AIFSH / ComfyUI-Hallo

MIT License
277 stars 13 forks source link

no sd model found? #44

Open hexxter opened 2 months ago

hexxter commented 2 months ago

Screenshot_20240808_204712

how can i set the sd model? It is null?

without i get this error:

find model: /home/alex/KI/ComfyUI/custom_nodes/ComfyUI-Hallo/pretrained_models/face_analysis/models/scrfd_10g_bnkps.onnx detection [1, 3, '?', '?'] 127.5 128.0
set det-size: (640, 640)
No faces detected in the image. Using the entire image as the face region.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1723142528.486053   13763 gl_context_egl.cc:85] Successfully initialized EGL. Major : 1 Minor: 5
I0000 00:00:1723142528.543733   13830 gl_context.cc:357] GL version: 3.2 (OpenGL ES 3.2 NVIDIA 555.42.06), renderer: NVIDIA GeForce RTX 4070/PCIe/SSE2
W0000 00:00:1723142528.544131   13763 face_landmarker_graph.cc:174] Sets FaceBlendshapesGraph acceleration to xnnpack by default.
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
W0000 00:00:1723142528.547903   13838 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1723142528.555137   13847 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
#face is invalid: 0
Traceback (most recent call last):
  File "/home/alex/KI/ComfyUI/custom_nodes/ComfyUI-Hallo/Hallo/scripts/inference.py", line 375, in <module>
    inference_process(command_line_args)
  File "/home/alex/KI/ComfyUI/custom_nodes/ComfyUI-Hallo/Hallo/scripts/inference.py", line 162, in inference_process
    source_image_lip_mask = image_processor.preprocess(
  File "/home/alex/KI/ComfyUI/custom_nodes/ComfyUI-Hallo/Hallo/hallo/datasets/image_processor.py", line 138, in preprocess
    get_mask(source_image_path, cache_dir, face_region_ratio)
  File "/home/alex/KI/ComfyUI/custom_nodes/ComfyUI-Hallo/Hallo/hallo/utils/util.py", line 439, in get_mask
    get_lip_mask(landmarks, height, width, os.path.join(
  File "/home/alex/KI/ComfyUI/custom_nodes/ComfyUI-Hallo/Hallo/hallo/utils/util.py", line 391, in get_lip_mask
    lip_landmarks = np.take(landmarks, lip_ids, 0)
  File "/home/alex/KI/ComfyUI/venv/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 192, in take
    return _wrapfunc(a, 'take', indices, axis=axis, out=out, mode=mode)
  File "/home/alex/KI/ComfyUI/venv/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 59, in _wrapfunc
    return bound(*args, **kwds)
IndexError: cannot do a non-empty take from an empty axes.
yueboxinli commented 2 months ago

model download:

https://huggingface.co/fudan-generative-ai/hallo

emircanerkul commented 15 hours ago

@yueboxinli I already did, i can see all my omnx data within https://github.com/deepinsight/insightface/releases/download/v0.7/antelopev2.zip

But still having same issue.

The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
2024-10-30 08:18:15.3583885 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\pretrained_models\face_analysis\models\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
2024-10-30 08:18:15.8852737 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\pretrained_models\face_analysis\models\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
2024-10-30 08:18:15.9234412 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\pretrained_models\face_analysis\models\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
2024-10-30 08:18:16.0792130 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\pretrained_models\face_analysis\models\glintr100.onnx recognition ['None', 3, 112, 112] 127.5 127.5
2024-10-30 08:18:16.6692921 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\pretrained_models\face_analysis\models\scrfd_10g_bnkps.onnx detection [1, 3, '?', '?'] 127.5 128.0
set det-size: (640, 640)
No faces detected in the image. Using the entire image as the face region.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
W0000 00:00:1730265496.857607   16348 face_landmarker_graph.cc:174] Sets FaceBlendshapesGraph acceleration to xnnpack by default.
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
W0000 00:00:1730265496.866764   15024 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1730265496.878018   15024 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
#face is invalid: 0
Traceback (most recent call last):
  File "C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\Hallo\scripts\inference.py", line 375, in <module>
    inference_process(command_line_args)
  File "C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\Hallo\scripts\inference.py", line 162, in inference_process
    source_image_lip_mask = image_processor.preprocess(
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\Hallo\hallo\datasets\image_processor.py", line 138, in preprocess
    get_mask(source_image_path, cache_dir, face_region_ratio)
  File "C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\Hallo\hallo\utils\util.py", line 439, in get_mask
    get_lip_mask(landmarks, height, width, os.path.join(
  File "C:\Users\emirc\ComfyUI\custom_nodes\ComfyUI-Hallo\Hallo\hallo\utils\util.py", line 391, in get_lip_mask
    lip_landmarks = np.take(landmarks, lip_ids, 0)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\numpy\core\fromnumeric.py", line 192, in take
    return _wrapfunc(a, 'take', indices, axis=axis, out=out, mode=mode)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\emirc\ComfyUI\venv\Lib\site-packages\numpy\core\fromnumeric.py", line 59, in _wrapfunc
    return bound(*args, **kwds)
           ^^^^^^^^^^^^^^^^^^^^
IndexError: cannot do a non-empty take from an empty axes.
Prompt executed in 7.61 seconds

Also same ss image