ComfyUI 설치

출처

• [Python] 파이썬 가상환경(venv) 종류 및 사용법 정리 : 호무비

ComfyUI 다운로드

C:\stable-diffusion>git clone https://github.com/comfyanonymous/ComfyUI.git

Python 가상환경만들기

가상환경 생성

C:\stable-diffusion>cd ComfyUI
C:\stable-diffusion\ComfyUI>python -m venv venvIdmVton

가상환경 활성화

C:\stable-diffusion\ComfyUI>venvIdmVton\Scripts\activate
(venvIdmVton) C:\stable-diffusion\ComfyUI>

pip 업그레이드

(venvIdmVton) C:\stable-diffusion\ComfyUI>python.exe -m pip install --upgrade pip

PyTouch 설치

(venvIdmVton) C:\stable-diffusion\ComfyUI>pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121

ComfyUI 관련 패키지 설치

(venvIdmVton) C:\stable-diffusion\ComfyUI>pip install -r requirements.txt

ComfyUI 실행

(venvIdmVton) C:\stable-diffusion\ComfyUI>python main.py
Total VRAM 8188 MB, total RAM 16092 MB
pytorch version: 2.4.0+cu121
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4060 Laptop GPU : cudaMallocAsync
Using pytorch cross attention
[Prompt Server] web root: C:\stable-diffusion\ComfyUI\web
C:\stable-diffusion\ComfyUI\venvIdmVton\Lib\site-packages\kornia\feature\lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  @torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)

Import times for custom nodes:
   0.0 seconds: C:\stable-diffusion\ComfyUI\custom_nodes\websocket_image_save.py

Starting server

To see the GUI go to: http://127.0.0.1:8188

ComfyUI Manager 설치

(venvIdmVton) C:\stable-diffusion\ComfyUI>cd custom_nodes
(venvIdmVton) C:\stable-diffusion\ComfyUI\custom_nodes>git clone https://github.com/ltdrdata/ComfyUI-Manager.git

ComfyUI 재실행

(venvIdmVton) C:\stable-diffusion\ComfyUI>python main.py
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies. (GitPython)
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-07-27 23:54:20.182361
** Platform: Windows
** Python version: 3.11.0 (main, Oct 24 2022, 18:26:48) [MSC v.1933 64 bit (AMD64)]
** Python executable: C:\stable-diffusion\ComfyUI\venvIdmVton\Scripts\python.exe
** ComfyUI Path: C:\stable-diffusion\ComfyUI
** Log path: C:\stable-diffusion\ComfyUI\comfyui.log

Prestartup times for custom nodes:
  18.1 seconds: C:\stable-diffusion\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 8188 MB, total RAM 16092 MB
pytorch version: 2.4.0+cu121
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4060 Laptop GPU : cudaMallocAsync
Using pytorch cross attention
[Prompt Server] web root: C:\stable-diffusion\ComfyUI\web
C:\stable-diffusion\ComfyUI\venvIdmVton\Lib\site-packages\kornia\feature\lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  @torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
### Loading: ComfyUI-Manager (V2.48.2)
### ComfyUI Revision: 2413 [f82d09c9] | Released on '2024-07-27'

Import times for custom nodes:
   0.0 seconds: C:\stable-diffusion\ComfyUI\custom_nodes\websocket_image_save.py
   0.3 seconds: C:\stable-diffusion\ComfyUI\custom_nodes\ComfyUI-Manager

Starting server

To see the GUI go to: http://127.0.0.1:8188
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json