Custom nodes pack for ComfyUI This custom node helps to conveniently enhance images through Detector, Detailer, Upscaler, Pipe, and more.
License: GNU General Public License v3.0
I didn't copy the original error log text, the error is probably like this"
error log: str obj has no attribute upscale_shape
or when temp_prefix is empty
error log: None obj has no attribute upscale_shape
577 line
refined_latent = IterativeLatentUpscale().doit(latent, upscale_factor, steps, upscaler, temp_prefix)should be
refined_latent = IterativeLatentUpscale().doit(latent, upscale_factor, steps, temp_prefix, upscaler)Hi, i have this error :
Error occurred when executing FaceDetailer:
CUDA error: unknown error
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.`File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 141, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 388, in doit
enhanced_img, cropped_enhanced, mask = FaceDetailer.enhance_face(
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 373, in enhance_face
DetailerForEach.do_detail(image, segs, model, vae, guide_size, guide_size_for, seed, steps, cfg,
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 186, in do_detail
enhanced_pil = core.enhance_detail(cropped_image, model, vae, guide_size, guide_size_for, seg.bbox,
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_core.py", line 235, in enhance_detail
refined_image = vae.decode(refined_latent['samples'])
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 551, in decode
pixel_samples[x:x+batch_number] = torch.clamp((self.first_stage_model.decode(1. / self.scale_factor * samples) + 1.0) / 2.0, min=0.0, max=1.0).cpu()
RuntimeError: CUDA error: unknown error
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile withTORCH_USE_CUDA_DSAto enable device-side assertions.Prompt executed in 1004.94 seconds
Exception in thread Thread-7 (prompt_worker):
Traceback (most recent call last):
File "threading.py", line 1016, in _bootstrap_inner
File "threading.py", line 953, in run
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\main.py", line 37, in prompt_worker
e.execute(item[2], item[1], item[3], item[4])
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 366, in execute
comfy.model_management.soft_empty_cache()
File "B:\ComfyUI\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 436, in soft_empty_cache
torch.cuda.empty_cache()
File "B:\ComfyUI\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\cuda\memory.py", line 133, in empty_cache
torch._C._cuda_emptyCache()
RuntimeError: CUDA error: unknown error
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile withTORCH_USE_CUDA_DSAto enable device-side assertions.
I use :
The used workspace works fine before i update everything.
When queueing more than one image with FaceDetailer in the workflow I get:
Error occurred when executing SaveImage:
list index out of range
File "C:\Users\rober\Downloads\AI Creations\ComfyUI\execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Users\rober\Downloads\AI Creations\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\Users\rober\Downloads\AI Creations\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Users\rober\Downloads\AI Creations\ComfyUI\nodes.py", line 1139, in save_images
full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0])
File "C:\Users\rober\Downloads\AI Creations\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\utils.py", line 200, in getitem
return self.data[index]
i'm getting this error:
D:\ComfyUI_windows_portable\python_embeded\python.exe: No module named mim
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack-Main\install.py", line 83, in ensure_mmdet_package
import mmcv
ModuleNotFoundError: No module named 'mmcv'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1195, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack-Main_init.py", line 16, in
import install # to install dependencies
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack-Main\install.py", line 124, in
install()
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack-Main\install.py", line 96, in install
ensure_mmdet_package()
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack-Main\install.py", line 88, in ensure_mmdet_package
subprocess.check_call(mim_install + ['mmcv==2.0.0'])
File "subprocess.py", line 369, in check_call
subprocess.CalledProcessError: Command '['D:\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', '--user', 'mmcv==2.0.0']' returned non-zero exit status 1.
Cannot import D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack-Main module for custom nodes: Command '['D:\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', '--user', 'mmcv==2.0.0']' returned non-zero exit status 1.
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1195, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-nodes-hnmr-main_init.py", line 3, in
from .sample import KSamplerSetting, KSamplerOverrided, KSamplerXYZ
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-nodes-hnmr-main\sample.py", line 5, in
import comfy.sample
ModuleNotFoundError: No module named 'comfy.sample'
Cannot import D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-nodes-hnmr-main module for custom nodes: No module named 'comfy.sample'
If I want to use FaceDetailer with CLIPSegDetectorProvider to target other thing than faces it obviously can't connect and I'm unsure if the bbox_detector and the sam_model will be in the basic_pipe.
I encountered an error while trying to install packages and import a module in my project. The error message and traceback are as follows:
ERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'D:\ai\image\comfy\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cv2\cv2.pyd'
Consider using the --user option or check the permissions.
Traceback (most recent call last):
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\init.py", line 33, in
import mmcv
ModuleNotFoundError: No module named 'mmcv'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 86, in ensure_mmdet_package
import mmcv
ModuleNotFoundError: No module named 'mmcv'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1513, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in _call_with_frames_removed
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\init.py", line 47, in
do_install()
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\init.py", line 21, in do_install
spec.loader.exec_module(impact_install)
File "", line 883, in exec_module
File "", line 241, in _call_with_frames_removed
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 127, in
install()
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 99, in install
ensure_mmdet_package()
File "D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 91, in ensure_mmdet_package
subprocess.check_call(mim_install + ['mmcv==2.0.0'])
File "subprocess.py", line 369, in check_call
subprocess.CalledProcessError: Command '['D:\ai\image\comfy\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', 'mmcv==2.0.0']' returned non-zero exit status 1.
Cannot import D:\ai\image\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack module for custom nodes: Command '['D:\ai\image\comfy\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', 'mmcv==2.0.0']' returned non-zero exit status 1.
The error suggests that there are permission issues during package installation, specifically related to the file 'cv2.pyd'. Additionally, the 'mmcv' module is missing, which results in a 'ModuleNotFoundError'.
Steps to Reproduce:
Attempt to install packages using the provided installation command.
Observe the permission error and the missing 'mmcv' module error.
Expected Behavior:
The packages should be installed without any permission issues, and the 'mmcv' module should be imported successfully.
Additional Information:
Operating System: Win 11 Pro
Python Version: embedded
Steps attempted to resolve the issue: I tried the troubleshooting, but it did not work. I also tried installing with the manager, same error.
Please let me know if any further information is required.
My comfy installations don't have ComfyUI in the path. While this is safe to assume for those that use the standalone, it's not always true for manual or linux installs. The result is the models are downloaded and stored outside of comfy.
