SILLYTAVERN + TTS + COMFYUI Manual Install

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


SILLYTAVERN + CHATTERBOX TTS + COMFYUI WAN 2.2
MANUAL INSTALL GUIDE



SILLYTAVERN LAUNCHER - MANUAL INSTALL (WINDOWS)
==================================================

Requirements:

Windows 10 or 11

Internet connection

Admin rights for installing Git

Step 1 - Install Git (if needed)

Option A - Using winget (recommended)

Press: WINDOWS + X

Click: "Terminal (Admin)" or "Command Prompt (Admin)"

Run this command:

winget install -e --id Git.Git

When it finishes, close the terminal and open a new one.

Option B - Using the website

Go to: https://git-scm.com/downloads

Download the Windows installer.

Install with the default settings.

Close the installer and open a new terminal.

To check if Git is installed correctly:

git --version

If it shows a version number, you are good.

Step 2 - Choose where you want SillyTavern

Example folder:

D:\AI\SillyTavern

Create or choose a folder where you want SillyTavern.

Open that folder in File Explorer.

Click in the address bar, type:

cmd

and press ENTER.

This opens a command prompt in that folder.

Step 3 - Clone the ST Launcher

In the command prompt, run:

git clone https://github.com/SillyTavern/SillyTavern-Launcher.git

When it finishes:

cd SillyTavern-Launcher

Step 4 - Run the installer

Still in the SillyTavern-Launcher folder, run:

installer.bat

A new window opens.
Follow the instructions there. It will download and install SillyTavern.

To start SillyTavern later, use the shortcut from the launcher or run the start script created by the launcher.





==================================================
CHATTERBOX-TTS-SERVER PLUGIN FOR SILLYTAVERN

This installs Chatterbox-TTS-Server as a plugin inside SillyTavern.

Requirements:

SillyTavern installed

Git installed

Python 3 installed and in PATH

Step 1 - Go to your SillyTavern main folder

Go to the folder where SillyTavern is installed.

Inside it, you should see a "plugins" folder.

Example path:

D:\AI\SillyTavern\SillyTavern-Launcher\SillyTavern

In that folder, do one of these:

Right click in empty space and choose "Open in Terminal" or "Open PowerShell window here"
or

Click in the address bar, type:

cmd

and press ENTER.

Step 2 - Go into plugins

In the terminal, run:

cd plugins

Step 3 - Clone Chatterbox-TTS-Server repo

Run:

git clone https://github.com/devnen/Chatterbox-TTS-Server.git

cd Chatterbox-TTS-Server

Step 4 - Create and activate the virtual env

Create venv:

python -m venv venv

Activate it:

venv\Scripts\activate

Now your prompt should show "(venv)" at the start.

Step 5 - Install CPU or NVIDIA GPU requirements

CPU only (works on any machine):

pip install -r requirements.txt

NVIDIA GPU mode (recommended if you have an NVIDIA GPU):

pip install -r requirements-nvidia.txt

Step 6 - Download Start.bat launcher file

You need a Start.bat file in the Chatterbox-TTS-Server folder.

Option A - Download with your browser:

Open this link:

https://huggingface.co/Aitrepreneur/test/resolve/main/Start.bat

Save the file as:

Start.bat

directly into:

...\SillyTavern\plugins\Chatterbox-TTS-Server\

Option B - Download using PowerShell:

From inside the Chatterbox-TTS-Server folder, run:

powershell -NoLogo -NoProfile -Command ^
"Invoke-WebRequest -Uri 'https://huggingface.co/Aitrepreneur/test/resolve/main/Start.bat?download=true
' -OutFile 'Start.bat' -UseBasicParsing"

Step 7 - How to start the TTS server later

Go to the folder:

SillyTavern\plugins\Chatterbox-TTS-Server

Double click:

Start.bat

This will:

activate the venv

start the Chatterbox TTS server

Then configure it inside SillyTavern as your TTS backend.






==================================================
COMFYUI + WAN 2.2 - LOCAL WINDOWS INSTALL

This installs ComfyUI Windows portable plus Wan 2.2 models (GGUF).

