Difference between revisions of "ComfyUI: instalasi"

Revision as of 15:34, 21 September 2025

Referensi: https://marcqualie.com/blog/post/install-comfyui-on-ubuntu

Install dependency

sudo apt update
sudo apt install git python3 python3-venv python3-dev build-essential libgl1 ssh systemd-timesyncd -y

Install nvidia drivers

sudo ubuntu-drivers list --gpgpu
sudo apt update
sudo ubuntu-drivers install --gpgpu
sudo nvidia-cuda-toolkit

sudo nvidia-smi

Clone ComfyUI into ~/src

git clone https://github.com/comfyanonymous/ComfyUI.git ~/src/comfyanonymous/ComfyUI

Set up the Python virtual environment

sudo apt install python3.12-venv

cd ~/src/comfyanonymous/ComfyUI
python3 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip wheel
pip install -r requirements.txt

Install GPU-accelerated PyTorch (Optional)

pip install torch torchvision

Referensi

https://marcqualie.com/blog/post/install-comfyui-on-ubuntu

Difference between revisions of "ComfyUI: instalasi"

Revision as of 15:34, 21 September 2025

Referensi

Navigation menu

Search

@@ Line 1: / Line 1: @@
-Berikut panduan instalasi '''ComfyUI menggunakan Docker''' di server '''Ubuntu 24.04'''.
+Referensi: https://marcqualie.com/blog/post/install-comfyui-on-ubuntu
+Install dependency
+ sudo apt update
+ sudo apt install git python3 python3-venv python3-dev build-essential libgl1 ssh systemd-timesyncd -y
-==1. Prasyarat==
-Pastikan server sudah siap:
- sudo apt update && sudo apt upgrade -y
+Install nvidia drivers
- sudo apt install -y git docker.io docker-compose
-Jika pakai GPU NVIDIA, instal juga driver & runtime:
+ sudo ubuntu-drivers list --gpgpu
+ sudo apt update
+ sudo ubuntu-drivers install --gpgpu
+ sudo nvidia-cuda-toolkit
-  sudo apt install -y nvidia-driver-535 nvidia-docker2
+  sudo nvidia-smi
- sudo systemctl restart docker
-==2. Clone Repository ComfyUI==
+Clone ComfyUI into ~/src
-  git clone https://github.com/comfyanonymous/ComfyUI.git
+  git clone https://github.com/comfyanonymous/ComfyUI.git ~/src/comfyanonymous/ComfyUI
- cd ComfyUI
+Set up the Python virtual environment
-==3. Buat File `docker-compose.yml`==
+ sudo apt install python3.12-venv
-Contoh konfigurasi (CPU only):
+ cd ~/src/comfyanonymous/ComfyUI
+ python3 -m venv .venv
+ source .venv/bin/activate
+ pip install --upgrade pip wheel
+ pip install -r requirements.txt
- version: "3.9"
+Install GPU-accelerated PyTorch (Optional)
- services:
-   comfyui:
-     image: ghcr.io/comfyanonymous/comfyui:latest
-     container_name: comfyui
-     ports:
-       - "8188:8188"
-     volumes:
-       - ./output:/app/output
-       - ./models:/app/models
-     restart: unless-stopped
-Jika ingin pakai '''GPU NVIDIA''' (CUDA):
+ pip install torch torchvision
- version: "3.9"
- services:
-   comfyui:
-     image: ghcr.io/comfyanonymous/comfyui:latest
-     container_name: comfyui
-     ports:
-       - "8188:8188"
-     volumes:
-       - ./output:/app/output
-       - ./models:/app/models
-     deploy:
-       resources:
-         reservations:
-           devices:
-             - capabilities: [gpu]
-     runtime: nvidia
-     restart: unless-stopped
-==4. Jalankan Container==
- docker-compose up -d
-Cek status:
- docker ps
+==Referensi==
+* https://marcqualie.com/blog/post/install-comfyui-on-ubuntu
-==5. Akses ComfyUI==
-Buka browser ke:
- http://<IP_SERVER>:8188
-==6. Tambahan (Opsional)==
-* Jika butuh update:
-  git pull
-  docker-compose pull
-  docker-compose up -d
-* Jika ingin custom extension, mount folder:
-  - ./custom_nodes:/app/custom_nodes
-Mau saya bikinkan '''versi Dockerfile custom'' (misalnya pakai Ubuntu base + Python 3.11 + ComfyUI build dari source), atau cukup langsung pakai image resmi dari `ghcr.io/comfyanonymous/comfyui` di atas?