kijai / comfyui-liveportraitkj Goto Github PK

View Code? Open in Web Editor NEW

1.4K 17.0 102.0 14.97 MB

ComfyUI nodes for LivePortrait

License: MIT License

Python 100.00%

comfyui-liveportraitkj's Introduction

ComfyUI nodes to use LivePortrait

Update 2

Added another alternative face detector: https://github.com/1adrianb/face-alignment

As this can use blazeface back camera model (or SFD), it's far better for smaller faces than MediaPipe, that only can use the blazeface short -model. The warmup on the first run when using this can take a long time, but subsequent runs are quick.

Example detection using the blazeface_back_camera:

AnimateDiff_00004.34.mp4

Update

Rework of almost the whole thing that's been in develop is now merged into main, this means old workflows will not work, but everything should be faster and there's lots of new features. For legacy purposes the old main branch is moved to the legacy -branch

Changes

Added MediaPipe as alternative to Insightface, everything should now be covered under MIT and Apache-2.0 licenses when using it.
Proper Vid2vid including smoothing algorhitm (thanks @melMass)
Improved speed and efficiency, allows for near realtime view even in Comfy (~80-100ms delay)
Restructured nodes for more options
Auto skipping frames with no face detected
Numerous other things I have forgotten about at this point, it's been a lot
Better Mac support on MPS (thanks @Grant-CP

update to this update:

converted the landmark runner onnx model to torch model, not something I have done before and I didn't manage to do anything but make it .pth file, so you'll just have to trust me on it. This allows running all this without even having onnxruntime, it runs on GPU and is about just as fast. It's available on the MediaPipe cropper node as option: When selected it's automatically downloaded from here: https://huggingface.co/Kijai/LivePortrait_safetensors/blob/main/landmark_model.pth

Examples:

Realtime with webcam feed:

liveportrait_realtime.mp4

Image2vid:

liveportrait_img2vid.mp4

Vid2Vid:

liveportrait_vid2vid.mp4

I have converted all the pickle files to safetensors: https://huggingface.co/Kijai/LivePortrait_safetensors/tree/main

They go here (and are automatically downloaded if the folder is not present) ComfyUI/models/liveportrait

Face detectors

You can either use the original default Insightface, or Google's MediaPipe.

Biggest difference is the license: Insightface is strictly for NON-COMMERCIAL use. MediaPipe is a bit worse at detection, and can't run on GPU in Windows, though it's much faster on CPU compared to Insightface

Insightface is not automatically installed, if you wish to use it follow these instructions: If you have a working compile environment, installing it can be as easy as:

pip install insightface

or for the portable version, in the ComfyUI_windows_portable -folder:

python_embeded/python.exe -m pip install insightface

If this fails (and it's likely), you can check the Troubleshooting part of the reactor node for alternative:

https://github.com/Gourieff/comfyui-reactor-node

For insightface model, extract this to ComfyUI/models/insightface/buffalo_l:

https://github.com/deepinsight/insightface/releases/download/v0.7/buffalo_l.zip

Please note that insightface license is non-commercial in nature.

comfyui-liveportraitkj's People

Contributors

Stargazers

Watchers

Forkers

mtb-tools djbielejeski sangplus sdwebui-extensions comfynodeprs mexicanamerican hoangminhanhtai coolhihi gaofee nkchocoai icelandiccenterartificialintelligence vcgithubcode render-ai xirtus lovehifi hirajanwin eltociear mihairotariu ourleds mojowebs matriarch-mayhem wipwai zakfong rvorias cabelo linecode serkandyck kesyn tonywhite11 thanhpham1987 thatgroot gfcprogramer grant-cp chaitanyasai-del weianding shenshen246 nafia007 embeddedme avat2 gizemgizg winsongr winnerking2010 utopic-dev zfbok breakcount phdratn moskanoro samuraibarbi junhosong80 imagebody hndrr faithstudio thamimtommy ilyamk wai-lynn adamsillva choufeng2018 imixsal treksis suryatmodulus quasimondo ryanyin01 muspelheimerscience srikant tomoyukiorita timelordq ekakit evolaw cxf0 militanthitchhiker ashishd daver101495 jacktzs168 ipsych ankur8613 ryanontheinside cylonspace degouville haochihlin whtxdyz brahianrosswill leo19901220 ai-shizuka zjy125jk wesley-yang camenduru chang-qing niya774 mcarbel khnext-ai jbhauchard octag0no yuchuanhuaying amesianx kellhuang readytodance agialpha bryanray zdaar redlion

comfyui-liveportraitkj's Issues

DEVELOP branch LivePortraitCropper dsize=512 resoluition

Hi! Kikai!

When I put 1024 to dsize, outputs ofr cropinfo get crazy. Is 512 is max resoultion?

A black box as a result

What is seen in the image, I am using comfyui portable

Turning either eye or lip retargeting on causes a "No face detected" error

I get the following error when turning eye_ or lip_retargeting on (regardless of what multiplier I type in):

[21:30:28] No face detected in the source image. cropper.py:78
!!! Exception during processing!!! No face detected in the source image!
Traceback (most recent call last):
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\nodes.py", line 260, in process
cropped_frames, full_frame = pipeline.execute(img, driving_images_np)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\live_portrait_pipeline.py", line 81, in execute
driving_lmk_lst = self.cropper.get_retargeting_lmk_info(driving_rgb_lst)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\cropper.py", line 108, in get_retargeting_lmk_info
ret_dct = self.crop_single_image(driving_image)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\cropper.py", line 79, in crop_single_image
raise Exception("No face detected in the source image!")
Exception: No face detected in the source image!

