Krea 2 Manual Install V2

Manual Install for my last Youtube video: https://youtu.be/v6KRngGo10U

Windows Installation (Local PC)
Step 1: Prerequisites

Make sure you have these installed before doing anything else:

7-Zip
https://www.7-zip.org/

Git for Windows
https://git-scm.com/download/win

Reboot once after installing Git to make sure it is available in cmd.

Step 2: Download and Extract ComfyUI

Download the official NVIDIA portable build of ComfyUI:

ComfyUI v0.26.0 (NVIDIA Portable)
https://github.com/comfyanonymous/ComfyUI/releases/download/v0.26.0/ComfyUI_windows_portable_nvidia.7z

Extract it with 7-Zip.

Your folder structure must look like this:

ComfyUI_windows_portable/
├── ComfyUI/
│   ├── models/
│   └── custom_nodes/
├── python_embeded/
└── run_nvidia_gpu.bat

If this structure is wrong, stop here and fix it.

Step 3: Install Required Custom Nodes

Open Command Prompt inside:

ComfyUI_windows_portable\ComfyUI\custom_nodes

Then clone all required nodes:

git clone https://github.com/ltdrdata/ComfyUI-Manager.git
git clone https://github.com/rgthree/rgthree-comfy.git
git clone https://github.com/kijai/ComfyUI-KJNodes.git
git clone https://github.com/cubiq/ComfyUI_essentials.git
git clone https://github.com/RamonGuthrie/ComfyUI-RBG-SmartSeedVariance.git
git clone https://github.com/capitan01R/ComfyUI-Krea2T-Enhancer.git

Step 4: Install Node Dependencies

Still inside custom_nodes, install requirements using ComfyUI’s embedded Python:

....\python_embeded\python.exe -m pip install -U pip

Then run:

....\python_embeded\python.exe -m pip install -r ComfyUI-Manager\requirements.txt
....\python_embeded\python.exe -m pip install -r rgthree-comfy\requirements.txt
....\python_embeded\python.exe -m pip install -r ComfyUI-KJNodes\requirements.txt
....\python_embeded\python.exe -m pip install -r ComfyUI_essentials\requirements.txt
....\python_embeded\python.exe -m pip install -r ComfyUI-RBG-SmartSeedVariance\requirements.txt
....\python_embeded\python.exe -m pip install -r ComfyUI-ComfyUI-Krea2T-Enhancer\requirements.txt

Yes, this takes time. That’s why the installer exists 😄

Step 5: Download KREA 2 Models

All model files are hosted here:

👉 Hugging Face
https://huggingface.co/Aitrepreneur/FLX/tree/main

Place them exactly like this:

models/text_encoders/
qwen3vl_4b_fp8_scaled.safetensors

models/loras/
krea2_turbo_lora_rank_64_bf16.safetensors

models/vae/
qwen_image_vae.safetensors

models/diffusion_models/
Choose one based on your GPU:

RTX 5000 series:
krea2_turbo_mxfp8.safetensors

RTX 4000 / 3000 / 2000 series or older:
krea2_turbo_fp8.safetensors

Make sure the filenames are exactly correct.

Step 6: Run ComfyUI

From ComfyUI_windows_portable:

Double-click:

run_nvidia_gpu.bat

Then open your browser at:

http://127.0.0.1:8188

If it launches, you’re done.

RunPod Installation (Cloud)
Step 1: Create Account 👉 RunPod  https://bit.ly/runpodAi

Step 2: Create Pod

Use a CUDA 12.1 compatible pod.

Recommended:

24 GB VRAM GPU
Your ComfyUI template
Expose port 8188

Step 3: Enter the ComfyUI Folder

SSH or use the Web Terminal inside the pod.

Make sure you are inside your ComfyUI root folder, where these exist:

models/
custom_nodes/
main.py

If you are not inside the ComfyUI root, stop and fix that first.

Step 4: Create Virtual Environment

Run:

python3 -m venv venv
source venv/bin/activate
pip install -U pip setuptools wheel

Step 5: Install Torch

This setup assumes CUDA 12.1:

pip install torch==2.4.0+cu121 torchvision==0.19.0+cu121 torchaudio==2.4.0+cu121
--index-url https://download.pytorch.org/whl/cu121

Then install the baseline image libs:

pip uninstall -y opencv-python || true
pip install opencv-python-headless==4.12.0.88
pip install "pillow>=11.0.0"

Step 6: Clone Required Custom Nodes

Go into custom_nodes:

cd custom_nodes

Then clone all required nodes:

git clone https://github.com/ltdrdata/ComfyUI-Manager.git
git clone https://github.com/rgthree/rgthree-comfy.git
git clone https://github.com/kijai/ComfyUI-KJNodes.git
git clone https://github.com/cubiq/ComfyUI_essentials.git
git clone https://github.com/RamonGuthrie/ComfyUI-RBG-SmartSeedVariance.git
git clone https://github.com/capitan01R/ComfyUI-Krea2T-Enhancer.git

Then go back to the ComfyUI root:

cd ..

Step 7: Install Node Dependencies

With the virtual environment still active, run:

pip install -r custom_nodes/ComfyUI-Manager/requirements.txt
pip install -r custom_nodes/rgthree-comfy/requirements.txt
pip install -r custom_nodes/ComfyUI-KJNodes/requirements.txt
pip install -r custom_nodes/ComfyUI_essentials/requirements.txt
pip install -r custom_nodes/ComfyUI-RBG-SmartSeedVariance/requirements.txt
pip install -r custom_nodes/ComfyUI-Krea2T-Enhancer/requirements.txt

Then install the extra packages used by this setup:

pip install gguf piexif
pip install librosa
pip install google-generativeai google-ai-generativelanguage

Step 8: Download KREA 2 Models

All model files are hosted here:

👉 Hugging Face
https://huggingface.co/Aitrepreneur/FLX/tree/main

You can use this base URL:

HF_BASE="https://huggingface.co/Aitrepreneur/FLX/resolve/main"

Then run:

mkdir -p models/text_encoders
mkdir -p models/vae
mkdir -p models/diffusion_models
mkdir -p models/loras

Download the text encoder:

curl -L -o models/text_encoders/qwen3vl_4b_fp8_scaled.safetensors "$HF_BASE/qwen3vl_4b_fp8_scaled.safetensors?download=true"

Download the VAE:

curl -L -o models/vae/qwen_image_vae.safetensors "$HF_BASE/qwen_image_vae.safetensors?download=true"

Download the LORA:

curl -L -o models/loras/krea2_turbo_lora_rank_64_bf16.safetensors "$HF_BASE/krea2_turbo_lora_rank_64_bf16.safetensors?download=true"

Download the KREA 2 model:

curl -L -o models/diffusion_models/krea2_turbo_fp8.safetensors "$HF_BASE/krea2_turbo_fp8.safetensors?download=true"

Step 9: Run ComfyUI and watch logs

tail -f /workspace/logs/comfyui.log