precision times ''max(M, N)'' where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass 'rcond=None', to keep using the old, explicitly pass 'rcond=-1'.
P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\python.exe C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\V_Express/inference.py --unet_config_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\stable-diffusion-v1-5\unet\config.json --vae_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\sd-vae-ft-mse --audio_encoder_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\wav2vec2-base-960h --insightface_model_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models --denoising_unet_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\denoising_unet.pth --reference_net_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\reference_net.pth --v_kps_guider_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\v_kps_guider.pth --audio_projection_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\audio_projection.pth --motion_module_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\motion_module.pth --retarget_strategy naive_retarget --device cuda --gpu_id 0 --dtype fp16 --num_pad_audio_frames 2 --standard_audio_sampling_rate 16000 --reference_image_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\input\Harry_Potter_character_poster.jpg --audio_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\input\audio.wav --kps_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\input\video_kps.pth --output_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\output\1718060923.3967137_vexpress.mp4 --image_width 512 --image_height 512 --fps 30.0 --seed 451 --num_inference_steps 30 --guidance_scale 3.5 --context_frames 12 --context_stride 1 --context_overlap 4 --reference_attention_weight 0.95 --audio_attention_weight 3.0
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\utils\weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
Some weights of the model checkpoint at C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\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 C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\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.
C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\configuration_utils.py:240: 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 'modules.unet_2d_condition.UNet2DConditionModel'>.load_config(...) followed by <class 'modules.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 weights of Reference Net from C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\reference_net.pth.
Loaded weights of Denoising U-Net from C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\denoising_unet.pth.
Loaded weights of Denoising U-Net Motion Module from C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\motion_module.pth.
Loaded weights of V-Kps Guider from C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\v_kps_guider.pth.
Loaded weights of Audio Projection from C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\audio_projection.pth.
EP Error
EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
EP Error
EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
EP Error
EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
EP Error
EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
EP Error
EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (512, 512)
C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: 'rcond' parameter will change to the default of machine precision times ''max(M, N)'' where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass 'rcond=None', to keep using the old, explicitly pass 'rcond=-1'.
P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
Length of audio is 2866222 with the sampling rate of 44100.
Traceback (most recent call last):
File "C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\V_Express/inference.py", line 281, in
main()
File "C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\V_Express/inference.py", line 209, in main
audio_waveform = torchaudio.functional.resample(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchaudio\functional\functional.py", line 1528, in resample
resampled = _apply_sinc_resample_kernel(waveform, orig_freq, new_freq, gcd, kernel, width)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchaudio\functional\functional.py", line 1453, in _apply_sinc_resample_kernel
raise TypeError(f"Expected floating point type for waveform tensor, but received {waveform.dtype}.")
TypeError: Expected floating point type for waveform tensor, but received torch.int16.
Prompt executed in 146.77 seconds
Has this problem been identified before? Is there any workaround for it?
Thank you
Hello, I am trying to test the node in my setup. When I try to run the prompt the following errors appear in the console at some point:
... C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: 'rcond' parameter will change to the default of machine precision times ''max(M, N)'' where M and N are the input matrix dimensions. To use the future default and silence this warning we advise to pass 'rcond=None', to keep using the old, explicitly pass 'rcond=-1'. P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4 C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\python.exe C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\V_Express/inference.py --unet_config_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\stable-diffusion-v1-5\unet\config.json --vae_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\sd-vae-ft-mse --audio_encoder_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\wav2vec2-base-960h --insightface_model_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models --denoising_unet_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\denoising_unet.pth --reference_net_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\reference_net.pth --v_kps_guider_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\v_kps_guider.pth --audio_projection_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\audio_projection.pth --motion_module_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\v-express\motion_module.pth --retarget_strategy naive_retarget --device cuda --gpu_id 0 --dtype fp16 --num_pad_audio_frames 2 --standard_audio_sampling_rate 16000 --reference_image_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\input\Harry_Potter_character_poster.jpg --audio_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\input\audio.wav --kps_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\input\video_kps.pth --output_path C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\output\1718060923.3967137_vexpress.mp4 --image_width 512 --image_height 512 --fps 30.0 --seed 451 --num_inference_steps 30 --guidance_scale 3.5 --context_frames 12 --context_stride 1 --context_overlap 4 --reference_attention_weight 0.95 --audio_attention_weight 3.0 A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\utils\weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") Some weights of the model checkpoint at C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\wav2vec2-base-960h were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0 EP Error EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider'] Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0 EP Error EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider'] Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0 EP Error EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider'] Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0 EP Error EP Error 'providers' and 'provider_options' should be the same length if both are given. when using ['CPUExecutionProvider'] Falling back to ['CPUExecutionProvider'] and retrying.
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\model_ckpts\insightface_models\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5 set det-size: (512, 512) C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: 'rcond' parameter will change to the default of machine precision times ''max(M, N)'' where M and N are the input matrix dimensions. To use the future default and silence this warning we advise to pass 'rcond=None', to keep using the old, explicitly pass 'rcond=-1'. P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4 Length of audio is 2866222 with the sampling rate of 44100. Traceback (most recent call last): File "C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\V_Express/inference.py", line 281, in
main()
File "C:\Users\user\dev\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_V-Express\V_Express/inference.py", line 209, in main
audio_waveform = torchaudio.functional.resample(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchaudio\functional\functional.py", line 1528, in resample
resampled = _apply_sinc_resample_kernel(waveform, orig_freq, new_freq, gcd, kernel, width)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\dev\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchaudio\functional\functional.py", line 1453, in _apply_sinc_resample_kernel
raise TypeError(f"Expected floating point type for waveform tensor, but received {waveform.dtype}.")
TypeError: Expected floating point type for waveform tensor, but received torch.int16.
Prompt executed in 146.77 seconds
Has this problem been identified before? Is there any workaround for it? Thank you