It detects the face fine without these options turned on, and I've also tried a few different images.

!!! Exception during processing!!! [Errno 2] No such file ./utils/resources/mask_template.png'

!!! Exception during processing!!! [Errno 2] No such file or directory: 'E:\IMAGE\ComfyUI_master\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\./utils/resources/mask_template.png'
Traceback (most recent call last):
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\nodes.py", line 260, in process
cropped_frames, full_frame = pipeline.execute(img, driving_images_np)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\live_portrait_pipeline.py", line 97, in execute
inference_cfg.mask_crop = cv2.imread(make_abs_path('./utils/resources/mask_template.png'), cv2.IMREAD_COLOR)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\ultralytics\utils\patches.py", line 26, in imread
return cv2.imdecode(np.fromfile(filename, np.uint8), flags)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: 'E:\IMAGE\ComfyUI_master\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\./utils/resources/mask_template.png'

Error occurred when executing LivePortraitProcess: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'cv::warpAffine'

Diagnostics-1720161440.log

Got it working on MacBook (MPS)

I have a version of these nodes working via MPS for those with macbooks. On my M1 Pro 32GB it took 60 seconds for 32 frames and 650 seconds for 600 frames. So about 1 second per animation frame.

Repo is here. I welcome all pull requests from other macbook users.
https://github.com/Grant-CP/ComfyUI-LivePortraitKJ-MPS

For @kijai I'm not sure that these changes can be added into the main as there are a few places where I changed numerical precision. So I would expect my version to have slightly worse performance. I am more than happy to talk about my changes if you want to start supporting MPS as a back end when you make nodes. Sorry for not forking correctly. I'm still learning how to use git.

ERROR RUNNING THE EXAMPLE: TypeError: Cannot read properties of undefined (reading 'clientId')

Installation is not allowed in this security_level

Can you make this add-on accomplish the new security issues in ComfyUI?

ComfyUI-LivePortraitKJ install failed: With the current security level configuration, only custom nodes from the "default channel" can be installed.

UnboundLocalError: local variable 'img_rgb' referenced before assignment in dev branch

!!! Exception during processing!!! local variable 'img_rgb' referenced before assignment
Traceback (most recent call last):
File "G:\comfyUI+AnimateDiff\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "G:\comfyUI+AnimateDiff\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "G:\comfyUI+AnimateDiff\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "G:\comfyUI+AnimateDiff\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\nodes.py", line 354, in process
cropped_out_list, full_out_list, out_mask_list = pipeline.execute(
File "G:\comfyUI+AnimateDiff\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\live_portrait_pipeline.py", line 86, in execute
crop_info = self.cropper.crop_single_image(source_frame_rgb, draw_keypoints=False)
File "G:\comfyUI+AnimateDiff\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\cropper.py", line 72, in crop_single_image
img_rgb,
UnboundLocalError: local variable 'img_rgb' referenced before assignment

Prompt executed in 9.59 seconds

Torch not compiled with CUDA enabled

i have a M3 Pro , how can I solve it?

thanks

Feature Request: Webcam to Image Facial Expression Change

Is there any way of using this model to apply facial tracking on a still image using a webcam input and not a pre-recorded video?

install ComfyUI-LivePortraitKJ error(onnxruntime-gpu)

mac m3，have this problem。 mac not have onnxruntime-gpu

ComfyUI-Manager: EXECUTE => ['/Users/haogui/code-language/python/ai/miniconda3/envs/py3.11.5/bin/python', '-m', 'pip', 'install', 'onnxruntime-gpu']

[!] ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu (from versions: none)
[!] ERROR: No matching distribution found for onnxruntime-gpu
install script failed: https://github.com/kijai/ComfyUI-LivePortraitKJ

cuDNN Execution Plan Failure Warning in PyTorch 2.3.0 with CUDA 11.8 and cuDNN 8.7

Description

When running certain operations in PyTorch, I'm encountering the following warnings:

UserWarning: Plan failed with a cudnnException: 
CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at 
../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)

This occurs during both 2D and 3D convolution operations.

Environment

PyTorch Version: 2.3.0
CUDA Version (PyTorch): 11.8
cuDNN Version (PyTorch): 8.7.0
OS: Ubuntu (please specify version)
GPU: NVIDIA A10G
NVIDIA Driver Version: 550.90.07
System CUDA Version: 12.4

Steps to Reproduce

Running inference.py

Additional Information

The warning appears for both nn.Conv2d and nn.Conv3d operations.
Despite the warning, the model seems to run, but I'm concerned about potential performance impacts or hidden issues.
This occurs even though the GPU (NVIDIA A10G) should be fully capable of handling these operations.

Questions

Is this warning indicative of a serious problem, or can it be safely ignored?
Could this be related to the mismatch between the system CUDA version (12.4) and the PyTorch CUDA version (11.8)?
Are there any workarounds or fixes available for this issue?
Will this cause huge performance impacts since I can train 20s video in 30s through ComfyUI custom nodes.