(venv) (base) PS D:\dev\sd.comfy> python .\main.py
Set vram state to: NORMAL_VRAM
Using xformers cross attention
Loading: ComfyUI-Impact-Pack
### ComfyUI-Impact-Pack: Check dependencies
WARNING: Ignoring invalid distribution -rotobuf (d:\dev\sd.py\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (d:\dev\sd.py\venv\lib\site-packages)
WARNING: Ignoring invalid distribution -ensorflow-intel (d:\dev\sd.py\venv\lib\site-packages)
### ComfyUI-Impact-Pack: Check basic models
Downloading https://cdn-lfs.huggingface.co/repos/cb/23/cb23b9f3fd8d6e9aee8c599e9e35770524a6a8efbf3add09ba96af3aada4d144/38208bb6b8a4633193feba532e96ed9a7942129af8fe948b27bfcf8e9a30a12e?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27mmdet_anime-face_yolov3.pth%3B+filename%3D%22mmdet_anime-face_yolov3.pth%22%3B&Expires=1681243449&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jZG4tbGZzLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2NiLzIzL2NiMjNiOWYzZmQ4ZDZlOWFlZThjNTk5ZTllMzU3NzA1MjRhNmE4ZWZiZjNhZGQwOWJhOTZhZjNhYWRhNGQxNDQvMzgyMDhiYjZiOGE0NjMzMTkzZmViYTUzMmU5NmVkOWE3OTQyMTI5YWY4ZmU5NDhiMjdiZmNmOGU5YTMwYTEyZT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE2ODEyNDM0NDl9fX1dfQ__&Signature=hDhyRVkJbH2BDrS502wttB5PU%7E71GyEccJjtJcDcMKasM0ig78LJpL5HZOrVQ8Yw3M97ozjgg6QGCJCJgIjjnjZTX57A9gC2LXnl7seZKzlcyycKEIfn85xDS21sRU4flEXoUE58ebN5uneUug2OYBdC1F-C9s2oV6dx7n7F0dGyaFPEFIyuacit-PRNeGKWGQ-2QCJ0j9cOCGK0%7EEPfWxlEoHYVSQvTPQ-r9PkgqQZXfJDKlxkW2e%7EoPdVjw7VnSaKp8RfAZPZh8Eh4yeEOtE6%7Es%7EuPA3-h--GbEwXZmZqlBRt2KHrrkcqVi1JCtwTIrFuZa77qXMgF31gBJxA-iw__&Key-Pair-Id=KVTP0A1DKRTAX to D:\dev\ComfyUI\models\mmdets\bbox\mmdet_anime-face_yolov3.pth
100%|██████████████████████████████████████████████████████████████| 246462357/246462357 [00:23<00:00, 10356830.11it/s]
Downloading https://raw.githubusercontent.com/Bing-su/dddetailer/master/config/mmdet_anime-face_yolov3.py to D:\dev\ComfyUI\models\mmdets\bbox\mmdet_anime-face_yolov3.py
100%|█████████████████████████████████████████████████████████████████████████| 5418/5418 [00:00<00:00, 5430045.18it/s]
Downloading https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth to D:\dev\ComfyUI\models\sams\sam_vit_b_01ec64.pth
100%|██████████████████████████████████████████████████████████████| 375042383/375042383 [00:16<00:00, 22838873.68it/s]
I changed comfyui-impact-pack.py
#if os.path.realpath("..").endswith("custom_nodes"):
# # For user
# comfy_path = os.path.realpath("../..")
#else:
# # For development
# comfy_path = os.path.realpath("../ComfyUI")
#-- hacked the above out. Probably better to search for "main.py", since main.py is in the root of comfy install.
comfy_path = os.path.realpath("./")
and it detects the models
this is the error that pops up in the center of the comfyui window
When loading the graph, the following node types were not found:
Float
Integer
Nodes that have failed to load will show as red on the graph.
I used this version ComfyUI_windows_portable_nvidia_cu118_or_cpu, and run update_comfyui.bat
But still don't work.
Could you help me to solve this? Thank you so much!
Everytime I start ComfyUI, these message would come out.
What should I do?
I'm not a programmer, I don't know what are these means.
Thank you so much!
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting openmim (from -r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/b9/19/f7436e610163f65ff83de5a768180e73765e54bdaee5f5f37983aa3171b9/openmim-0.3.7-py2.py3-none-any.whl (51 kB)
Collecting segment-anything (from -r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 2))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/75/77/8e0c16abf151a1dd076b562febc0da2ecf1132b0b41826087af96f101f42/segment_anything-1.0-py3-none-any.whl (36 kB)
Requirement already satisfied: scikit-image in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from -r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (0.20.0)
Collecting Click (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/c2/f1/df59e28c642d583f7dacffb1e0965d0e00b218e0186d7858ac5233dce840/click-8.1.3-py3-none-any.whl (96 kB)
Requirement already satisfied: colorama in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (0.4.6)
Collecting model-index (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/0f/a6/4d4cbbef704f186d143e2859296a610a355992e4eae71582bd598093b36a/model_index-0.1.11-py3-none-any.whl (34 kB)
Collecting pandas (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/90/30/8b857447b0f4b59d5bd84e934e82ef8c82b73d71d1c9611c8aaaa8d44a50/pandas-2.0.1-cp310-cp310-win_amd64.whl (10.7 MB)
Requirement already satisfied: pip>=19.3 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (23.1.2)
Requirement already satisfied: requests in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (2.29.0)
Collecting rich (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/39/03/6de23bdd88f5ee7f8b03f94f6e88108f5d7ffe6d207e95cdb06d9aa4cd57/rich-13.3.5-py3-none-any.whl (238 kB)
Requirement already satisfied: tabulate in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (0.9.0)
Requirement already satisfied: numpy>=1.21.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (1.24.3)
Requirement already satisfied: scipy>=1.8 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (1.10.1)
Requirement already satisfied: networkx>=2.8 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (3.1)
Requirement already satisfied: pillow>=9.0.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (9.5.0)
Requirement already satisfied: imageio>=2.4.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (2.28.0)
Requirement already satisfied: tifffile>=2019.7.26 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (2023.4.12)
Requirement already satisfied: PyWavelets>=1.1.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (1.4.1)
Requirement already satisfied: packaging>=20.0 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (23.1)
Requirement already satisfied: lazy_loader>=0.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scikit-image->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 3)) (0.2)
Requirement already satisfied: pyyaml in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from model-index->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (6.0)
Collecting markdown (from model-index->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/9a/a1/1352b0e5a3c71a79fa9265726e2217f69df9fd4de0bcb5725cc61f62a5df/Markdown-3.4.3-py3-none-any.whl (93 kB)
Collecting ordered-set (from model-index->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/33/55/af02708f230eb77084a299d7b08175cff006dea4f2721074b92cdb0296c0/ordered_set-4.1.0-py3-none-any.whl (7.6 kB)
Requirement already satisfied: python-dateutil>=2.8.2 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from pandas->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (2.8.2)
Collecting pytz>=2020.1 (from pandas->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/7f/99/ad6bd37e748257dd70d6f85d916cafe79c0b0f5e2e95b11f7fbc82bf3110/pytz-2023.3-py2.py3-none-any.whl (502 kB)
Collecting tzdata>=2022.1 (from pandas->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d5/fb/a79efcab32b8a1f1ddca7f35109a50e4a80d42ac1c9187ab46522b2407d7/tzdata-2023.3-py2.py3-none-any.whl (341 kB)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (3.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (1.26.15)
Requirement already satisfied: certifi>=2017.4.17 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (2022.12.7)
Collecting markdown-it-py<3.0.0,>=2.2.0 (from rich->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/bf/25/2d88e8feee8e055d015343f9b86e370a1ccbec546f2865c98397aaef24af/markdown_it_py-2.2.0-py3-none-any.whl (84 kB)
Collecting pygments<3.0.0,>=2.13.0 (from rich->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/34/a7/37c8d68532ba71549db4212cb036dbd6161b40e463aba336770e80c72f84/Pygments-2.15.1-py3-none-any.whl (1.1 MB)
Collecting mdurl~=0.1 (from markdown-it-py<3.0.0,>=2.2.0->rich->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1))
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/b3/38/89ba8ad64ae25be8de66a6d463314cf1eb366222074cfda9ee839c56a4b4/mdurl-0.1.2-py3-none-any.whl (10.0 kB)
