search

comfyanonymous / ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
https://www.comfy.org/
GNU General Public License v3.0
58.9k stars 6.25k forks source link

I've been using comfyui just fine all day. I close out and come back to it an hour later and cant get back in raise AssertionError #4608

Open rachelcenter opened 3 months ago

rachelcenter commented 3 months ago

Expected Behavior

When I click "run_nvidia_gpu" file on a windows computer (Comfyui Windows portable) I expect terminal to launch Comfyui for me in Firefox

Actual Behavior

Terminal gives me this error and says "press any key to continue" and then terminal closes and comfyui doesnt open. Full terminal code pasted under debug log below.

Steps to Reproduce

Double click "run_nvidia_gpu" file within Comfyui Windows Portable. then go to manager and install Lora-Training-In-Comfy. I'm not the only person to have this issue: https://github.com/comfyanonymous/ComfyUI/discussions/3802

Debug Logs

D:\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-08-25 21:59:24.244525
** Platform: Windows
** Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr  2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe
** ComfyUI Path: D:\ComfyUI_windows_portable\ComfyUI
** Log path: D:\ComfyUI_windows_portable\comfyui.log

Prestartup times for custom nodes:
   0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
   0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use
   2.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Traceback (most recent call last):
  File "D:\ComfyUI_windows_portable\ComfyUI\main.py", line 86, in <module>
    import execution
  File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 13, in <module>
    import nodes
  File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 21, in <module>
    import comfy.diffusers_load
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\diffusers_load.py", line 3, in <module>
    import comfy.sd
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 5, in <module>
    from comfy import model_management
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 142, in <module>
    total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
                                  ^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 111, in get_torch_device
    return torch.device(torch.cuda.current_device())
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 878, in current_device
    _lazy_init()
  File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 305, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

D:\ComfyUI_windows_portable>pause
Press any key to continue . . .

Other

No response

rakib91221 commented 3 months ago

Expected Behavior

When I click "run_nvidia_gpu" file on a windows computer (Comfyui Windows portable) I expect terminal to launch Comfyui for me in Firefox

Actual Behavior

Terminal gives me this error and says "press any key to continue" and then terminal closes and comfyui doesnt open. Full terminal code pasted under debug log below.

Steps to Reproduce

Double click "run_nvidia_gpu" file within Comfyui Windows Portable. then go to manager and install Lora-Training-In-Comfy. I'm not the only person to have this issue: #3802

Debug Logs

D:\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-08-25 21:59:24.244525
** Platform: Windows
** Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr  2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe
** ComfyUI Path: D:\ComfyUI_windows_portable\ComfyUI
** Log path: D:\ComfyUI_windows_portable\comfyui.log

Prestartup times for custom nodes:
   0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
   0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use
   2.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Traceback (most recent call last):
  File "D:\ComfyUI_windows_portable\ComfyUI\main.py", line 86, in <module>
    import execution
  File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 13, in <module>
    import nodes
  File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 21, in <module>
    import comfy.diffusers_load
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\diffusers_load.py", line 3, in <module>
    import comfy.sd
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 5, in <module>
    from comfy import model_management
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 142, in <module>
    total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
                                  ^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 111, in get_torch_device
    return torch.device(torch.cuda.current_device())
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 878, in current_device
    _lazy_init()
  File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 305, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

D:\ComfyUI_windows_portable>pause
Press any key to continue . . .

Other

No response

same problem

rachelcenter commented 3 months ago

Expected Behavior

When I click "run_nvidia_gpu" file on a windows computer (Comfyui Windows portable) I expect terminal to launch Comfyui for me in Firefox

Actual Behavior

Terminal gives me this error and says "press any key to continue" and then terminal closes and comfyui doesnt open. Full terminal code pasted under debug log below.

Steps to Reproduce

Double click "run_nvidia_gpu" file within Comfyui Windows Portable. then go to manager and install Lora-Training-In-Comfy. I'm not the only person to have this issue: #3802

Debug Logs

D:\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-08-25 21:59:24.244525
** Platform: Windows
** Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr  2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe
** ComfyUI Path: D:\ComfyUI_windows_portable\ComfyUI
** Log path: D:\ComfyUI_windows_portable\comfyui.log

Prestartup times for custom nodes:
   0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
   0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use
   2.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Traceback (most recent call last):
  File "D:\ComfyUI_windows_portable\ComfyUI\main.py", line 86, in <module>
    import execution
  File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 13, in <module>
    import nodes
  File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 21, in <module>
    import comfy.diffusers_load
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\diffusers_load.py", line 3, in <module>
    import comfy.sd
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 5, in <module>
    from comfy import model_management
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 142, in <module>
    total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
                                  ^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 111, in get_torch_device
    return torch.device(torch.cuda.current_device())
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 878, in current_device
    _lazy_init()
  File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 305, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

D:\ComfyUI_windows_portable>pause
Press any key to continue . . .

Other

No response

same problem

https://github.com/comfyanonymous/ComfyUI/issues/2427

rachelcenter commented 3 months ago

https://github.com/comfyanonymous/ComfyUI/issues/2427

havent solved it yet

ltdrdata commented 3 months ago

2427

havent solved it yet

You need to reinstall torch.

koskoakos commented 2 months ago

Issue is likely with custom nodes reinstalling pytorch+cpu instead of CUDA because of poorly written requirements or dependencies. Reinstall torch with CUDA https://pytorch.org/get-started/locally/