해당 comfyui 가상 환경에 설치하여야 함
cd C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI
PS C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI> ls
하여 가상환경 디렉토리 venv를 확인
PS C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI> ls
d----- 2025-05-06 오후 5:45 utils
d----- 2025-05-06 오후 5:40 venv
PS C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI> .\venv\Scripts\activate
(venv) PS C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI> pip list
torch 2.7.0
(venv) PS C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI> pip install --force-reinstall torch --index-url https://download.pytorch.org/whl/cu118
Successfully installed MarkupSafe-2.1.5 filelock-3.13.1 fsspec-2024.6.1 jinja2-3.1.4 mpmath-1.3.0 networkx-3.3 sympy-1.13.3 torch-2.7.0+cu118 typing-extensions-4.12.2
(venv) PS C:\Users\jglee\AppData\Roaming\StabilityMatrix\Packages\ComfyUI> pip list
torch 2.7.0+cu118
comfyui를 실행한다.
Total VRAM 6140 MB, total RAM 16024 MB
pytorch version: 2.7.0+cu118
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4050 Laptop GPU : cudaMallocAsync
Using pytorch attention
Python version: 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
ComfyUI version: 0.3.31
Requested to load BaseModel
loaded completely 3377.8306777954103 1639.406135559082 True
100%|██████████| 20/20 [00:07<00:00, 2.61it/s]
Requested to load AutoencoderKL
loaded partially 128.0 127.99993133544922 0
Prompt executed in 13.52 seconds
13.52초