Requirement already satisfied: six>=1.5 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from python-dateutil>=2.8.2->pandas->openmim->-r D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt (line 1)) (1.16.0)
Installing collected packages: segment-anything, pytz, tzdata, pygments, ordered-set, mdurl, markdown, Click, pandas, model-index, markdown-it-py, rich, openmim
WARNING: The script pygmentize.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script markdown_py.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script mi.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script markdown-it.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script mim.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
Successfully installed Click-8.1.3 markdown-3.4.3 markdown-it-py-2.2.0 mdurl-0.1.2 model-index-0.1.11 openmim-0.3.7 ordered-set-4.1.0 pandas-2.0.1 pygments-2.15.1 pytz-2023.3 rich-13.3.5 segment-anything-1.0 tzdata-2023.3
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting pycocotools==2.0.6
Downloading https://github.com/Bing-su/dddetailer/releases/download/pycocotools/pycocotools-2.0.6-cp310-cp310-win_amd64.whl (75 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 76.0/76.0 kB 831.8 kB/s eta 0:00:00
Requirement already satisfied: matplotlib>=2.1.0 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from pycocotools==2.0.6) (3.7.1)
Requirement already satisfied: numpy in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from pycocotools==2.0.6) (1.24.3)
Requirement already satisfied: contourpy>=1.0.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (1.0.7)
Requirement already satisfied: cycler>=0.10 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (4.39.3)
Requirement already satisfied: kiwisolver>=1.0.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (1.4.4)
Requirement already satisfied: packaging>=20.0 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (23.1)
Requirement already satisfied: pillow>=6.2.0 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (9.5.0)
Requirement already satisfied: pyparsing>=2.3.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (3.0.9)
Requirement already satisfied: python-dateutil>=2.7 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from matplotlib>=2.1.0->pycocotools==2.0.6) (2.8.2)
Requirement already satisfied: six>=1.5 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from python-dateutil>=2.7->matplotlib>=2.1.0->pycocotools==2.0.6) (1.16.0)
Installing collected packages: pycocotools
Successfully installed pycocotools-2.0.6
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting openmim
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/b9/19/f7436e610163f65ff83de5a768180e73765e54bdaee5f5f37983aa3171b9/openmim-0.3.7-py2.py3-none-any.whl (51 kB)
Collecting Click (from openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/c2/f1/df59e28c642d583f7dacffb1e0965d0e00b218e0186d7858ac5233dce840/click-8.1.3-py3-none-any.whl (96 kB)
Requirement already satisfied: colorama in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim) (0.4.6)
Collecting model-index (from openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/0f/a6/4d4cbbef704f186d143e2859296a610a355992e4eae71582bd598093b36a/model_index-0.1.11-py3-none-any.whl (34 kB)
Collecting pandas (from openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/90/30/8b857447b0f4b59d5bd84e934e82ef8c82b73d71d1c9611c8aaaa8d44a50/pandas-2.0.1-cp310-cp310-win_amd64.whl (10.7 MB)
Requirement already satisfied: pip>=19.3 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim) (23.1.2)
Requirement already satisfied: requests in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim) (2.29.0)
Collecting rich (from openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/39/03/6de23bdd88f5ee7f8b03f94f6e88108f5d7ffe6d207e95cdb06d9aa4cd57/rich-13.3.5-py3-none-any.whl (238 kB)
Requirement already satisfied: tabulate in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from openmim) (0.9.0)
Requirement already satisfied: pyyaml in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from model-index->openmim) (6.0)
Collecting markdown (from model-index->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/9a/a1/1352b0e5a3c71a79fa9265726e2217f69df9fd4de0bcb5725cc61f62a5df/Markdown-3.4.3-py3-none-any.whl (93 kB)
Collecting ordered-set (from model-index->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/33/55/af02708f230eb77084a299d7b08175cff006dea4f2721074b92cdb0296c0/ordered_set-4.1.0-py3-none-any.whl (7.6 kB)
Requirement already satisfied: python-dateutil>=2.8.2 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from pandas->openmim) (2.8.2)
Collecting pytz>=2020.1 (from pandas->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/7f/99/ad6bd37e748257dd70d6f85d916cafe79c0b0f5e2e95b11f7fbc82bf3110/pytz-2023.3-py2.py3-none-any.whl (502 kB)
Collecting tzdata>=2022.1 (from pandas->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d5/fb/a79efcab32b8a1f1ddca7f35109a50e4a80d42ac1c9187ab46522b2407d7/tzdata-2023.3-py2.py3-none-any.whl (341 kB)
Requirement already satisfied: numpy>=1.21.0 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from pandas->openmim) (1.24.3)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim) (3.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim) (1.26.15)
Requirement already satisfied: certifi>=2017.4.17 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->openmim) (2022.12.7)
Collecting markdown-it-py<3.0.0,>=2.2.0 (from rich->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/bf/25/2d88e8feee8e055d015343f9b86e370a1ccbec546f2865c98397aaef24af/markdown_it_py-2.2.0-py3-none-any.whl (84 kB)
Collecting pygments<3.0.0,>=2.13.0 (from rich->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/34/a7/37c8d68532ba71549db4212cb036dbd6161b40e463aba336770e80c72f84/Pygments-2.15.1-py3-none-any.whl (1.1 MB)
Collecting mdurl~=0.1 (from markdown-it-py<3.0.0,>=2.2.0->rich->openmim)
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/b3/38/89ba8ad64ae25be8de66a6d463314cf1eb366222074cfda9ee839c56a4b4/mdurl-0.1.2-py3-none-any.whl (10.0 kB)
Requirement already satisfied: six>=1.5 in d:\ai\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from python-dateutil>=2.8.2->pandas->openmim) (1.16.0)
Installing collected packages: pytz, tzdata, pygments, ordered-set, mdurl, markdown, Click, pandas, model-index, markdown-it-py, rich, openmim
WARNING: The script pygmentize.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script markdown_py.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script mi.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script markdown-it.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
WARNING: The script mim.exe is installed in 'C:\Users\PC\AppData\Roaming\Python\Python310\Scripts' which is not on PATH.
Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
Successfully installed Click-8.1.3 markdown-3.4.3 markdown-it-py-2.2.0 mdurl-0.1.2 model-index-0.1.11 openmim-0.3.7 ordered-set-4.1.0 pandas-2.0.1 pygments-2.15.1 pytz-2023.3 rich-13.3.5 tzdata-2023.3
D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe: No module named mim
Traceback (most recent call last):
File "D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 83, in ensure_mmdet_package
import mmcv
ModuleNotFoundError: No module named 'mmcv'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1354, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack_init.py", line 16, in
import install # to install dependencies
File "D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 124, in
install()
File "D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 96, in install
ensure_mmdet_package()
File "D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 88, in ensure_mmdet_package
subprocess.check_call(mim_install + ['mmcv==2.0.0'])
File "subprocess.py", line 369, in check_call
subprocess.CalledProcessError: Command '['D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', '--user', 'mmcv==2.0.0']' returned non-zero exit status 1.
Cannot import D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack module for custom nodes: Command '['D:\AI\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', '--user', 'mmcv==2.0.0']' returned non-zero exit status 1.
