Thank you so much! this worked for me for my Windows 11, 64x 32 system. I have a 16 gb ram, intel cpu. AMD. I just followed first half of video without the CUDA part cause i don't have it. Face swap runs well!
This really was a great video and well explained, thank you for great work, this really solved my problem, and I was struggling for long, I bumped on your video after countless attempts at getting the reactor worked after a fresh OS install, But this worked for me finally. Awesome Video.
I have been trying for days with no success and then saw a post on the official channel for Reactor that someone else said to downgrade the onnxruntime. So after following your instructions here I Then downgraded CUDA to 11.8 and the added all the extras like you di in bin, lib and include to the 11.8 CUDA folder. resorting back to Cuda 11.8 then I removed the onnxruntime and then reinstanlled it downgradin it to 1.17.1 and Voila Success. python_embeded\python.exe -m pip uninstall -y onnxruntime onnxruntime-gpu python_embeded\python.exe -m pip install onnxruntime==1.17.1 FINALLLLLLYYYYYYYYYY!!!!!!!!
Hi friend, how you downgrade CUDA to 11.8? I still having the same problem, the same ERROR pops up: "CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page......... etc etc etc"
finally after 3 days of darkness with your help it can be solved. python_embeded\python.exe -m pip uninstall -y onnxruntime onnxruntime-gpu python_embeded\python.exe -m pip install onnxruntime==1.17.1 using this method and it work again like before thanks bro
Hi, thanks for the tutorial. Only one problem I have with REAKTOR, the fact that it ruins the color of the hair (it loses color due to contouring over the face) when applying the new face. Is there any solution to this situation? Thanks in advance.
This issue arises because you have installed a PyTorch version that is not compatible with the CUDA version (Compute Platform). You can identify your CUDA version using the nvidia-smi command. For example, if your CUDA version is 12, but you have installed a PyTorch version that is compatible with CUDA 12.1. To resolve this, uninstall PyTorch and reinstall it to match your CUDA version (computer platform). If your CUDA version is 12, and you cannot find a PyTorch version compatible with that, install a PyTorch version compatible with a CUDA version less than 12, such as 11.8. No issues will arise in this case. Note that you cannot install a PyTorch version with a higher CUDA version than your current platform. If you have installed the CPU version of PyTorch, this problem should not occur. Source: stackoverflow.com/questions/75103127/getting-notimplementederror-could-not-run-torchvisionnms-with-arguments-fr cek pytorch version according to your CUDA pytorch.org/
which python_embeded that you do that trigger this? if it is trigger while installing insight face, make sure you use the correct python version. Try download the right version and install it again.
Hello, I have workflows that are shared on sites and are open to everyone. I download and install the missing models, lora, etc. in those workflows, but I still get errors. I want these to be fixed and prepared in a way that I can run. If I pay you, can you do these for me?
Sorry, could you specify the error? Some Custom Node require you to install other thing. For example, reactor require to install Cuda. Some require a certain python version. I think you should check each custom node that it has, and see it github page, to make sure you don't need any new version. Also if you get the workflow from site, check the review and user reputation. Some time people upload workflow that simply don't work. Also by checking the review and comment you might find a clue about what to do with your error.
hi, i keep getting (IMPORT FAILED) ReActor Node for ComfyUI. there is a "fix" button there i select it but nothing chages. stuck in this error badly. i also install it manually but nothing changed. i don't know what is the problem.
are you just updated? it seems this problem arise suddenly after the new update. Let's wait and see for now. It still working for me, but people trying to do new installation seems to have this problem after they updated ther comfy ui.
try git the older version, match the date around when i upload the video. Then install it again. After that update the comfy again. Check the list here: github.com/comfyanonymous/ComfyUI/commits/master/
I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following: (ComfyUI Portable) From the root folder check the version of Python: run CMD and type python_embeded\python.exe -V Download prebuilt Insightface package for Python 3.10 or for Python 3.11 (if in the previous step you see 3.11) or for Python 3.12 (if in the previous step you see 3.12) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable From the root folder run: (SD WebUI) CMD and .\venv\Scripts\activate (ComfyUI Portable) run CMD Then update your PIP: (SD WebUI) python -m pip install -U pip (ComfyUI Portable) python_embeded\python.exe -m pip install -U pip Then install Insightface: (SD WebUI) pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12) (ComfyUI Portable) python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or python_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or python_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12) Enjoy! from the source: github.com/Gourieff/comfyui-reactor-node
Unfortunately this is not working for me. I have tried other similar guides but it won't load ReActor. Even the "try fix" operation suggested by ComfyUI does not work. I don't even see any error message when installing the requirements. I am on windows 10. What am i missing?