Logs

python inference.py
[08:08:55] Load appearance_feature_extractor done.                                                                                               live_portrait_wrapper.py:29
           Load motion_extractor done.                                                                                                           live_portrait_wrapper.py:32
[08:08:56] Load warping_module done.                                                                                                             live_portrait_wrapper.py:35
           Load spade_generator done.                                                                                                            live_portrait_wrapper.py:38
           Load stitching_retargeting_module done.                                                                                               live_portrait_wrapper.py:42
[08:08:57] LandmarkRunner warmup time: 0.813s                                                                                                          landmark_runner.py:89
[08:08:58] FaceAnalysisDIY warmup time: 0.797s                                                                                                       face_analysis_diy.py:79
           Load source image from /home/ubuntu/LivePortrait/src/config/../../assets/examples/source/s6.jpg                                      live_portrait_pipeline.py:46
[08:08:59] Load from video file (mp4 mov avi etc...): /home/ubuntu/LivePortrait/src/config/../../assets/examples/driving/d0.mp4                 live_portrait_pipeline.py:72
/home/ubuntu/LivePortrait/LivePortrait/lib/python3.9/site-packages/torch/nn/modules/conv.py:605: UserWarning: Plan failed with a cudnnException: 
CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at 
../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
  return F.conv3d(
/home/ubuntu/LivePortrait/LivePortrait/lib/python3.9/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: 
CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at 
../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
  return F.conv2d(input, weight, bias, self.stride,
Animating... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:05
Concatenating result... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00
Dump to animations/s6--d0_concat.mp4

writing ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━   0% -:--:--[swscaler @ 0x581ebc0] Warning: data is not aligned! This can lead to a speed loss
Dump to animations/s6--d0.mp4

[feature] Insight face stays loaded after generation

Hi Kijai, thank you for your amazing nods <3

Is there a way that Insightface don't unload after generation ? it might not be a problem for most people but my Insight face is somehow broken (if i fix it, it break some other nods :D ) it take around 100seconds to just load insightface, the video generation 20second. each time i change the picture or video it starts to load insightface again (100seconds wait).

For example in IPAdapter or FaceID it only loads insightface one time, after that you can change images and it stays loaded until you close comfy or clear workflow.

missing nodes?

"install missing custom nodes" wont find any

Error when using example workflow

2024-07-05 12:56:03.568554311 [E:onnxruntime:Default, provider_bridge_ort.cc:1744 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

[12:56:03] LandmarkRunner warmup time: 0.027s              landmark_runner.py:89
2024-07-05 12:56:03.786485287 [E:onnxruntime:Default, provider_bridge_ort.cc:1744 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: /workspace/ComfyUI/models/insightface/models/buffalo_l/1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
2024-07-05 12:56:03.914326696 [E:onnxruntime:Default, provider_bridge_ort.cc:1744 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: /workspace/ComfyUI/models/insightface/models/buffalo_l/2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
2024-07-05 12:56:03.952310361 [E:onnxruntime:Default, provider_bridge_ort.cc:1744 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: /workspace/ComfyUI/models/insightface/models/buffalo_l/det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
2024-07-05 12:56:03.995014228 [E:onnxruntime:Default, provider_bridge_ort.cc:1744 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: /workspace/ComfyUI/models/insightface/models/buffalo_l/genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
2024-07-05 12:56:04.089183904 [E:onnxruntime:Default, provider_bridge_ort.cc:1744 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: /workspace/ComfyUI/models/insightface/models/buffalo_l/w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (512, 512)
[12:56:04] FaceAnalysisDIY warmup time: 0.023s           face_analysis_diy.py:79
[ WARN:[email protected]] global loadsave.cpp:241 findDecoder imread_('/workspace/ComfyUI/custom_nodes/ComfyUI-LivePortraitKJ/liveportrait/./utils/resources/mask_template.png'): can't open/read file: check file path/integrity
!!! Exception during processing!!! OpenCV(4.10.0) /io/opencv/modules/imgproc/src/imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'warpAffine'

Traceback (most recent call last):
  File "/workspace/ComfyUI/execution.py", line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "/workspace/ComfyUI/execution.py", line 81, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
  File "/workspace/ComfyUI/execution.py", line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-LivePortraitKJ/nodes.py", line 260, in process
    cropped_frames, full_frame = pipeline.execute(img, driving_images_np)
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-LivePortraitKJ/liveportrait/live_portrait_pipeline.py", line 98, in execute
    mask_ori = _transform_img(inference_cfg.mask_crop, crop_info['M_c2o'], dsize=(img_rgb.shape[1], img_rgb.shape[0]))
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-LivePortraitKJ/liveportrait/utils/crop.py", line 30, in _transform_img
    return cv2.warpAffine(img, M[:2, :], dsize=_dsize, flags=flags)
cv2.error: OpenCV(4.10.0) /io/opencv/modules/imgproc/src/imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'warpAffine'

How to handle situations where only some frames do not detect faces.

error :

No face detected in the source image!

add video auto cropping

LivePortrait has support video auto cropping , please add it to comfyui

Solution for DLL load failed onnxruntime_pybind11 & no module named insightface

Hello guys, i spend 2 days figuring these two

if you have followed the readme and still have one of those error

### DLL load failed onnxruntime_pybind11
installing VC64 from Microsoft (LINK) and rebooting solved it

### no module named insightface
you need to pip uninstall insightface before trying installing manually the insightface from this troubleshot guide
https://github.com/Gourieff/comfyui-reactor-node?tab=readme-ov-file#troubleshooting

please look at this project

https://github.com/HaozheZhao/UltraEdit

cv::warpAffine'

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: E:\Comfyui\ComfyUI_windows_portable\ComfyUI\models\insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (512, 512)
[10:17:08] FaceAnalysisDIY warmup time: 0.085s face_analysis_diy.py:79!!! Exception during processing!!! OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'cv::warpAffine'

Traceback (most recent call last):
File "E:\Comfyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Comfyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)

File "E:\Comfyui\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))

File "E:\Comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortrait\nodes.py", line 256, in process
cropped_frames, full_frame = pipeline.execute(img, driving_images_np)

File "E:\Comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortrait\liveportrait\live_portrait_pipeline.py", line 98, in execute
mask_ori = _transform_img(inference_cfg.mask_crop, crop_info['M_c2o'], dsize=(img_rgb.shape[1], img_rgb.shape[0]))

File "E:\Comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortrait\liveportrait\utils\crop.py", line 30, in _transform_img
return cv2.warpAffine(img, M[:2, :], dsize=_dsize, flags=flags)

cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'cv::warpAffine'

CPU High

When runing sample video d6, the cpu reach 100% for long time.