I have a binary mask that I am passing through the Mask to Segs node, but it only shows a very small sliver of the mask.
I have literally no idea what I am doing wrong. This worked fine before with other sections of the body.
I noticed that some samplers give very bad results with TwoAdvancedSamplersForMask so I did some tests.
The first set is with denoising set to 1, second is using it with upscaling at 0.45 denoising. Different lora models are applied to each KSamplerAdvancedProvider. There is also the controlnet pose I was using to hold the character together, but it doesn't matter much without a bigger frame.
Several samplers produce very bad results.
I also did a round with denoising at 1 using the normal TwoSamplersForMask:
On a slightly different note, with the addition of the TwoAdvancedSamplersForMask, it only seems fitting to have a TwoAdvancedSamplersFor Mask Upscaler Provider along with a pipe variant like with the simple version of the node. Unless there are issues with this?
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 257, in execute
recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed, prompt_id, self.outputs_ui)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 128, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_pack.py", line 846, in doit
refined_latent = IterativeLatentUpscale().doit(latent, upscale_factor, steps, temp_prefix, upscaler, unique_id)
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_pack.py", line 801, in doit
current_latent = upscaler.upscale_shape(step_info, current_latent, new_w, new_h, temp_prefix)
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_core.py", line 1106, in upscale_shape
refined_latent = self.tiled_ksample(upscaled_latent)
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_core.py", line 1073, in tiled_ksample
return TiledKSampler().sample(model, seed, tile_width, tile_height, tiling_strategy, steps, cfg, sampler_name, scheduler,
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI_TiledKSampler/nodes.py", line 266, in sample
return sample_common(model, 'enable', seed, tile_width, tile_height, tiling_strategy, steps_total, cfg, sampler_name, scheduler, positive, negative, latent_image, steps_total-steps, steps_total, 'disable', denoise=1.0)
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI_TiledKSampler/nodes.py", line 230, in sample_common
tile_result = sampler.sample(tiled_noise, pos, neg, cfg=cfg, latent_image=tiled_latent, start_step=start_at_step + i * tile_steps, last_step=start_at_step + i*tile_steps + tile_steps, force_full_denoise=force_full_denoise and i+1 == end_at_step - start_at_step, denoise_mask=tiled_mask, callback=callback, disable_pbar=True)
File "/home/poisenbery/AI_Stuff/ComfyUI/comfy/samplers.py", line 684, in sample
samples = getattr(k_diffusion_sampling, "sample_{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
File "/home/poisenbery/AI_Stuff/ComfyUI/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/poisenbery/AI_Stuff/ComfyUI/comfy/k_diffusion/sampling.py", line 649, in sample_dpmpp_2m_sde
h_last = h
UnboundLocalError: local variable 'h' referenced before assignment
I'm not sure if this goes in this repo or the tiledKsampler repo
dmpdd_2m_sde will always give me this error
The following error is seen when installing with a venv install.py
was resolved locally when I installed mmcv manually.
ERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'F:\\Generative AI\\ComfyUI\\venv\\Lib\\site-packages\\cv2\\cv2.pyd' Check the permissions.
Traceback (most recent call last):
File "F:\Generative AI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 86, in ensure_mmdet_package
import mmcv
ModuleNotFoundError: No module named 'mmcv'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "F:\Generative AI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 127, in
install()
File "F:\Generative AI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 99, in install
ensure_mmdet_package()
File "F:\Generative AI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 91, in ensure_mmdet_package
subprocess.check_call(mim_install + ['mmcv==2.0.0'])
File "C:\Program Files\Python310\lib\subprocess.py", line 369, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['F:\Generative AI\ComfyUI\venv\Scripts\python.exe', '-m', 'mim', 'install', 'mmcv==2.0.0']' returned non-zero exit status 1.
I'm wondering if there are any other detection models.
The anime face detection works great for anime but doesn't work well for other styles.
I've tried setting the threshold low and I'm not getting any detection on many faces.
When batch_size > 1 in Empty Latent Image node and Detailer (SEGS) node exists in pipe then this error occurs
p.s.: this is sample workflow from this project (advanced-simple.json).
I have the following setup:
I would expect this to run each detailer on a different face as marked with the mask in the Image Loader. After some operations, it results in the masks I want as demonstrated on the preview nodes. However, both detailers run for both faces for some reason.
That's how this works, right? There's no documentation so I just assumed. Does it need to be human guts? Or maybe I need to beseech zeus for his favor?
Traceback (most recent call last):
File "D:\AI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1205, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 879, in exec_module
File "", line 1016, in get_code
File "", line 1073, in get_data
FileNotFoundError: [Errno 2] No such file or directory: 'D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\init.py'
This was working until I updated to commit 9c13ec6. The functionality is still there, just that you can no longer see what the wildcards are being populated with.
Newbie here, looked for the answer myself but I don't really know what to search for.
I loaded the detailed image from the How to section, increased the batch_size to 2 and started the queue.
After generating the first one it display this error message.
How do I avoid this issue when queuing multiple images?
EDIT: this also happens witth a simple prompt ex.: "a dog"
Error occurred when executing FaceDetailer:
pic should be 2/3 dimensional. Got 4 dimensions.
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\ComfyUI\execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 826, in doit
enhanced_img, cropped_enhanced, cropped_enhanced_alpha, mask = FaceDetailer.enhance_face(
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 799, in enhance_face
sam_mask = core.make_sam_mask(sam_model_opt, segs, image, sam_detection_hint, sam_dilation,
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 335, in make_sam_mask
predictor.set_image(image, "RGB")
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\python_embeded\lib\site-packages\segment_anything\predictor.py", line 56, in set_image
input_image = self.transform.apply_image(image)
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\python_embeded\lib\site-packages\segment_anything\utils\transforms.py", line 31, in apply_image
return np.array(resize(to_pil_image(image), target_size))
File "C:\Users\my_user\Desktop\ComfyUI_windows_portable\python_embeded\lib\site-packages\torchvision\transforms\functional.py", line 278, in to_pil_image
raise ValueError(f"pic should be 2/3 dimensional. Got {pic.ndim} dimensions.")
Your image:
The first image for my settings (just increased batch_size):
PS C:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack> C:\ComfyUI\python_embeded\python.exe install.py
Traceback (most recent call last):
File "C:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\install.py", line 15, in <module>
import impact_config
ModuleNotFoundError: No module named 'impact_config'
The right image is displayed on the node so it receives it correctly, but it looks in the wrong directory when trying to output it
The example from https://github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Impact-Pack/tutorial/ONNX.md https://github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Impact-Pack/misc/onnx.json does not work:
Traceback (most recent call last):
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 257, in execute
recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed, prompt_id, self.outputs_ui)
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 128, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "H:\ComfyUI_windows_portable\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "H:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 981, in doit
return (core.segs_to_combined_mask(segs), )
File "H:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_core.py", line 628, in segs_to_combined_mask
shape = segs[0]
TypeError: 'NoneType' object is not subscriptable
Hi, I am running https://raw.githubusercontent.com/ltdrdata/ComfyUI-extension-tutorials/Main/ComfyUI-Impact-Pack/images/simple.png as an example and got this:
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 20 but got size 19 for tensor number 1 in the list.