@@CaoCao2025 mhm, i have no idea. I thought all the requirements go installed automatically (other than everything else the guide mention). If i run nvidia-smi the command window shuts down immediately and i can't tell. Any pointers?
you need to install CUDA Toolkit manually too, it's also a different from cuddn. I can't guide you with installing CUDA because i am afraid to mess up my setting. You can follow many other tutorial of installing Cuda Toolkit.
@@CaoCao2025 any particular tutorial you’d recommend? Also, how destructive are the “wrong” settings? I work with 3d and the last thing I want is to mess up my pc during a project! ;)
First of all thank yo very much for your videos, they are straight to the point. Great job my friend. Still having the same problem, the same ERROR pops up: "CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page......... etc etc etc" I notice something different on my Installation process, I followed your instruction BUT at 1:15 (when Install.bat is executed), when you said "As you can see, we finish installing Onyx 1.16........" in my case, it does not install anything, it just shows the windows prompt like this: Installing. . . CUDA 12.1 OK Done Press any key to continue . . . The user @HiProfileAI said something about downgrade the CUDA version to 11.8, gonna try that as well.
It says to me: unexpected EOF, expected 101681834 more bytes. The file might be corrupted. I try a lot of time, with differents way... Always a error...
V. "INVALID_PROTOBUF : Load model from \models\insightface\inswapper_128.onnx failed:Protobuf parsing failed" OR "AttributeError: 'NoneType' object has no attribute 'get'" OR "AttributeError: 'FaceSwapScript' object has no attribute 'save_original'" This error may occur if there's smth wrong with the model file inswapper_128.onnx Try to download it manually from huggingface.co/datasets/Gourieff/ReActor/resolve/main/models/inswapper_128.onnx and put it to the \models\insightface replacing existing one
are you just updated? it seems this problem arise suddenly after the new update. Let's wait and see for now. It still working for me, but people trying to do new installation seems to have this problem after they updated ther comfy ui.
try git the older version, match the date around when i upload the video. Then install it again. After that update the comfy again. Check the list here: github.com/comfyanonymous/ComfyUI/commits/master/
Unfortunately I ran into several errors. Some of which I was able to resolve and others I could not. I really wish there was a more streamlined process for this stuff.
@@CaoCao2025 I am having this issue also. I tried uninstalling onnx and re-installing but when I clone reactor and click install I get this same result
@@steveh3206 is the reactor node already show up? it might be possible, that you already installed it. If the reactor already show up, try using it and tell me if it generate error.
try git the older version of comfy, match the date around when i upload the video. Then install it again. After that update the comfy again. Check the list here: github.com/comfyanonymous/ComfyUI/commits/master/
1:13 i get this error mesh_core_cython.cpp insightface/thirdparty/face3d/mesh/cython/mesh_core_cython.cpp(36): fatal error C1083: Cannot open include file: 'Python.h': No such file or directory error: command 'C:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.41.34120\\bin\\HostX86\\x64\\cl.exe' failed with exit code 2 [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for insightface Failed to build insightface ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (insightface)
I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following: (ComfyUI Portable) From the root folder check the version of Python: run CMD and type python_embeded\python.exe -V Download prebuilt Insightface package for Python 3.10 or for Python 3.11 (if in the previous step you see 3.11) or for Python 3.12 (if in the previous step you see 3.12) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable From the root folder run: (SD WebUI) CMD and .\venv\Scripts\activate (ComfyUI Portable) run CMD Then update your PIP: (SD WebUI) python -m pip install -U pip (ComfyUI Portable) python_embeded\python.exe -m pip install -U pip Then install Insightface: (SD WebUI) pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12) (ComfyUI Portable) python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or python_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or python_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12) Enjoy! from the source: github.com/Gourieff/comfyui-reactor-node
i am still getting this Installing... CUDA 12.1 Status: The 'insightface==0.7.3' distribution was not found and is required by the application Collecting insightface==0.7.3 Using cached insightface-0.7.3.tar.gz (439 kB) Installing build dependencies ... done Getting requirements to build wheel ... error error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [18 lines of output] Traceback (most recent call last): File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in main() File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs']) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 118, in get_requires_for_build_wheel return hook(config_settings) ^^^^^^^^^^^^^^^^^^^^^ File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\build_meta.py", line 327, in get_requires_for_build_wheel return self._get_build_requires(config_settings, requirements=[]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\build_meta.py", line 297, in _get_build_requires self.run_setup() File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\build_meta.py", line 313, in run_setup exec(code, locals()) File "", line 11, in ModuleNotFoundError: No module named 'Cython' [end of output] note: This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a problem with pip. Ok Done Press any key to continue . . .
