WAN ANIMATE 2.2 V2 MANUAL INSTALL

Manual Install Method from my last Youtube video:  https://youtu.be/apd68jTrxYc



Windows Installation
Step 1: Prerequisites

Make sure you have the following installed:

7-Zip → https://www.7-zip.org/

Git → https://git-scm.com/download/win

Step 2: Download and Extract ComfyUI

Download the latest ComfyUI NVIDIA portable build (v0.3.65):
https://github.com/comfyanonymous/ComfyUI/releases/download/v0.3.65/ComfyUI_windows_portable_nvidia.7z

Extract with 7-Zip. Your folder should look like:

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

Step 3: Install Required Custom Nodes

Open cmd inside ComfyUI_windows_portable\ComfyUI\custom_nodes and run:

git clone https://github.com/ltdrdata/ComfyUI-Manager.git
git clone https://github.com/kijai/ComfyUI-WanVideoWrapper
git clone https://github.com/rgthree/rgthree-comfy
git clone https://github.com/kijai/ComfyUI-KJNodes
git clone https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite
git clone https://github.com/kijai/ComfyUI-segment-anything-2
git clone https://github.com/9nate-drake/Comfyui-SecNodes
git clone https://github.com/kijai/ComfyUI-WanAnimatePreprocess


Then install dependencies for each node that has a requirements.txt. Example:

..\..\python_embeded\python.exe -m pip install -r ComfyUI-Manager\requirements.txt
..\..\python_embeded\python.exe -m pip install -r ComfyUI-WanVideoWrapper\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-VideoHelperSuite\requirements.txt
..\..\python_embeded\python.exe -m pip install -r ComfyUI-segment-anything-2\requirements.txt
..\..\python_embeded\python.exe -m pip install -r Comfyui-SecNodes\requirements.txt
..\..\python_embeded\python.exe -m pip install -r ComfyUI-WanAnimatePreprocess\requirements.txt

Step 4: Download WAN Animate 2.2 Models

All files are hosted at:
👉 https://huggingface.co/Aitrepreneur/FLX/tree/main

Place them under the correct folders in ComfyUI_windows_portable\ComfyUI\models\:

clip_vision

clip_vision_h.safetensors


detection

vitpose_h_wholebody_data.bin

vitpose_h_wholebody_model.onnx

vitpose-l-wholebody.onnx

yolov10m.onnx



diffusion_models

Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors



loras

lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors

WanAnimate_relight_lora_fp16.safetensors



sams

SeC-4B-fp16.safetensors



text_encoders

umt5-xxl-enc-bf16.safetensors



vae

Wan2_1_VAE_bf16.safetensors



Step 5: Install Extra Python Dependencies

From inside ComfyUI_windows_portable\python_embeded run:

python.exe -m pip install -U pip
python.exe -m pip install "triton-windows<3.5"
python.exe -m pip install hf_transfer
python.exe -m pip install https://github.com/woct0rdho/SageAttention/releases/download/v2.2.0-windows.post3/sageattention-2.2.0+cu128torch2.8.0.post3-cp39-abi3-win_amd64.whl


Also add Python include libs for Triton:
(download zip → extract into python_embeded)
https://github.com/woct0rdho/triton-windows/releases/download/v3.0.0-windows.post1/python_3.13.2_include_libs.zip

Step 6: Run ComfyUI

Double-click run_nvidia_gpu.bat inside ComfyUI_windows_portable.





## **RunPod Installation**

1. Create account at https://bit.ly/runpodAi
2. Pick a 24 GB VRAM GPU with the **aitrepreneur/comfyui** template
3. Access port **8888**
4. Mirror the same folder structure from this guide
5. Use `curl` to grab files, e.g.:
   `curl -L -o "filename" "URL"`
6. Watch logs:
   `tail -f workspace/logs/comfyui.log`



Inside the ComfyUI root (models/ and custom_nodes/ exist):

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


Install Torch + Dependencies

Run:

pip install torch==2.8.0+cu128 torchvision==0.23.0+cu128 torchaudio==2.8.0+cu128 \
    --index-url https://download.pytorch.org/whl/cu128
pip install xformers==0.0.32.post2 triton==3.4.0 diffusers==0.35.2 \
    transformers==4.57.1 peft==0.17.1 accelerate==1.10.1 safetensors==0.6.2 \
    einops==0.8.1 sentencepiece==0.2.1 numpy==2.2.6 opencv-python-headless==4.12.0.88 \
    pillow>=10.3.0 gguf piexif


Optional (for some nodes):

pip install onnxruntime-gpu==1.23.0 onnx coloredlogs humanfriendly flatbuffers


Install SageAttention

Try the wheel first:

pip install --no-build-isolation --prefer-binary "sageattention==1.0.6"


If that fails:

pip install --no-build-isolation "git+https://github.com/woct0rdho/SageAttention.git"