I have tried setting it up on my own and using different models but no luck. Any ideas?
Windows 10, comfy portable, I have tried different models.
Thanks!
-Aaron
Hi!
When I install it, I saw the success message.
### ComfyUI-Impact-Pack: Check basic models
Installation was successful.
After restarting ComfyUI, please refresh the browser.
FECTH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.jsonBut when rebooting ComfyUI, this error happens.
### ComfyUI-Impact-Pack: Check basic models
Traceback (most recent call last):
File "/Users/ocean/main/ComfyUI/nodes.py", line 1422, in load_custom_node
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 883, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "/Users/ocean/main/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/__init__.py", line 47, in <module>
import impact.impact_server # to load server api
File "/Users/ocean/main/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_server.py", line 8, in <module>
import impact.core as core
File "/Users/ocean/main/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 3, in <module>
from mmdet.apis import (inference_detector, init_detector)
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/apis/__init__.py", line 2, in <module>
from .det_inferencer import DetInferencer
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/apis/det_inferencer.py", line 21, in <module>
from mmdet.evaluation import INSTANCE_OFFSET
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/evaluation/__init__.py", line 3, in <module>
from .metrics import * # noqa: F401,F403
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/evaluation/metrics/__init__.py", line 3, in <module>
from .coco_metric import CocoMetric
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/evaluation/metrics/coco_metric.py", line 18, in <module>
from mmdet.structures.mask import encode_mask_results
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/structures/mask/__init__.py", line 3, in <module>
from .structures import (BaseInstanceMasks, BitmapMasks, PolygonMasks,
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmdet/structures/mask/structures.py", line 12, in <module>
from mmcv.ops.roi_align import roi_align
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmcv/ops/__init__.py", line 2, in <module>
from .active_rotated_filter import active_rotated_filter
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmcv/ops/active_rotated_filter.py", line 10, in <module>
ext_module = ext_loader.load_ext(
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmcv/utils/ext_loader.py", line 13, in load_ext
ext = importlib.import_module('mmcv.' + name)
File "/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/importlib/__init__.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
ImportError: dlopen(/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmcv/_ext.cpython-310-darwin.so, 0x0002): symbol not found in flat namespace '__ZN2at3mps9MPSStream6commitEb'
Cannot import /Users/ocean/main/ComfyUI/custom_nodes/ComfyUI-Impact-Pack module for custom nodes: dlopen(/Users/ocean/miniconda3/envs/comfyui/lib/python3.10/site-packages/mmcv/_ext.cpython-310-darwin.so, 0x0002): symbol not found in flat namespace '__ZN2at3mps9MPSStream6commitEb'
Import times for custom nodes:
0.0 seconds: /Users/ocean/main/ComfyUI/custom_nodes/sampler_rescalecfg.py
0.1 seconds: /Users/ocean/main/ComfyUI/custom_nodes/ComfyUI-Manager
7.3 seconds (IMPORT FAILED): /Users/ocean/main/ComfyUI/custom_nodes/ComfyUI-Impact-Pack
Starting server
To see the GUI go to: http://127.0.0.1:8188I wonder the cause 🧐
Thanks.
Info:
I found the upscale to guidesize very unpredictable - sometimes deciding not to upscale at all even if it should, sometimes overblowing the resolution extremely.
I messed around with it and changed the upscale value in the code to use the cropped area height or width instead of using the BBox height and width to get the final resolution, which then upscales it to the proper guide size , which seems to work better.
upscale = guide_size/min(h,w)
¡Hello!
I have been using AITemplate for a bit now. This repo: https://github.com/hlky/AIT
And now I started testing the detailing nodes and they throw up an error with AITemplate.
AITemplate requires sizes to be on multiples of 64 and so far FaceDetailer has generated non compatible sizes, is there a way to add AITemplate compatibility by having a node that enforces sizes to be on multiples of 64, or is it already possible to have it generate on said multiples?
EDIT: Got a workaround by switching to crop_region and set guide size to 512, AIT generates on multiples of 64 STARTING on 512 it seems.
On pic related it generated an area of 766, 832 which are no go for AIT
Hi.... ComfyUI-CLIPSeg is no more update for the latest ComfyUI.
I can't install this plugin.
What's your plan for this？
Thank you！
Hi, I've got a fresh install of ComfyUI and followed the installation instructions here but it says import failed after I launch ComfyUI. I tried other custom nodes and they work but for some reason I can't get this one working. Any help would be appreciated!
Here's the full log:
C:\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
Total VRAM 10240 MB, total RAM 16306 MB
xformers version: 0.0.20
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3080
Using xformers cross attention
### Loading: ComfyUI-Impact-Pack (V2.15.3)
Traceback (most recent call last):
File "C:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1416, in load_custom_node
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 883, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\__init__.py", line 48, in <module>
import impact.impact_server # to load server api
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_server.py", line 8, in <module>
import impact.core as core
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 1166, in <module>
import comfy.latent_formats as latent_formats
ModuleNotFoundError: No module named 'comfy.latent_formats'
Cannot import C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack module for custom nodes: No module named 'comfy.latent_formats'
Import times for custom nodes:
1.0 seconds (IMPORT FAILED): C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
Starting server
To see the GUI go to: http://127.0.0.1:8188
I get the following error message every time I attempt to build pycocotools-2.0.6 when attempting to install the impact pack.