- are you already installing visual studio vs c++ build tool - if you don;t wnat to, follow this step: I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following: (ComfyUI Portable) From the root folder check the version of Python: run CMD and type python_embeded\python.exe -V Download prebuilt Insightface package for Python 3.10 (github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp310-cp310-win_amd64.whl) or for Python 3.11 (github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp311-cp311-win_amd64.whl) or for Python 3.12 (github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp312-cp312-win_amd64.whl) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable From the root folder run: (SD WebUI) CMD and .\venv\Scripts\activate (ComfyUI Portable) run CMD Then update your PIP: (SD WebUI) python -m pip install -U pip (ComfyUI Portable) python_embeded\python.exe -m pip install -U pip Then install Insightface: (SD WebUI) pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12) (ComfyUI Portable) python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or python_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or python_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12) Enjoy!
After searching for days for a working solution to installing reactor, I finally found it with you. Many thanks.
thanks, glad i could help
Thank you very much for explaining the installation, I didn't understand where the errors were coming from. Have a nice day
Glad it helped
Thank you so much! this worked for me for my Windows 11, 64x 32 system. I have a 16 gb ram, intel cpu. AMD. I just followed first half of video without the CUDA part cause i don't have it. Face swap runs well!
thanks for your information
This really was a great video and well explained, thank you for great work, this really solved my problem, and I was struggling for long, I bumped on your video after countless attempts at getting the reactor worked after a fresh OS install, But this worked for me finally. Awesome Video.
Glad it helped!
Wow , thank you very much , you're the best !
You're welcome!
대단히 감사합니다
최고의 강의입니다.
많은 시간을 허비했는데 당신의 영상으로 해결했습니다....
도움이 되어서 기쁘다
Thank you. You saved my day. Liked and Subscribed.
your welcome
Thanks, man! You hepled me a lot👍
Glad I could help!
Thanks, you solved a big issue
glad i could help
FINALLY. THANK YOU SO MUCH.
your welcome
I have been trying for days with no success and then saw a post on the official channel for Reactor that someone else said to downgrade the onnxruntime.
So after following your instructions here I Then downgraded CUDA to 11.8 and the added all the extras like you di in bin, lib and include to the 11.8 CUDA folder. resorting back to Cuda 11.8 then I removed the onnxruntime and then reinstanlled it downgradin it to 1.17.1 and Voila Success.
python_embeded\python.exe -m pip uninstall -y onnxruntime onnxruntime-gpu
python_embeded\python.exe -m pip install onnxruntime==1.17.1
FINALLLLLLYYYYYYYYYY!!!!!!!!
What was't working for you? It installs everything without errors for me, it just won't load in ComfyUI.
Congratulations
Hi friend, how you downgrade CUDA to 11.8?
I still having the same problem, the same ERROR pops up:
"CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page......... etc etc etc"
finally after 3 days of darkness with your help it can be solved.
python_embeded\python.exe -m pip uninstall -y onnxruntime onnxruntime-gpu
python_embeded\python.exe -m pip install onnxruntime==1.17.1
using this method and it work again like before
thanks bro
how do you force to uninstall onx?