Any improvment for that?

Node for sadtalker

Hi, a comfyui nodes for sadtalker too will be pretty cool. Have you looked into sadtalker?

[feature request] Face selection when more than one

It should be easy to expose from insightface the face index if there is more than one face in the "source" video.

Output based on self-recorded videos with stable webcam coming off very shaky

I tried capturing videos with webcam with shoulders being very still...
I am getting very shaky results like a shivering, other instances the head would start scaling up and down.
any idea what i am doing wrong ?

albumentations module missing and i can't get it installed properly

I manged to get insightface installed by installing reactor thought i get the below error on launching comfyui

Traceback (most recent call last):
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1907, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node_init.py", line 23, in
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node\nodes.py", line 27, in
from scripts.reactor_faceswap import (
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node\scripts\reactor_faceswap.py", line 14, in
from scripts.reactor_swapper import (
File "D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node\scripts\reactor_swapper.py", line 9, in
import insightface
File "D:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface_init_.py", line 18, in
from . import app
File "D:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\app_init_.py", line 2, in
from .mask_renderer import *
File "D:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\insightface\app\mask_renderer.py", line 4, in
import albumentations as A
ModuleNotFoundError: No module named 'albumentations'

Cannot import D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node module for custom nodes: No module named 'albumentations'

Import times for custom nodes:
0.0 seconds: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
0.1 seconds: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
0.1 seconds (IMPORT FAILED): D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortrait
0.2 seconds (IMPORT FAILED): D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-reactor-node
0.3 seconds: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
0.3 seconds: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes
5.7 seconds: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-MotionDiff

If i do a Python - pip install of albumentations i get a "already satisfied" response
IF i install via the comfy manager pip installer, i can launch without issues ( the worflow still doesn't transfer the animation though ) however, upon restarting comfyui i get the same error again

RuntimeError: PyTorch is not linked with support for mps devices

Please, what about it?

[22:23:04] FaceAnalysisDIY warmup time: 1.731s face_analysis_diy.py:79
!!! Exception during processing!!! PyTorch is not linked with support for mps devices
Traceback (most recent call last):
File "C:\Comfyui\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Comfyui\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Comfyui\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Comfyui\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ-MPS\nodes.py", line 260, in process
cropped_frames, full_frame = pipeline.execute(img, driving_images_np)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Comfyui\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ-MPS\liveportrait\live_portrait_pipeline.py", line 50, in execute
I_s = self.live_portrait_wrapper.prepare_source(img_crop_256x256)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Comfyui\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ-MPS\liveportrait\live_portrait_wrapper.py", line 63, in prepare_source
x = x.to(self.device)
^^^^^^^^^^^^^^^^^
RuntimeError: PyTorch is not linked with support for mps devices

video upload dont

the possibility to upload the video does not appear, can someone help me? thank you very much

LivePortrait Croper ＆KeypointsToImage missing!

When using this sample workflow, an error occurred where the LivePortrait Cropper and Keypoints To Image nodes could not be found
https://github.com/kijai/ComfyUI-LivePortraitKJ/tree/develop/examples

The common error due to InsightFace not being downloaded has been resolved, and i2v is possible, but v2v is not working

Error Installing insight face with the provided method

I get the below error

Building wheels for collected packages: insightface
Building wheel for insightface (pyproject.toml) ... error
error: subprocess-exited-with-error