Requirements:

Windows 10 or 11

NVIDIA GPU

7-Zip installed

Git installed

curl available (comes with Windows 10+)

VRAM recommendation for Wan 2.2:

Q4_K_S = use if GPU has less than 12 GB VRAM

Q5_K_S = use if GPU has 12 to 24 GB VRAM

Q8_0 = use if GPU has 24 GB or more VRAM (best quality)

Step 1 - Create a base folder

Example:

D:\AI\ComfyUI

Open this folder, click in the address bar, type:

cmd

and press ENTER to open a command prompt there.

Step 2 - Download ComfyUI Windows portable

In the command prompt, run:

curl -L -o ComfyUI_windows_portable_nvidia.7z "https://github.com/comfyanonymous/ComfyUI/releases/download/v0.3.71/ComfyUI_windows_portable_nvidia.7z
"

Wait until the file finishes downloading.

Step 3 - Extract ComfyUI

Use 7-Zip or similar:

Right click on:
ComfyUI_windows_portable_nvidia.7z

Choose:
Extract here

You should now have:

D:\AI\ComfyUI\ComfyUI_windows_portable

Inside that folder you should see:

run_nvidia_gpu.bat

python_embeded

ComfyUI

etc.

Step 4 - Install custom nodes

In the same terminal:

cd ComfyUI_windows_portable
cd ComfyUI\custom_nodes

Clone required nodes:

git clone https://github.com/ltdrdata/ComfyUI-Manager.git

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

git clone https://github.com/Fannovel16/comfyui_controlnet_aux.git

git clone https://github.com/ltdrdata/ComfyUI-Impact-Pack.git

git clone https://github.com/city96/ComfyUI-GGUF.git

git clone https://github.com/rgthree-comfy/rgthree-comfy.git

git clone https://github.com/yolain/ComfyUI-Easy-Use.git

git clone https://github.com/kijai/ComfyUI-KJNodes.git

git clone https://github.com/ssitu/ComfyUI_UltimateSDUpscale.git

git clone https://github.com/cubiq/ComfyUI_essentials.git

git clone https://github.com/Zehong-Ma/ComfyUI-MagCache.git

git clone https://github.com/wallish77/wlsh_nodes.git

git clone https://github.com/vrgamegirl19/comfyui-vrgamedevgirl.git

git clone https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite.git

git clone https://github.com/Fannovel16/ComfyUI-Frame-Interpolation.git

git clone https://github.com/ClownsharkBatwing/RES4LYF.git

git clone https://github.com/1038lab/ComfyUI-RMBG.git

git clone https://github.com/TinyTerra/ComfyUI_tinyterraNodes.git

git clone https://github.com/ltdrdata/was-node-suite-comfyui.git

Step 5 - Install Python requirements for these nodes

Go back to the ComfyUI_windows_portable root:

cd ..
cd ..

Now you should be in:

...\ComfyUI_windows_portable

Use the embedded Python to install the requirements:

python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-Manager\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\comfyui_controlnet_aux\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-Impact-Pack\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-GGUF\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\rgthree-comfy\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-Easy-Use\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-KJNodes\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI_essentials\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-MagCache\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\wlsh_nodes\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\comfyui-vrgamedevgirl\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\RES4LYF\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-RMBG\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\requirements.txt
python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\was-node-suite-comfyui\requirements.txt

If some fail, you can still run ComfyUI. Most features will still work.

Step 6 - Download Wan 2.2 model files (Windows)

Base model URL:

https://huggingface.co/Aitrepreneur/FLX/resolve/main

From ComfyUI_windows_portable root:

cd ComfyUI\models

A) Text encoder:

curl -L -o "text_encoders\umt5-xxl-encoder-Q5_K_S.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/umt5-xxl-encoder-Q5_K_S.gguf?download=true
"

B) VAE:

curl -L -o "vae\wan_2.1_vae.safetensors" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/wan_2.1_vae.safetensors?download=true
"

C) UNET models by VRAM

Q4_K_S (less than 12 GB VRAM):

curl -L -o "unet\Wan2.2-I2V-A14B-HighNoise-Q4_K_S.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-I2V-A14B-HighNoise-Q4_K_S.gguf?download=true
"

curl -L -o "unet\Wan2.2-I2V-A14B-LowNoise-Q4_K_S.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-I2V-A14B-LowNoise-Q4_K_S.gguf?download=true
"