Thank you for sharing 👍🏾🤩
Thank you. Thanks to you, I solved the problem that wasn't solved. Thank you for the good video. T_T b
Glad i could help
Great my friend. good share
Cảm ơn bạn đã chia sẻ
L2 👍
Amazing sharing 💯
have a nice day 🙏⛅🌞
Hi, thanks for the tutorial. Only one problem I have with REAKTOR, the fact that it ruins the color of the hair (it loses color due to contouring over the face) when applying the new face. Is there any solution to this situation? Thanks in advance.
1. you could repair it using inpainting
2. try using roop instead of reactor
You saved me from wasting thousands of times trying to solve this issue .. I was depressed and disappointed .. thanks to you its installed ♥
congrat
NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA
This issue arises because you have installed a PyTorch version that is not compatible with the CUDA version (Compute Platform). You can identify your CUDA version using the nvidia-smi command.
For example, if your CUDA version is 12, but you have installed a PyTorch version that is compatible with CUDA 12.1. To resolve this, uninstall PyTorch and reinstall it to match your CUDA version (computer platform).
If your CUDA version is 12, and you cannot find a PyTorch version compatible with that, install a PyTorch version compatible with a CUDA version less than 12, such as 11.8. No issues will arise in this case.
Note that you cannot install a PyTorch version with a higher CUDA version than your current platform.
If you have installed the CPU version of PyTorch, this problem should not occur.
Source:
stackoverflow.com/questions/75103127/getting-notimplementederror-could-not-run-torchvisionnms-with-arguments-fr
cek pytorch version according to your CUDA
pytorch.org/
Bro I did that python_embeded and now it's saying access is denied ? What should I do I can't open comfy now
which python_embeded that you do that trigger this? if it is trigger while installing insight face, make sure you use the correct python version. Try download the right version and install it again.
Hello, I have workflows that are shared on sites and are open to everyone. I download and install the missing models, lora, etc. in those workflows, but I still get errors. I want these to be fixed and prepared in a way that I can run. If I pay you, can you do these for me?
Sorry, could you specify the error? Some Custom Node require you to install other thing. For example, reactor require to install Cuda. Some require a certain python version. I think you should check each custom node that it has, and see it github page, to make sure you don't need any new version.
Also if you get the workflow from site, check the review and user reputation. Some time people upload workflow that simply don't work. Also by checking the review and comment you might find a clue about what to do with your error.
Thank you...
hi, i keep getting (IMPORT FAILED) ReActor Node for ComfyUI.
there is a "fix" button there i select it but nothing chages. stuck in this error badly.
i also install it manually but nothing changed. i don't know what is the problem.
what comfy version that you have?
@@CaoCao2025 it is ComfyUI v0.2.2 Release
are you just updated? it seems this problem arise suddenly after the new update. Let's wait and see for now. It still working for me, but people trying to do new installation seems to have this problem after they updated ther comfy ui.
try git the older version, match the date around when i upload the video. Then install it again. After that update the comfy again. Check the list here: github.com/comfyanonymous/ComfyUI/commits/master/
😂 the voice, lol
I feel like I’m listening to a Hogwarts Teacher who is showing us the latest mischievous spell magic. Not sure I like it tho.
lol
Getting Error (Getting requirements to build wheel did not run successfully.) When trying to install comfyui-reactor-node.🤔
I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following:
(ComfyUI Portable) From the root folder check the version of Python:
run CMD and type python_embeded\python.exe -V
Download prebuilt Insightface package for Python 3.10 or for Python 3.11 (if in the previous step you see 3.11) or for Python 3.12 (if in the previous step you see 3.12) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable
From the root folder run:
(SD WebUI) CMD and .\venv\Scripts\activate
(ComfyUI Portable) run CMD
Then update your PIP:
(SD WebUI) python -m pip install -U pip
(ComfyUI Portable) python_embeded\python.exe -m pip install -U pip
Then install Insightface:
(SD WebUI) pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12)
(ComfyUI Portable) python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or python_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or python_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12)
Enjoy!
from the source:
github.com/Gourieff/comfyui-reactor-node
Unfortunately this is not working for me. I have tried other similar guides but it won't load ReActor. Even the "try fix" operation suggested by ComfyUI does not work. I don't even see any error message when installing the requirements. I am on windows 10. What am i missing?
what CUDA version that you have?