× Building wheel for insightface (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [233 lines of output]
WARNING: pandoc not enabled
running bdist_wheel
running build
running build_py
creating build
creating build\lib.win-amd64-cpython-311
creating build\lib.win-amd64-cpython-311\insightface
copying insightface_init_.py -> build\lib.win-amd64-cpython-311\insightface
creating build\lib.win-amd64-cpython-311\insightface\app
copying insightface\app\common.py -> build\lib.win-amd64-cpython-311\insightface\app
copying insightface\app\face_analysis.py -> build\lib.win-amd64-cpython-311\insightface\app
copying insightface\app\mask_renderer.py -> build\lib.win-amd64-cpython-311\insightface\app
copying insightface\app_init_.py -> build\lib.win-amd64-cpython-311\insightface\app
creating build\lib.win-amd64-cpython-311\insightface\commands
copying insightface\commands\insightface_cli.py -> build\lib.win-amd64-cpython-311\insightface\commands
copying insightface\commands\model_download.py -> build\lib.win-amd64-cpython-311\insightface\commands
copying insightface\commands\rec_add_mask_param.py -> build\lib.win-amd64-cpython-311\insightface\commands
copying insightface\commands_init_.py -> build\lib.win-amd64-cpython-311\insightface\commands
creating build\lib.win-amd64-cpython-311\insightface\data
copying insightface\data\image.py -> build\lib.win-amd64-cpython-311\insightface\data
copying insightface\data\pickle_object.py -> build\lib.win-amd64-cpython-311\insightface\data
copying insightface\data\rec_builder.py -> build\lib.win-amd64-cpython-311\insightface\data
copying insightface\data_init_.py -> build\lib.win-amd64-cpython-311\insightface\data
creating build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\arcface_onnx.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\attribute.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\inswapper.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\landmark.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\model_store.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\model_zoo.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\retinaface.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo\scrfd.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
copying insightface\model_zoo_init_.py -> build\lib.win-amd64-cpython-311\insightface\model_zoo
creating build\lib.win-amd64-cpython-311\insightface\thirdparty
copying insightface\thirdparty_init_.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty
creating build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils\constant.py -> build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils\download.py -> build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils\face_align.py -> build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils\filesystem.py -> build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils\storage.py -> build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils\transform.py -> build\lib.win-amd64-cpython-311\insightface\utils
copying insightface\utils_init_.py -> build\lib.win-amd64-cpython-311\insightface\utils
creating build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d
copying insightface\thirdparty\face3d_init_.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d
creating build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
copying insightface\thirdparty\face3d\mesh\io.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
copying insightface\thirdparty\face3d\mesh\light.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
copying insightface\thirdparty\face3d\mesh\render.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
copying insightface\thirdparty\face3d\mesh\transform.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
copying insightface\thirdparty\face3d\mesh\vis.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
copying insightface\thirdparty\face3d\mesh_init_.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh
creating build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
copying insightface\thirdparty\face3d\mesh_numpy\io.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
copying insightface\thirdparty\face3d\mesh_numpy\light.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
copying insightface\thirdparty\face3d\mesh_numpy\render.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
copying insightface\thirdparty\face3d\mesh_numpy\transform.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
copying insightface\thirdparty\face3d\mesh_numpy\vis.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
copying insightface\thirdparty\face3d\mesh_numpy_init_.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh_numpy
creating build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\morphable_model
copying insightface\thirdparty\face3d\morphable_model\fit.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\morphable_model
copying insightface\thirdparty\face3d\morphable_model\load.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\morphable_model
copying insightface\thirdparty\face3d\morphable_model\morphabel_model.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\morphable_model
copying insightface\thirdparty\face3d\morphable_model_init_.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\morphable_model
running egg_info
writing insightface.egg-info\PKG-INFO
writing dependency_links to insightface.egg-info\dependency_links.txt
writing entry points to insightface.egg-info\entry_points.txt
writing requirements to insightface.egg-info\requires.txt
writing top-level names to insightface.egg-info\top_level.txt
reading manifest file 'insightface.egg-info\SOURCES.txt'
writing manifest file 'insightface.egg-info\SOURCES.txt'
D:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\command\build_py.py:207: _Warning: Package 'insightface.thirdparty.face3d.mesh.cython' is absent from the packages configuration.
!!

          ********************************************************************************
          ############################
          # Package would be ignored #
          ############################
          Python recognizes 'insightface.thirdparty.face3d.mesh.cython' as an importable package[^1],
          but it is absent from setuptools' `packages` configuration.

          This leads to an ambiguous overall configuration. If you want to distribute this
          package, please make sure that 'insightface.thirdparty.face3d.mesh.cython' is explicitly added
          to the `packages` configuration field.

          Alternatively, you can also rely on setuptools' discovery methods
          (for example by using `find_namespace_packages(...)`/`find_namespace:`
          instead of `find_packages(...)`/`find:`).

          You can read more about "package discovery" on setuptools documentation page:

          - https://setuptools.pypa.io/en/latest/userguide/package_discovery.html

          If you don't want 'insightface.thirdparty.face3d.mesh.cython' to be distributed and are
          already explicitly excluding 'insightface.thirdparty.face3d.mesh.cython' via
          `find_namespace_packages(...)/find_namespace` or `find_packages(...)/find`,
          you can try to use `exclude_package_data`, or `include-package-data=False` in
          combination with a more fine grained `package-data` configuration.

          You can read more about "package data files" on setuptools documentation page:

          - https://setuptools.pypa.io/en/latest/userguide/datafiles.html


          [^1]: For Python, any directory (with suitable naming) can be imported,
                even if it does not contain any `.py` files.
                On the other hand, currently there is no concept of package data
                directory, all directories are treated like packages.
          ********************************************************************************

  !!
    check.warn(importable)
  D:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\command\build_py.py:207: _Warning: Package 'insightface.data.images' is absent from the `packages` configuration.
  !!

          ********************************************************************************
          ############################
          # Package would be ignored #
          ############################
          Python recognizes 'insightface.data.images' as an importable package[^1],
          but it is absent from setuptools' `packages` configuration.

          This leads to an ambiguous overall configuration. If you want to distribute this
          package, please make sure that 'insightface.data.images' is explicitly added
          to the `packages` configuration field.

          Alternatively, you can also rely on setuptools' discovery methods
          (for example by using `find_namespace_packages(...)`/`find_namespace:`
          instead of `find_packages(...)`/`find:`).

          You can read more about "package discovery" on setuptools documentation page:

          - https://setuptools.pypa.io/en/latest/userguide/package_discovery.html

          If you don't want 'insightface.data.images' to be distributed and are
          already explicitly excluding 'insightface.data.images' via
          `find_namespace_packages(...)/find_namespace` or `find_packages(...)/find`,
          you can try to use `exclude_package_data`, or `include-package-data=False` in
          combination with a more fine grained `package-data` configuration.

          You can read more about "package data files" on setuptools documentation page:

          - https://setuptools.pypa.io/en/latest/userguide/datafiles.html


          [^1]: For Python, any directory (with suitable naming) can be imported,
                even if it does not contain any `.py` files.
                On the other hand, currently there is no concept of package data
                directory, all directories are treated like packages.
          ********************************************************************************

  !!
    check.warn(importable)
  D:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\command\build_py.py:207: _Warning: Package 'insightface.data.objects' is absent from the `packages` configuration.
  !!

