Open MiladZarour opened 1 month ago
Write the code, open a pull request.
how to start the main.py script ? I am getting this error when I run it ?
File "D:\Fix_Comfyui\ComfyUI\comfy\model_management.py", line 89, in get_torch_device
return torch.device(torch.cuda.current_device())
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Fix_Comfyui\ComfyUI\venv\Lib\site-packages\torch\cuda\__init__.py", line 778, in current_device
_lazy_init()
File "D:\Fix_Comfyui\ComfyUI\venv\Lib\site-packages\torch\cuda\__init__.py", line 284, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Process finished with exit code 1 I want to test my code if there is any another way ?
oh CUDA wasn't installed I think now should works..
to run the main.py I think I have to run same as the run_nvidia_gpu.bat ?
python.exe -s ComfyUI\main.py --windows-standalone-build
I installed CUDA , and installed all the requirement.txt
and running the main.py :
D:\\Fix_Comfyui\\ComfyUI\\venv\\Scripts\\python.exe -s D:\\Fix_Comfyui\\ComfyUI\\main.py --windows-standalone-build
getting this error :
Traceback (most recent call last):
File "D:\Fix_Comfyui\ComfyUI\main.py", line 79, in <module>
import execution
File "D:\Fix_Comfyui\ComfyUI\execution.py", line 11, in <module>
import nodes
File "D:\Fix_Comfyui\ComfyUI\nodes.py", line 21, in <module>
import comfy.diffusers_load
File "D:\Fix_Comfyui\ComfyUI\comfy\diffusers_load.py", line 3, in <module>
import comfy.sd
File "D:\Fix_Comfyui\ComfyUI\comfy\sd.py", line 5, in <module>
from comfy import model_management
File "D:\Fix_Comfyui\ComfyUI\comfy\model_management.py", line 120, in <module>
total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
^^^^^^^^^^^^^^^^^^
File "D:\Fix_Comfyui\ComfyUI\comfy\model_management.py", line 89, in get_torch_device
return torch.device(torch.cuda.current_device())
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Fix_Comfyui\ComfyUI\venv\Lib\site-packages\torch\cuda\__init__.py", line 778, in current_device
_lazy_init()
File "D:\Fix_Comfyui\ComfyUI\venv\Lib\site-packages\torch\cuda\__init__.py", line 284, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
and running :
Milad@Milad MINGW64 /d/Fix_Comfyui/ComfyUI (master)
$ D:\\Fix_Comfyui\\ComfyUI\\venv\\Scripts\\python.exe D:\\Fix_Comfyui\\ComfyUI\\main.py
Traceback (most recent call last):
File "D:\Fix_Comfyui\ComfyUI\main.py", line 79, in <module>
import execution
File "D:\Fix_Comfyui\ComfyUI\execution.py", line 11, in <module>
import nodes
File "D:\Fix_Comfyui\ComfyUI\nodes.py", line 21, in <module>
import comfy.diffusers_load
File "D:\Fix_Comfyui\ComfyUI\comfy\diffusers_load.py", line 3, in <module>
import comfy.sd
File "D:\Fix_Comfyui\ComfyUI\comfy\sd.py", line 5, in <module>
from comfy import model_management
File "D:\Fix_Comfyui\ComfyUI\comfy\model_management.py", line 120, in <module>
total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
^^^^^^^^^^^^^^^^^^
File "D:\Fix_Comfyui\ComfyUI\comfy\model_management.py", line 89, in get_torch_device
return torch.device(torch.cuda.current_device())
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Fix_Comfyui\ComfyUI\venv\Lib\site-packages\torch\cuda\__init__.py", line 778, in current_device
_lazy_init()
File "D:\Fix_Comfyui\ComfyUI\venv\Lib\site-packages\torch\cuda\__init__.py", line 284, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
it works now !
D:\Fix_Comfyui\ComfyUI\venv\Scripts\python.exe D:\Fix_Comfyui\ComfyUI\main.py
Total VRAM 8192 MB, total RAM 65365 MB
pytorch version: 2.3.0+cu118
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3060 Ti : cudaMallocAsync
VAE dtype: torch.bfloat16
Using pytorch cross attention
D:\Fix_Comfyui\ComfyUI\comfy\extra_samplers\uni_pc.py:19: SyntaxWarning: invalid escape sequence '\h'
"""Create a wrapper class for the forward SDE (VP type).
****** User settings have been changed to be stored on the server instead of browser storage. ******
****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ******
Import times for custom nodes:
0.0 seconds: D:\Fix_Comfyui\ComfyUI\custom_nodes\websocket_image_save.py
Starting server
To see the GUI go to: http://127.0.0.1:8188
Now I will start !
and I realised that I actually forked the wrong Comfyui 😁
I should forked https://github.com/ltdrdata/ComfyUI-Manager actually, because there where I should edit I believe.....
I get the same error. How did you fix it?
Same error here.
take a look at https://github.com/hiddenswitch/ComfyUI?tab=readme-ov-file#installing for better support for automatic model downloading
When using ComfyUI and running run_with_gpu.bat, importing a JSON file may result in missing nodes. This issue can be easily fixed by opening the manager and clicking on "Install Missing Nodes," allowing us to check and install the required nodes.
However, this functionality does not extend to missing models or IP-adapters.
To address this, I suggest implementing a feature that allows the installation of missing models and other components directly from the manager tab when importing a JSON file. This would streamline the process and ensure all necessary components are installed seamlessly.
I would like to contribute and try fixing this issue.