@@CaoCao2025 mhm, i have no idea. I thought all the requirements go installed automatically (other than everything else the guide mention). If i run nvidia-smi the command window shuts down immediately and i can't tell. Any pointers?
@@CaoCao2025 cudnn_9.3.0
you need to install CUDA Toolkit manually too, it's also a different from cuddn. I can't guide you with installing CUDA because i am afraid to mess up my setting. You can follow many other tutorial of installing Cuda Toolkit.
@@CaoCao2025 any particular tutorial you’d recommend? Also, how destructive are the “wrong” settings? I work with 3d and the last thing I want is to mess up my pc during a project! ;)
First of all thank yo very much for your videos, they are straight to the point. Great job my friend.
Still having the same problem, the same ERROR pops up:
"CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page......... etc etc etc"
I notice something different on my Installation process, I followed your instruction BUT at 1:15 (when Install.bat is executed), when you said "As you can see, we finish installing Onyx 1.16........" in my case, it does not install anything, it just shows the windows prompt like this:
Installing. . .
CUDA 12.1
OK
Done
Press any key to continue . . .
The user @HiProfileAI said something about downgrade the CUDA version to 11.8, gonna try that as well.
you might try uninstall the onnyx and install it again, follow the command line on video description
@@CaoCao2025 You were right my friend, I skipped that part of your tutorial. Now it works, thank you very much.
your welcome, glad i could help
It says to me: unexpected EOF, expected 101681834 more bytes. The file might be corrupted. I try a lot of time, with differents way... Always a error...
in what part of installation the error showing up?
Error occurred when executing ReActorFaceSwapOpt:
'NoneType' object has no attribute 'get'
V. "INVALID_PROTOBUF : Load model from \models\insightface\inswapper_128.onnx failed:Protobuf parsing failed" OR "AttributeError: 'NoneType' object has no attribute 'get'" OR "AttributeError: 'FaceSwapScript' object has no attribute 'save_original'"
This error may occur if there's smth wrong with the model file inswapper_128.onnx
Try to download it manually from
huggingface.co/datasets/Gourieff/ReActor/resolve/main/models/inswapper_128.onnx
and put it to the \models\insightface replacing existing one
Looks Pretty
followed all the steps, cant get it to work. In the manager it says import failed, try fix doenst help
what comfy version that you have?
@@CaoCao2025 0.2.2
are you just updated? it seems this problem arise suddenly after the new update. Let's wait and see for now. It still working for me, but people trying to do new installation seems to have this problem after they updated ther comfy ui.
@@CaoCao2025 just installed it. Yes i think we might need to wait for a bugfix.
try git the older version, match the date around when i upload the video. Then install it again. After that update the comfy again. Check the list here: github.com/comfyanonymous/ComfyUI/commits/master/
Unfortunately I ran into several errors. Some of which I was able to resolve and others I could not. I really wish there was a more streamlined process for this stuff.
Yes, i also struggle when i install this.
when i press install.bat,
Installing...
CUDA 12.4
Ok
Done
Press any key to continue . . .
and nothing else like the video long install, please help
do you already uninstall onnyx and install it again?
@@CaoCao2025 I am having this issue also. I tried uninstalling onnx and re-installing but when I clone reactor and click install I get this same result
@@steveh3206 is the reactor node already show up? it might be possible, that you already installed it. If the reactor already show up, try using it and tell me if it generate error.
@@CaoCao2025 No the nodes are showing as install failed
@@steveh3206 do you already set your CUDA location in PATH ?
good work1 :)
could you do this with multiple images as source? to get a more accurate face?
im guessing use a batch instead of load image?
i'll try and come back
i think you could use a face model for reactor
batch will not work
@@CaoCao2025 okay ill try that thanks!
not working still asking "try fix"
try git the older version of comfy, match the date around when i upload the video. Then install it again. After that update the comfy again. Check the list here: github.com/comfyanonymous/ComfyUI/commits/master/
can you put your English script through an LLM for corrections before doing the voiceover... it was really hard to follow.