          ********************************************************************************
          ############################
          # Package would be ignored #
          ############################
          Python recognizes 'insightface.data.objects' as an importable package[^1],
          but it is absent from setuptools' `packages` configuration.

          This leads to an ambiguous overall configuration. If you want to distribute this
          package, please make sure that 'insightface.data.objects' is explicitly added
          to the `packages` configuration field.

          Alternatively, you can also rely on setuptools' discovery methods
          (for example by using `find_namespace_packages(...)`/`find_namespace:`
          instead of `find_packages(...)`/`find:`).

          You can read more about "package discovery" on setuptools documentation page:

          - https://setuptools.pypa.io/en/latest/userguide/package_discovery.html

          If you don't want 'insightface.data.objects' to be distributed and are
          already explicitly excluding 'insightface.data.objects' via
          `find_namespace_packages(...)/find_namespace` or `find_packages(...)/find`,
          you can try to use `exclude_package_data`, or `include-package-data=False` in
          combination with a more fine grained `package-data` configuration.

          You can read more about "package data files" on setuptools documentation page:

          - https://setuptools.pypa.io/en/latest/userguide/datafiles.html


          [^1]: For Python, any directory (with suitable naming) can be imported,
                even if it does not contain any `.py` files.
                On the other hand, currently there is no concept of package data
                directory, all directories are treated like packages.
          ********************************************************************************

  !!
    check.warn(importable)
  creating build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  copying insightface\thirdparty\face3d\mesh\cython\mesh_core.cpp -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  copying insightface\thirdparty\face3d\mesh\cython\mesh_core.h -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  copying insightface\thirdparty\face3d\mesh\cython\mesh_core_cython.cpp -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  creating build\lib.win-amd64-cpython-311\insightface\data\images
  copying insightface\data\images\Tom_Hanks_54745.png -> build\lib.win-amd64-cpython-311\insightface\data\images
  copying insightface\data\images\mask_black.jpg -> build\lib.win-amd64-cpython-311\insightface\data\images
  copying insightface\data\images\mask_blue.jpg -> build\lib.win-amd64-cpython-311\insightface\data\images
  copying insightface\data\images\mask_green.jpg -> build\lib.win-amd64-cpython-311\insightface\data\images
  copying insightface\data\images\mask_white.jpg -> build\lib.win-amd64-cpython-311\insightface\data\images
  copying insightface\data\images\t1.jpg -> build\lib.win-amd64-cpython-311\insightface\data\images
  creating build\lib.win-amd64-cpython-311\insightface\data\objects
  copying insightface\data\objects\meanshape_68.pkl -> build\lib.win-amd64-cpython-311\insightface\data\objects
  copying insightface\thirdparty\face3d\mesh\cython\mesh_core_cython.c -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  copying insightface\thirdparty\face3d\mesh\cython\mesh_core_cython.cpp -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  copying insightface\thirdparty\face3d\mesh\cython\mesh_core_cython.pyx -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  copying insightface\thirdparty\face3d\mesh\cython\setup.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
  running build_ext
  building 'insightface.thirdparty.face3d.mesh.cython.mesh_core_cython' extension
  creating build\temp.win-amd64-cpython-311
  creating build\temp.win-amd64-cpython-311\Release
  creating build\temp.win-amd64-cpython-311\Release\insightface
  creating build\temp.win-amd64-cpython-311\Release\insightface\thirdparty
  creating build\temp.win-amd64-cpython-311\Release\insightface\thirdparty\face3d
  creating build\temp.win-amd64-cpython-311\Release\insightface\thirdparty\face3d\mesh
  creating build\temp.win-amd64-cpython-311\Release\insightface\thirdparty\face3d\mesh\cython
  "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.40.33807\bin\HostX86\x64\cl.exe" /c /nologo /O2 /W3 /GL /DNDEBUG /MD -Iinsightface/thirdparty/face3d/mesh/cython -ID:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\numpy\core\include -ID:\ComfyUI\ComfyUI_windows_portable\python_embeded\include -ID:\ComfyUI\ComfyUI_windows_portable\python_embeded\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.40.33807\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.40.33807\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22621.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" /EHsc /Tpinsightface/thirdparty/face3d/mesh/cython/mesh_core.cpp /Fobuild\temp.win-amd64-cpython-311\Release\insightface/thirdparty/face3d/mesh/cython/mesh_core.obj
  mesh_core.cpp
  insightface/thirdparty/face3d/mesh/cython/mesh_core.cpp(147): warning C4244: '=': conversion from 'int' to 'float', possible loss of data
  insightface/thirdparty/face3d/mesh/cython/mesh_core.cpp(147): warning C4244: '=': conversion from 'int' to 'float', possible loss of data
  insightface/thirdparty/face3d/mesh/cython/mesh_core.cpp(210): warning C4244: '=': conversion from 'int' to 'float', possible loss of data
  insightface/thirdparty/face3d/mesh/cython/mesh_core.cpp(210): warning C4244: '=': conversion from 'int' to 'float', possible loss of data
  insightface/thirdparty/face3d/mesh/cython/mesh_core.cpp(294): warning C4244: '=': conversion from 'int' to 'float', possible loss of data
  insightface/thirdparty/face3d/mesh/cython/mesh_core.cpp(294): warning C4244: '=': conversion from 'int' to 'float', possible loss of data
  "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.40.33807\bin\HostX86\x64\cl.exe" /c /nologo /O2 /W3 /GL /DNDEBUG /MD -Iinsightface/thirdparty/face3d/mesh/cython -ID:\ComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\numpy\core\include -ID:\ComfyUI\ComfyUI_windows_portable\python_embeded\include -ID:\ComfyUI\ComfyUI_windows_portable\python_embeded\Include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.40.33807\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.40.33807\ATLMFC\include" "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\VS\include" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.22621.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\um" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\shared" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\winrt" "-IC:\Program Files (x86)\Windows Kits\10\\include\10.0.22621.0\\cppwinrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" /EHsc /Tpinsightface/thirdparty/face3d/mesh/cython/mesh_core_cython.cpp /Fobuild\temp.win-amd64-cpython-311\Release\insightface/thirdparty/face3d/mesh/cython/mesh_core_cython.obj
  mesh_core_cython.cpp
  insightface/thirdparty/face3d/mesh/cython/mesh_core_cython.cpp(36): fatal error C1083: Cannot open include file: 'Python.h': No such file or directory
  error: command 'C:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.40.33807\\bin\\HostX86\\x64\\cl.exe' failed with exit code 2
  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for insightface
Failed to build insightface
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (insightface)