Q5_K_S (12 to 24 GB VRAM):

curl -L -o "unet\Wan2.2-I2V-A14B-HighNoise-Q5_K_S.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-I2V-A14B-HighNoise-Q5_K_S.gguf?download=true
"

curl -L -o "unet\Wan2.2-I2V-A14B-LowNoise-Q5_K_S.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-I2V-A14B-LowNoise-Q5_K_S.gguf?download=true
"

Q8_0 (24 GB or more VRAM, best quality):

curl -L -o "unet\Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf?download=true
"

curl -L -o "unet\Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf?download=true
"

D) LoRAs:

curl -L -o "loras\Wan2.2-Lightning_I2V-A14B-4steps-lora_HIGH_fp16.safetensors" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-Lightning_I2V-A14B-4steps-lora_HIGH_fp16.safetensors?download=true
"

curl -L -o "loras\Wan2.2-Lightning_I2V-A14B-4steps-lora_LOW_fp16.safetensors" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/Wan2.2-Lightning_I2V-A14B-4steps-lora_LOW_fp16.safetensors?download=true
"

E) Upscalers:

curl -L -o "upscale_models\4x-ClearRealityV1.pth" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/4x-ClearRealityV1.pth?download=true
"

curl -L -o "upscale_models\RealESRGAN_x4plus_anime_6B.pth" "https://huggingface.co/Aitrepreneur/FLX/resolve/main/RealESRGAN_x4plus_anime_6B.pth?download=true
"

Step 7 - Launch ComfyUI

Go back to:

...\ComfyUI_windows_portable

Double click:

run_nvidia_gpu.bat

Then open your browser and go to:

http://127.0.0.1:8188

(or the address shown in the terminal)






==================================================
COMFYUI + WAN 2.2 - RUNPOD (MANUAL OUTLINE)

## **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`



Clone the custom nodes

From ComfyUI root:

cd custom_nodes

Clone the same repos as in Windows:

git clone https://github.com/ltdrdata/ComfyUI-Manager.git

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

git clone https://github.com/Fannovel16/comfyui_controlnet_aux.git

git clone https://github.com/ltdrdata/ComfyUI-Impact-Pack.git

git clone https://github.com/city96/ComfyUI-GGUF.git

git clone https://github.com/rgthree-comfy/rgthree-comfy.git

git clone https://github.com/yolain/ComfyUI-Easy-Use.git

git clone https://github.com/kijai/ComfyUI-KJNodes.git

git clone https://github.com/ssitu/ComfyUI_UltimateSDUpscale.git

git clone https://github.com/cubiq/ComfyUI_essentials.git

git clone https://github.com/Zehong-Ma/ComfyUI-MagCache.git

git clone https://github.com/wallish77/wlsh_nodes.git

git clone https://github.com/vrgamegirl19/comfyui-vrgamedevgirl.git

git clone https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite.git

git clone https://github.com/Fannovel16/ComfyUI-Frame-Interpolation.git

git clone https://github.com/ClownsharkBatwing/RES4LYF.git

git clone https://github.com/1038lab/ComfyUI-RMBG.git

git clone https://github.com/TinyTerra/ComfyUI_tinyterraNodes.git

git clone https://github.com/ltdrdata/was-node-suite-comfyui.git

Then go back:

cd ..

Install their requirements (similar to Windows), for example:

pip install -r custom_nodes/ComfyUI-Manager/requirements.txt
pip install -r custom_nodes/ComfyUI-WanVideoWrapper/requirements.txt
etc.



Download Wan 2.2 models on RunPod

From ComfyUI root:

cd models

Use the same model files as Windows, but with Linux paths. For example:

Text encoder:

curl -L -o "text_encoders/umt5-xxl-encoder-Q5_K_S.gguf"
"https://huggingface.co/Aitrepreneur/FLX/resolve/main/umt5-xxl-encoder-Q5_K_S.gguf?download=true"

VAE:

curl -L -o "vae/wan_2.1_vae.safetensors"
"https://huggingface.co/Aitrepreneur/FLX/resolve/main/wan_2.1_vae.safetensors?download=true"

Then download UNETs, LoRAs and upscale models using the same URLs as the Windows commands, just changing backslashes "" to slashes "/" in the paths.

Step 8 - Launch ComfyUI