All Guides

ComfyUI Einrichtung (KI-Bilderzeugung)

Installieren und nutzen Sie die knotenbasierte KI-Bilderzeugungsoberflaeche von ComfyUI.

Advanced40 Min.

Setup Steps

1. System requirements: NVIDIA GPU (4GB+ VRAM), Python 3.10+, Git

2. Clone ComfyUI:

git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI

3. Create a Python virtual environment:

python3 -m venv venv
source venv/bin/activate

4. Install dependencies:

pip install -r requirements.txt

5. Install PyTorch for NVIDIA GPU:

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

6. Download a model (to models/checkpoints/):

wget -P models/checkpoints/ https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors

7. Start ComfyUI:

python main.py

8. Open http://127.0.0.1:8188 in your browser

9. For remote access:

python main.py --listen 0.0.0.0 --port 8188

10. Install custom nodes (ComfyUI-Manager recommended):

cd custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager.git