Is this node compatible with the original checkpoints?

cv2.error: OpenCV(4.10.0)

[01:54:21] LandmarkRunner warmup time: 0.042s landmark_runner.py:89
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (512, 512)
[01:54:53] FaceAnalysisDIY warmup time: 0.037s face_analysis_diy.py:79
[deforum] Executor HiJack Failed and was deactivated, please report the issue on GitHub
[01:54:54] LandmarkRunner warmup time: 0.039s landmark_runner.py:89
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: D:\ComfyUI-ainewsto\ComfyUI\models\insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (512, 512)
[01:55:27] FaceAnalysisDIY warmup time: 0.052s face_analysis_diy.py:79
!!! Exception during processing!!! OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'cv::warpAffine'

Traceback (most recent call last):
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\deforum-comfy-nodes\deforum_nodes\exec_hijack.py", line 50, in map_node_over_list
results.append(getattr(obj, func)(**sliced_input))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\nodes.py", line 260, in process
cropped_frames, full_frame = pipeline.execute(img, driving_images_np)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\live_portrait_pipeline.py", line 98, in execute
mask_ori = _transform_img(inference_cfg.mask_crop, crop_info['M_c2o'], dsize=(img_rgb.shape[1], img_rgb.shape[0]))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\crop.py", line 30, in _transform_img
return cv2.warpAffine(img, M[:2, :], dsize=_dsize, flags=flags)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'cv::warpAffine'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\ComfyUI-ainewsto\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\deforum-comfy-nodes\deforum_nodes\exec_hijack.py", line 55, in map_node_over_list
return orig_exec(obj, input_data_all, func, allow_interrupt)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\nodes.py", line 260, in process
cropped_frames, full_frame = pipeline.execute(img, driving_images_np)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\live_portrait_pipeline.py", line 98, in execute
mask_ori = _transform_img(inference_cfg.mask_crop, crop_info['M_c2o'], dsize=(img_rgb.shape[1], img_rgb.shape[0]))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-ainewsto\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\crop.py", line 30, in _transform_img
return cv2.warpAffine(img, M[:2, :], dsize=_dsize, flags=flags)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\imgwarp.cpp:2825: error: (-215:Assertion failed) src.cols > 0 && src.rows > 0 in function 'cv::warpAffine'

No matching distribution found for yaml

ERROR: Could not find a version that satisfies the requirement yaml (from versions: none)
ERROR: No matching distribution found for yaml

Is it "PyYAML" that needs to be installed?

Conflicting Modes? Or missing?

Hi there, after I LivePortrait installed via ComfyUI Manager, and also out insightface files to "\ComfyUI\models\insightface\buffalo_l" I still miss the nodes.

In the description of LivePortrait (Manager) I see following:

Conflicted Nodes:
DownloadAndLoadLivePortraitModels [ComfyUI-LivePortraitKJ-MPS], LivePortraitProcess [ComfyUI-LivePortraitKJ-MPS]

What shall I do? I am using Portable ComfyUI.

Thank you,
best regards,
Merzmensch

Asking for animal face animation

There is Generalization to Animals in the original project.
Any plan for implemnting this feature?

Retargeting makes the face stuck

I dont get whats the point of eye retargeting and lips retargeting when it clearly doesnot work at all and makes the face stuck . I am so confused , can you clarify or is this feature under construction?

Error in Windows-Portable (AttributeError: module 'ComfyUI_Ib_CustomNodes.script' has no attribute 'WorkflowToScriptTranspiler')

Traceback (most recent call last):
File "H:\ComfyUI_windows_main_portable\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Ib_CustomNodes_init_.py", line 47, in pnginfo_add_text_hook
comfy_script = script.WorkflowToScriptTranspiler(workflow).to_script(end_nodes)
AttributeError: module 'ComfyUI_Ib_CustomNodes.script' has no attribute 'WorkflowToScriptTranspiler'

Deformed result with LivePortrait

I test a lot of videos but get the same deformed result the original model example is really good did I did something wrong.

the image needs a specific ratio and the video
What is the requirement for the image and video in size, cropped area etc...

LivePortrait.bug.mp4

Feature request: Face index selection and multiple face inputs.

Hey there great work!
Got this thing cooking. But would really love to select a single subject in a group similar to the React nodes index selection going from left to right top to bottom I think. And a separate input for individual driver sequences would be great. The idea being to put many performances on many faces with one pass with image sequences.
Thank you!
Daniel

Video has not been completely processed

Just a few frames are being processed

Just.a.few.frames.mp4

Error occurred when executing LivePortraitProcess

Error occurred when executing LivePortraitProcess:

D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:636 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.