Building wheels for collected packages: pycocotools
Building wheel for pycocotools (pyproject.toml) ... error
error: subprocess-exited-with-error
× Building wheel for pycocotools (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [77 lines of output]
running bdist_wheel
running build
running build_py
creating build
creating build/lib.linux-x86_64-cpython-38
creating build/lib.linux-x86_64-cpython-38/pycocotools
copying pycocotools/mask.py -> build/lib.linux-x86_64-cpython-38/pycocotools
copying pycocotools/cocoeval.py -> build/lib.linux-x86_64-cpython-38/pycocotools
copying pycocotools/coco.py -> build/lib.linux-x86_64-cpython-38/pycocotools
copying pycocotools/__init__.py -> build/lib.linux-x86_64-cpython-38/pycocotools
running build_ext
cythoning pycocotools/_mask.pyx to pycocotools/_mask.c
building 'pycocotools._mask' extension
creating build/temp.linux-x86_64-cpython-38
creating build/temp.linux-x86_64-cpython-38/common
creating build/temp.linux-x86_64-cpython-38/pycocotools
gcc -pthread -B /home/david/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/tmp/pip-build-env-kc76w2j3/overlay/lib/python3.8/site-packages/numpy/core/include -I./common -I/home/david/anaconda3/include/python3.8 -c ./common/maskApi.c -o build/temp.linux-x86_64-cpython-38/./common/maskApi.o -Wno-cpp -Wno-unused-function -std=c99
./common/maskApi.c: In function ‘rleToBbox’:
./common/maskApi.c:151:32: warning: unused variable ‘xp’ [-Wunused-variable]
151 | uint h, w, xs, ys, xe, ye, xp, cc; siz j, m;
| ^~
./common/maskApi.c: In function ‘rleFrPoly’:
./common/maskApi.c:197:3: warning: this ‘for’ clause does not guard... [-Wmisleading-indentation]
197 | for(j=0; j<k; j++) x[j]=(int)(scale*xy[j*2+0]+.5); x[k]=x[0];
| ^~~
./common/maskApi.c:197:54: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘for’
197 | for(j=0; j<k; j++) x[j]=(int)(scale*xy[j*2+0]+.5); x[k]=x[0];
| ^
./common/maskApi.c:198:3: warning: this ‘for’ clause does not guard... [-Wmisleading-indentation]
198 | for(j=0; j<k; j++) y[j]=(int)(scale*xy[j*2+1]+.5); y[k]=y[0];
| ^~~
./common/maskApi.c:198:54: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘for’
198 | for(j=0; j<k; j++) y[j]=(int)(scale*xy[j*2+1]+.5); y[k]=y[0];
| ^
./common/maskApi.c: In function ‘rleToString’:
./common/maskApi.c:243:7: warning: this ‘if’ clause does not guard... [-Wmisleading-indentation]
243 | if(more) c |= 0x20; c+=48; s[p++]=c;
| ^~
./common/maskApi.c:243:27: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘if’
243 | if(more) c |= 0x20; c+=48; s[p++]=c;
| ^
./common/maskApi.c: In function ‘rleFrString’:
./common/maskApi.c:251:3: warning: this ‘while’ clause does not guard... [-Wmisleading-indentation]
251 | while( s[m] ) m++; cnts=malloc(sizeof(uint)*m); m=0;
| ^~~~~
./common/maskApi.c:251:22: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘while’
251 | while( s[m] ) m++; cnts=malloc(sizeof(uint)*m); m=0;
| ^~~~
./common/maskApi.c:259:5: warning: this ‘if’ clause does not guard... [-Wmisleading-indentation]
259 | if(m>2) x+=(long) cnts[m-2]; cnts[m++]=(uint) x;
| ^~
./common/maskApi.c:259:34: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘if’
259 | if(m>2) x+=(long) cnts[m-2]; cnts[m++]=(uint) x;
| ^~~~
gcc -pthread -B /home/david/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/tmp/pip-build-env-kc76w2j3/overlay/lib/python3.8/site-packages/numpy/core/include -I./common -I/home/david/anaconda3/include/python3.8 -c pycocotools/_mask.c -o build/temp.linux-x86_64-cpython-38/pycocotools/_mask.o -Wno-cpp -Wno-unused-function -std=c99
pycocotools/_mask.c: In function ‘__pyx_pf_11pycocotools_5_mask_12iou’:
pycocotools/_mask.c:6162:31: warning: comparison of integer expressions of different signedness: ‘Py_ssize_t’ {aka ‘long int’} and ‘siz’ {aka ‘long unsigned int’} [-Wsign-compare]
6162 | if (unlikely(!((__pyx_t_8 == __pyx_v_n) != 0))) {
| ^~
pycocotools/_mask.c:938:43: note: in definition of macro ‘unlikely’
938 | #define unlikely(x) __builtin_expect(!!(x), 0)
| ^
gcc -pthread -shared -B /home/david/anaconda3/compiler_compat -L/home/david/anaconda3/lib -Wl,-rpath=/home/david/anaconda3/lib -Wl,--no-as-needed -Wl,--sysroot=/ build/temp.linux-x86_64-cpython-38/./common/maskApi.o build/temp.linux-x86_64-cpython-38/pycocotools/_mask.o -o build/lib.linux-x86_64-cpython-38/pycocotools/_mask.cpython-38-x86_64-linux-gnu.so
/home/david/anaconda3/compiler_compat/ld: /usr/lib/libc.so.6: unknown type [0x13] section `.relr.dyn'
/home/david/anaconda3/compiler_compat/ld: skipping incompatible /usr/lib/libc.so.6 when searching for /usr/lib/libc.so.6
/home/david/anaconda3/compiler_compat/ld: /usr/lib/libc.so.6: unknown type [0x13] section `.relr.dyn'
/home/david/anaconda3/compiler_compat/ld: skipping incompatible /usr/lib/libc.so.6 when searching for /usr/lib/libc.so.6
/home/david/anaconda3/compiler_compat/ld: cannot find /usr/lib/libc.so.6
/home/david/anaconda3/compiler_compat/ld: /usr/lib/ld-linux-x86-64.so.2: unknown type [0x13] section `.relr.dyn'
/home/david/anaconda3/compiler_compat/ld: skipping incompatible /usr/lib/ld-linux-x86-64.so.2 when searching for /usr/lib/ld-linux-x86-64.so.2
/home/david/anaconda3/compiler_compat/ld: /usr/lib/ld-linux-x86-64.so.2: unknown type [0x13] section `.relr.dyn'
/home/david/anaconda3/compiler_compat/ld: skipping incompatible /usr/lib/ld-linux-x86-64.so.2 when searching for /usr/lib/ld-linux-x86-64.so.2
/home/david/anaconda3/compiler_compat/ld: cannot find /usr/lib/ld-linux-x86-64.so.2
collect2: error: ld returned 1 exit status
/tmp/pip-build-env-kc76w2j3/overlay/lib/python3.8/site-packages/Cython/Compiler/Main.py:369: FutureWarning: Cython directive 'language_level' not set, using 2 for now (Py2). This will change in a later release! File: /tmp/pip-install-s60dy_02/pycocotools_c1ed8a2714aa4d5eb6b5c8cfe682c99f/pycocotools/_mask.pyx
tree = Parsing.p_module(s, pxd, full_module_name)
error: command '/usr/bin/gcc' failed with exit code 1
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for pycocotools
Failed to build pycocotools
ERROR: Could not build wheels for pycocotools, which is required to install pyproject.toml-based projects
I can't load Impact pack. I have this error :
File "S:\ComfyUI\nodes.py", line 1514, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "S:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack_init.py", line 75, in
impact.wildcards.read_wildcard_dict(wildcards_path)
File "S:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\wildcards.py", line 19, in read_wildcard_dict
lines = f.read().splitlines()
File "C:\Users\kaned\AppData\Local\Programs\Python\Python310\lib\encodings\cp1252.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x8d in position 2282: character maps toCannot import S:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack module for custom nodes: 'charmap' codec can't decode byte 0x8d in position 2282: character maps to
How fix it ? Thanks
Any detailer nodes I try cause this exception when the batch size is 2 or higher.
Error occurred when executing DetailerForEachDebugPipe:
Cannot handle this data type: (1, 1, 1024, 3), |u1
File "C:\Path\To\ComfyUI\execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Path\To\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\Path\To\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Path\To\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 1406, in doit
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
File "C:\Path\To\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 388, in do_detail
image_pil = tensor2pil(image).convert('RGBA')
File "C:\Path\To\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\utils.py", line 14, in tensor2pil
return Image.fromarray(np.clip(255. * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8))
File "C:\Path\To\ComfyUI\venv\lib\site-packages\PIL\Image.py", line 3092, in fromarray
raise TypeError(msg) from e
Heyo, I was having lots of luck with the AnimeFace detector with the detailer node. It seems that it detects each face, and does an img2img on EACH one, resulting in very high quality outputs.