good suggestion, sorry for the bad english, english is not my first language
like the video
1:13 i get this error mesh_core_cython.cpp
insightface/thirdparty/face3d/mesh/cython/mesh_core_cython.cpp(36): fatal error C1083: Cannot open include file: 'Python.h': No such file or directory
error: command 'C:\\Program Files\\Microsoft Visual Studio\\2022\\Community\\VC\\Tools\\MSVC\\14.41.34120\\bin\\HostX86\\x64\\cl.exe' failed with exit code 2
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for insightface
Failed to build insightface
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (insightface)
I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following:
(ComfyUI Portable) From the root folder check the version of Python:
run CMD and type python_embeded\python.exe -V
Download prebuilt Insightface package for Python 3.10 or for Python 3.11 (if in the previous step you see 3.11) or for Python 3.12 (if in the previous step you see 3.12) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable
From the root folder run:
(SD WebUI) CMD and .\venv\Scripts\activate
(ComfyUI Portable) run CMD
Then update your PIP:
(SD WebUI) python -m pip install -U pip
(ComfyUI Portable) python_embeded\python.exe -m pip install -U pip
Then install Insightface:
(SD WebUI) pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12)
(ComfyUI Portable) python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or python_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or python_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12)
Enjoy!
from the source:
github.com/Gourieff/comfyui-reactor-node
How to ReActor run with GPU?
I use "run_nvidia_gpu.bat" but CPU always full load 100%, and the gpu seems to be idle.
make sure you install CUDA and Cuddn already set up the environment variable for them
@@CaoCao2025 I removed onnxruntime package, keep onnxruntime-gpu, and the GPU worked
glad it work for you, thanks for sharing
i am still getting this
Installing...
CUDA 12.1
Status: The 'insightface==0.7.3' distribution was not found and is required by the application
Collecting insightface==0.7.3
Using cached insightface-0.7.3.tar.gz (439 kB)
Installing build dependencies ... done
Getting requirements to build wheel ... error
error: subprocess-exited-with-error
× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> [18 lines of output]
Traceback (most recent call last):
File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in
main()
File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in main
json_out['return_val'] = hook(**hook_input['kwargs'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 118, in get_requires_for_build_wheel
return hook(config_settings)
^^^^^^^^^^^^^^^^^^^^^
File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\build_meta.py", line 327, in get_requires_for_build_wheel
return self._get_build_requires(config_settings, requirements=[])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\build_meta.py", line 297, in _get_build_requires
self.run_setup()
File "H:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\setuptools\build_meta.py", line 313, in run_setup
exec(code, locals())
File "", line 11, in
ModuleNotFoundError: No module named 'Cython'
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error
× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip.
Ok
Done
Press any key to continue . . .
- are you already installing visual studio vs c++ build tool
- if you don;t wnat to, follow this step:
I. (For Windows users) If you still cannot build Insightface for some reasons or just don't want to install Visual Studio or VS C++ Build Tools - do the following:
(ComfyUI Portable) From the root folder check the version of Python:
run CMD and type python_embeded\python.exe -V
Download prebuilt Insightface package for Python 3.10 (github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp310-cp310-win_amd64.whl) or for Python 3.11 (github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp311-cp311-win_amd64.whl) or for Python 3.12 (github.com/Gourieff/Assets/raw/main/Insightface/insightface-0.7.3-cp312-cp312-win_amd64.whl) and put into the stable-diffusion-webui (A1111 or SD.Next) root folder (where you have "webui-user.bat" file) or into ComfyUI root folder if you use ComfyUI Portable
From the root folder run:
(SD WebUI) CMD and .\venv\Scripts\activate
(ComfyUI Portable) run CMD
Then update your PIP:
(SD WebUI) python -m pip install -U pip
(ComfyUI Portable) python_embeded\python.exe -m pip install -U pip
Then install Insightface:
(SD WebUI) pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12)
(ComfyUI Portable) python_embeded\python.exe -m pip install insightface-0.7.3-cp310-cp310-win_amd64.whl (for 3.10) or python_embeded\python.exe -m pip install insightface-0.7.3-cp311-cp311-win_amd64.whl (for 3.11) or python_embeded\python.exe -m pip install insightface-0.7.3-cp312-cp312-win_amd64.whl (for 3.12)
Enjoy!