File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\nodes.py", line 247, in process
cropper = Cropper(crop_cfg=crop_cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\cropper.py", line 39, in init
self.landmark_runner = LandmarkRunner(
^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LivePortraitKJ\liveportrait\utils\landmark_runner.py", line 36, in init
self.session = onnxruntime.InferenceSession(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 394, in init
raise fallback_error from e
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 389, in init
self._create_inference_session(self._fallback_providers, None)
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 435, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)

how should I install CUDA or find the PATH to add it in system
thanks

Animation doesn't seem to transfer

I finally got the workflow to load without errors however upon selecting the photo and video and excuting the prompt, the output seems to be the originalvideo with the same still photo next to it, seems the animation doesn't transfer

I get the below exception in callback

got prompt
Load appearance_feature_extractor done.
Load motion_extractor done.
Load warping_module done.
Load spade_generator done.
Load stitching_retargeting_module done.
[14:06:11] LandmarkRunner warmup time: 2.115s landmark_runner.py:89
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'device_id': '0', 'has_user_compute_stream': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'user_compute_stream': '0', 'gpu_external_alloc': '0', 'gpu_mem_limit': '18446744073709551615', 'enable_cuda_graph': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'prefer_nhwc': '0', 'use_ep_level_unified_stream': '0', 'use_tf32': '1'}, 'CPUExecutionProvider': {}}
find model: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\models\insightface\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'device_id': '0', 'has_user_compute_stream': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'user_compute_stream': '0', 'gpu_external_alloc': '0', 'gpu_mem_limit': '18446744073709551615', 'enable_cuda_graph': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'prefer_nhwc': '0', 'use_ep_level_unified_stream': '0', 'use_tf32': '1'}, 'CPUExecutionProvider': {}}
find model: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\models\insightface\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'device_id': '0', 'has_user_compute_stream': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'user_compute_stream': '0', 'gpu_external_alloc': '0', 'gpu_mem_limit': '18446744073709551615', 'enable_cuda_graph': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'prefer_nhwc': '0', 'use_ep_level_unified_stream': '0', 'use_tf32': '1'}, 'CPUExecutionProvider': {}}
find model: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\models\insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'device_id': '0', 'has_user_compute_stream': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'user_compute_stream': '0', 'gpu_external_alloc': '0', 'gpu_mem_limit': '18446744073709551615', 'enable_cuda_graph': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'prefer_nhwc': '0', 'use_ep_level_unified_stream': '0', 'use_tf32': '1'}, 'CPUExecutionProvider': {}}
find model: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\models\insightface\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'device_id': '0', 'has_user_compute_stream': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'user_compute_stream': '0', 'gpu_external_alloc': '0', 'gpu_mem_limit': '18446744073709551615', 'enable_cuda_graph': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'prefer_nhwc': '0', 'use_ep_level_unified_stream': '0', 'use_tf32': '1'}, 'CPUExecutionProvider': {}}
find model: D:\ComfyUI\ComfyUI_windows_portable\ComfyUI\models\insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (512, 512)
[14:06:14] FaceAnalysisDIY warmup time: 1.609s face_analysis_diy.py:79
Animating... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:04
Prompt executed in 18.90 seconds
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
File "asyncio\events.py", line 84, in _run
File "asyncio\proactor_events.py", line 165, in _call_connection_lost
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

Setting explation needed

It will be appreciated if there is explation for these setting.

So I could find out if it is possible to make result better by adjust setting. Or it is the limit of model.
Some output not as expected, wrong mouth shape or others.

An error occurred while connecting to "audio"：IndexError: list index out of range

An error occurred while connecting to "audio":
!!! Exception during processing!!! list index out of range Traceback (most recent call last): File "D:\AI\ComfyUI\execution.py", line 141, in recursive_execute input_data_all = get_input_data(inputs, class_def, unique_id, outputs, prompt, extra_data) File "D:\AI\ComfyUI\execution.py", line 26, in get_input_data obj = outputs[input_unique_id][output_index] IndexError: list index out of range

When loading the graph, the following node types were not found:

DownloadAndLoadLivePortraitModels
LivePortraitProcess

Core Dump Error??

Good morning! For some reason I started getting this error with is causing ComfyUI to shut down. Not sure what I changed since yesterday (it was working fine) but today it's giving me this error. I updated everything but that didn't help. Any ideas?

To see the GUI go to: http://127.0.0.1:8188
got prompt
[rgthree] Using rgthree's optimized recursive execution.
[rgthree] First run patching recursive_output_delete_if_changed and recursive_will_execute.
[rgthree] Note: If execution seems broken due to forward ComfyUI changes, you can disable the optimization from rgthree settings in ComfyUI.
Load appearance_feature_extractor done.
Load motion_extractor done.
Load warping_module done.
Load spade_generator done.
Load stitching_retargeting_module done.
Could not load library libcudnn_cnn_infer.so.8. Error: libnvrtc.so: cannot open shared object file: No such file or directory
Aborted (core dumped)
(comfyui_env) user@AI:~/ComfyUI$

Node not displayed ImageConcatMulti

how to install the node?

Not an issue but for everybody that has problems with Insightface

Download a FRESH ComfyUI portable

When installing (even when run as admin) use

python_embeded/python.exe -m pip install --user insightface

instead of

python_embeded/python.exe -m pip install insightface

(The --user part is lacking in the Instructions)

Hallo Node implementation

Hi Kijai, sorry for posting this here, I would like to see a Hallo node implementation by you for comfyui the implemented one for comfy are hell as slow but all your implementation are fast.
https://github.com/fudan-generative-vision/hallo

Separate preprocessing of driving images into it's own node

It would be nice to have the preprocessing in it's own node to save memory on a larger workflow with multiple source images.