I downloaded the Person-Mask2Former model, thinking that it would work the same, but I get an error no matter what I try doing:
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 257, in execute
recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed, prompt_id, self.outputs_ui)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 120, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed, prompt_id, outputs_ui)
[Previous line repeated 1 more time]
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 128, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/home/poisenbery/AI_Stuff/ComfyUI/execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_pack.py", line 55, in load_mmdet
model = core.load_mmdet(mmdet_path)
File "/home/poisenbery/AI_Stuff/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_core.py", line 35, in load_mmdet
model = init_detector(model_config, model_path, device="cpu")
File "/home/poisenbery/AI_Stuff/ComfyUI/venv/lib/python3.10/site-packages/mmdet/apis/inference.py", line 61, in init_detector
model = MODELS.build(config.model)
File "/home/poisenbery/AI_Stuff/ComfyUI/venv/lib/python3.10/site-packages/mmengine/registry/registry.py", line 545, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/home/poisenbery/AI_Stuff/ComfyUI/venv/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 241, in build_model_from_cfg
return build_from_cfg(cfg, registry, default_args)
File "/home/poisenbery/AI_Stuff/ComfyUI/venv/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 135, in build_from_cfg
raise type(e)(
AttributeError: class `Mask2Former` in mmdet/models/detectors/mask2former.py: class `Mask2FormerHead` in mmdet/models/dense_heads/mask2former_head.py: 'ConfigDict' object has no attribute 'layer_cfg
How can I use Person-Mask2Former to achieve similar effect on multiple subjects?
using this script
WORKFLOW("impact-1", async ({ presets, flow, graph }) => {
const preset = await presets.basicImageGeneration({
positive: `(masterpiece, top quality, best quality), portrait, 1girl, blue eyes`,
negative: "worst quality,",
ckptName: "AOM3A1_orangemixs.safetensors",
steps: 20,
cfg: 7,
width: 512,
height: 512,
batchSize: 1,
})
const mask = graph.ImpactSegmDetectorCombined({
dilation: 0,
image: preset.image,
segm_model: graph.ImpactMMDetLoader({ model_name: "bbox/mmdet_anime-face_yolov3.pth" }),
threshold: 0.5,
})
graph.SaveImage({ images: graph.MaskToImage({ mask }), filename_prefix: "impact" })
await flow.PROMPT()
})it generates
that fails because of some missing positional argument
Loads checkpoint by local backend from path: C:\Users\user\dev\intuition\ComfyUI\models\mmdets\bbox/mmdet_anime-face_yolov3.pth
Traceback (most recent call last):
File "C:\Users\user\dev\intuition\ComfyUI\execution.py", line 195, in execute
recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed)
File "C:\Users\user\dev\intuition\ComfyUI\execution.py", line 58, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed)
File "C:\Users\user\dev\intuition\ComfyUI\execution.py", line 58, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed)
File "C:\Users\user\dev\intuition\ComfyUI\execution.py", line 67, in recursive_execute
outputs[unique_id] = getattr(obj, obj.FUNCTION)(**input_data_all)
File "C:\Users\user\dev\intuition\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 1369, in doit
mmdet_results = inference_segm(segm_model, image, threshold)
TypeError: inference_segm() missing 1 required positional argument: 'label'
related to ?
def inference_segm(image, modelname, conf_thres, label):
def inference_segm_old(model, image, conf_threshold):With the workflow:
I get the following error:
Loads checkpoint by local backend from path: E:\code\stable-difusion\ComfyUI\models\mmdets\bbox/mmdet_anime-face_yolov3.pth
Traceback (most recent call last):
File "E:\code\stable-difusion\ComfyUI\execution.py", line 197, in execute
recursive_execute(self.server, prompt, self.outputs, x, extra_data, executed)
File "E:\code\stable-difusion\ComfyUI\execution.py", line 58, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed)
File "E:\code\stable-difusion\ComfyUI\execution.py", line 58, in recursive_execute
recursive_execute(server, prompt, outputs, input_unique_id, extra_data, executed)
File "E:\code\stable-difusion\ComfyUI\execution.py", line 67, in recursive_execute
outputs[unique_id] = getattr(obj, obj.FUNCTION)(**input_data_all)
File "E:\code\stable-difusion\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 109,
in load_model
sam = sam_model_registry[model_kind](checkpoint=modelname)
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\segment_anything\build_sam.py", line 38, in build_sam_vit_b
return _build_sam(
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\segment_anything\build_sam.py", line 105, in _build_sam
state_dict = torch.load(f)
File "E:\code\stable-difusion\ComfyUI\custom_nodes\ComfyUI_tagger\modules\safe.py", line 106, in load
return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs)
File "E:\code\stable-difusion\ComfyUI\custom_nodes\ComfyUI_tagger\modules\safe.py", line 151, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 920, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: A load persistent id instruction was encountered,
but no persistent_load function was specified.
Hey, I've been trying to use the mask output from FaceDetailer followed by invert mask and it kinda works but not well.
I am trying to keep faces but change the rest.
If I don't invert the mask, only the face is changed, so I know that part is correct.
If I do invert the mask, the rest of the image is changed, but so the face is also changed to a lesser extent.
I can't find any examples of anyone doing this anywhere and I haven't figured it out yet.
I'll keep working on it but I'm posting this here in case anyone knows what I should do to make the inverted mask 100% respected.
I am using inpainting models.
Thanks for these awesome nodes,
-Aaron
I thought increase bbox dilation would help but it didn't
can it be done somehow?
Hi there, I'm trying to install ComfyUI-Impact-Pack so I can ensure it's compatible with CushyStudio https://github.com/rvion/CushyStudio
I think I have those properly setup
openmim
segment-anything
pycocotools
onnxruntime
mim install
and
mmcv==2.0.0, mmdet==3.0.0, mmengine==0.7.2
but when ComfyUI starts, it gives
### Loading: ComfyUI-Impact-Pack
Traceback (most recent call last):
File "C:\Users\user\dev\intuition\ComfyUI\nodes.py", line 1237, in load_custom_node
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 883, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "C:\Users\user\dev\intuition\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\__init__.py", line 19, in <module>
from .impact_pack import NODE_CLASS_MAPPINGS
File "C:\Users\user\dev\intuition\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\impact_pack.py", line 22, in <module>
from mmdet.apis import (inference_detector, init_detector)
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\apis\__init__.py", line 2, in <module>
from .det_inferencer import DetInferencer
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\apis\det_inferencer.py", line 21, in <module>
from mmdet.evaluation import INSTANCE_OFFSET
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\evaluation\__init__.py", line 3, in <module>
from .metrics import * # noqa: F401,F403
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\evaluation\metrics\__init__.py", line 3, in <module>
from .coco_metric import CocoMetric
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\evaluation\metrics\coco_metric.py", line 16, in <module>
from mmdet.datasets.api_wrappers import COCO, COCOeval
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\datasets\__init__.py", line 14, in <module>
from .utils import get_loading_pipeline
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\datasets\utils.py", line 5, in <module>
from mmdet.datasets.transforms import LoadAnnotations, LoadPanopticAnnotations
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\datasets\transforms\__init__.py", line 6, in <module>
from .formatting import ImageToTensor, PackDetInputs, ToTensor, Transpose
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\datasets\transforms\formatting.py", line 9, in <module>
from mmdet.structures.bbox import BaseBoxes
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\structures\bbox\__init__.py", line 2, in <module>
from .base_boxes import BaseBoxes
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\structures\bbox\base_boxes.py", line 9, in <module>
from mmdet.structures.mask.structures import BitmapMasks, PolygonMasks
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\structures\mask\__init__.py", line 3, in <module>
from .structures import (BaseInstanceMasks, BitmapMasks, PolygonMasks,
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmdet\structures\mask\structures.py", line 12, in <module>
from mmcv.ops.roi_align import roi_align
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmcv\ops\__init__.py", line 2, in <module>
from .active_rotated_filter import active_rotated_filter
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmcv\ops\active_rotated_filter.py", line 10, in <module>
ext_module = ext_loader.load_ext(
File "C:\Users\user\dev\intuition\venv\lib\site-packages\mmcv\utils\ext_loader.py", line 13, in load_ext
ext = importlib.import_module('mmcv.' + name)
File "C:\python31010\lib\importlib\__init__.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
ImportError: DLL load failed while importing _ext: The specified procedure could not be found.
