Mocha in ComfyUI (Portable already installed): Model Files + Dependencies Only

Last Updated: Wednesday, 02/25/2026

Scope: This guide assumes ComfyUI Portable is already installed and launches. It focuses only on:

1) Required Repositories / Files (Direct Links)

2) Exact Local Paths (ComfyUI Portable)

ComfyUI_windows_portable/
  ComfyUI/
    custom_nodes/
    models/
      diffusion_models/
      vae/
      text_encoders/
      loras/
    output/

3) Install / Update WanVideoWrapper

3.1 Clone (if missing)

cd ComfyUI_windows_portable/ComfyUI/custom_nodes
git clone https://github.com/kijai/ComfyUI-WanVideoWrapper.git

3.2 Update (recommended even if already installed)

cd ComfyUI_windows_portable/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper
git pull

4) Install Dependencies

From your ComfyUI portable root:

cd ComfyUI_windows_portable
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\requirements.txt
If pip fails, run: 
python_embeded\python.exe -m pip install --upgrade pip setuptools wheel
Then run the requirements command again.

5) Download Required Model Files + Destination Folder Mapping

5.1 Mocha main model

5.2 Wan 2.1 VAE file

5.3 Text encoder file (FP8 recommended for lower VRAM)

5.4 LightX2V acceleration LoRA (recommended)

6) Load Workflow + Verify File Detection

  1. Launch ComfyUI
  2. Drag workflow JSON into canvas
  3. Press R to refresh model lists
  4. In each relevant node dropdown, select the model files you placed above

7) Quick Verification Checklist

8) Most Common Setup Errors

Once these files/dependencies are set, your environment is ready for Mocha inference workflows.