Back to the Basics and far Beyond that! (Patreon)
Downloads
Content
Hi Friends,
You know me for my advanced workflows and deep-dive tutorials. But every once in a while it's important to go back to the basics — and ComfyUI in 2026 deserves a fresh look. A lot has changed. Things have become easier and more powerful at the same time. But some areas, like workflow building, have also grown more complex. That's why having solid foundational knowledge matters more than ever.
If you're just getting started, I recommend my absolute beginner's guide first. A lot has changed in the world of AI and image models — but in my opinion, SDXL, Pony, and Illustrious are still great models, especially for beginners. They don't need complex setups, and they don't require the latest hardware.
https://www.patreon.com/posts/big-news-ai-is-90798230
What’s coming to Patreon next?
Developing software won’t be my only focus going forward. I have a lot of new content planned for you:
More LoRA training – from fundamentals to advanced, production-ready setups
Long-form AI content creation – I’ll show you how to plan, structure, and produce larger AI-driven projects
New in-depth guides – clearer, more focused, and built for real-world use
And of course Software 🤣
The year has already started strong, and together we’ll push things to the next level. 🚀There’s a lot coming—and this is just the beginning.
🛠️ The Installation Guide
For those of you who want to get your hands dirty, here is the full manual installation guide for the command line.
💡 PRO TIP for Paid Members:If you want to skip the manual typing and potential errors, remember that you have exclusive access to my Installer. It not only installs ComfyUI but also auto-downloads the best models and workflows for you:👉 Download the One-Click Installer: https://www.patreon.com/posts/surprise-update-150848984
Manual Installation (The "Hard" Way):
Step 1: The Pre-requisites
Git: https://git-scm.com/install/
Python (3.12.10 recommended): https://www.python.org/downloads/release/python-31210/
Step 2: The CommandsOpen your terminal (CMD) and run these one by one:
Bash
# 1. Clone ComfyUI
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI
# 2. Create and Activate Virtual Environment
py -3.12 -m venv venv
venv\Scripts\activate
# 3. Upgrade Pip
python -m pip install --upgrade pip setuptools wheel
# 4. Install Torch (Nightly Build with CUDA support)
python -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128
# 5. Install ComfyUI Requirements (CRITICAL STEP)
python -m pip install -r requirements.txt
# 6. Install ComfyUI Manager
cd custom_nodes
git clone https://github.com/ltdrdata/ComfyUI-Manager.git
cd ..
Step 3: Run itTo start ComfyUI, make sure you are in the ComfyUI folder
create a new .bat file and call it "run.bat" or something and put this in:REM Activate the virtual environmentcall venv\Scripts\activate
REM Run ComfyUI in a new windowpython main.py --windows-standalone-build
Save the file and do a double click on the file and ComfyUI will start up.
Thanks again for believing in me and my content. Let's make some awesome art!
Best Regards,
Chris