Cannot import C:\Users\user\dev\intuition\ComfyUI\custom_nodes\ComfyUI-Impact-Pack module for custom nodes: DLL load failed while importing _ext: The specified procedure could not be found.
xformers version: 0.0.17+b89a493.d20230304
any idea how to fix this ?
Impact-Pack install fails due to requirement of onnxruntime which doesn't have a module for python 3.11. This results in the error:
ERROR: Could not find a version that satisfies the requirement onnxruntime (from versions: none)
ERROR: No matching distribution found for onnxruntimepython 3.11 is included in the latest nightly comfy portable release (see bottom) https://github.com/comfyanonymous/ComfyUI/releases
This is bound to be an issue because a) the latest versions of torch use python 3.11, and b) the people at onnx are slackers who haven't bothered updating in a year.
If you're like me, and upgraded comfyUI to use the latest torch and python, it definitely creates an issue. I won't go into details here on how I did it, but I have comfyui running with a conda env with python 3.11 and the updated packages.
How I solved it:
With the environment active:
conda install python=3.10.10
pip install onnxruntime
conda install python=3.11.3This downgrades python. Installs onnx. upgrades python.
result: setup continues with the install and
references:
I had a working workflow, updated to 9c13ec6, replaced the mmdetdetector node with ultralyticsdetector node and no get this error when trying to use it:
Traceback (most recent call last):
File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 144, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 67, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\detectors.py", line 83, in doit
segs = bbox_detector.detect(image, threshold, dilation, crop_factor, drop_size)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\subpack\impact\subcore.py", line 94, in detect
detected_results = inference_bbox(self.bbox_model, core.tensor2pil(image), threshold)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\subpack\impact\subcore.py", line 48, in inference_bbox
results[0].append(pred[0].names[i])
KeyError: 1
If you need the workflow, it's in this image.
I am impressed with Clipspace very nice features.
I would love to be able to use images from the clipboard to make it easier to work with drawing tools, but is that difficult to do?
Hello!
Since a few days ago we are getting the following error.
My research showed so far it has something to do with the sam loader maybe?
Error occurred when executing FaceDetailer:
The size of tensor a (0) must match the size of tensor b (256) at non-singleton dimension 1
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 800, in doit
enhanced_img, cropped_enhanced, mask = FaceDetailer.enhance_face(
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 779, in enhance_face
sam_mask = core.make_sam_mask(sam_model_opt, segs, image, sam_detection_hint, sam_dilation,
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 433, in make_sam_mask
detected_masks = sam_predict(predictor, points, plabs, dilated_bbox, threshold)
File "E:\Stable Diffusion\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 308, in sam_predict
cur_masks, scores, _ = predictor.predict(point_coords=point_coords, point_labels=point_labels, box=box)
File "E:\Stable Diffusion\ComfyUI_windows_portable\python_embeded\lib\site-packages\segment_anything\predictor.py", line 154, in predict
masks, iou_predictions, low_res_masks = self.predict_torch(
File "E:\Stable Diffusion\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "E:\Stable Diffusion\ComfyUI_windows_portable\python_embeded\lib\site-packages\segment_anything\predictor.py", line 222, in predict_torch
sparse_embeddings, dense_embeddings = self.model.prompt_encoder(
File "E:\Stable Diffusion\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "E:\Stable Diffusion\ComfyUI_windows_portable\python_embeded\lib\site-packages\segment_anything\modeling\prompt_encoder.py", line 155, in forward
point_embeddings = self._embed_points(coords, labels, pad=(boxes is None))
File "E:\Stable Diffusion\ComfyUI_windows_portable\python_embeded\lib\site-packages\segment_anything\modeling\prompt_encoder.py", line 88, in _embed_points
point_embedding[labels == -1] += self.not_a_point_embed.weight
i use FaceDetailerPipe...
Error occurred when executing FaceDetailerPipe:
'Sam' object has no attribute 'is_auto_mode'
File "C:\Product\ComfyUI\execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Product\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\Product\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Product\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 1337, in doit
enhanced_img, cropped_enhanced, mask = FaceDetailer.enhance_face(
File "C:\Product\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 790, in enhance_face
sam_mask = core.make_sam_mask(sam_model_opt, segs, image, sam_detection_hint, sam_dilation,
File "C:\Product\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 328, in make_sam_mask
if sam_model.is_auto_mode:
File "C:\Product\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
Can't use some UI layouts as it uses the Imapct-Pack nodes. Which fails to load. Can you help, please?
I'm using this standalone ComfyUI:
(https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_cu118_or_cpu.7z)
9.7 seconds (IMPORT FAILED): A:\AI_Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
10.8 seconds (IMPORT FAILED): A:\AI_Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
Cannot import A:\AI_Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack module for custom nodes: Command '['A:\AI_Files\ComfyUI_windows_portable\python_embeded\python.exe', '-s', '-m', 'mim', 'install', 'mmcv==2.0.0']' returned non-zero exit status 1.
Cannot import D:\ComfyUI\ComfyUI\custom_nodes\comfyui-impact-pack.py module for custom nodes: type object 'PromptServer' has no attribute 'instance'
not sure how to fix this
Could anyone explain what exactly the guide_size property does? I know the general description from the readme:
guide_size: This feature attempt detail recovery only when the size of the detected mask is smaller than this value. If the size is larger, this feature increase the resolution and attempt detail recovery.
... but that, figuring if the area is too big to be scaled up is not all it does, and that's not exactly how it does it, right? From seeing it at work, I sometimes get logs like crop region (622, 657) x 1.2340581845389367 -> (704, 768), which is bigger than the 256 default value I had set, so if I were to take the readme literally it shouldn't be upscaled at all. All of it makes it seem like it's also being used to determine how large the new render size is in very roundabout way (not quite multiples of the value, since 704 isn't a multiple), as well as the scale ratio, which is a lot of things for one single value to control, and I just can't seem to get it to behave how I'd like.
Could it be possible to get a precise description of everything this property is doing, how is it doing, and could we perhaps have a conversation about whether all these things should not be separated into at least two, maybe even three separate properties to allow more control, and prevent some detail that really needed to be re-rendered to be skipped because it just landed at the wrong upscale ratio?
Thanks!
Hi,
Could you please update your amazing nodes to be compatible with the latest ComfyUI_TiledKSampler?
BlenderNeko has introduced a new parameter tiling_strategy and possibly removed the concurrent_tiles.
Thank you and keep up the good work!
Missing custom nodes does show anything.
Tried Impact Pack. Nothing in there.
Can you help
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.