WAN 2.2 in Stable Forge UI Neo - One Click Windows Installer

I built another one-click installer for Stable Diffusion WebUI Forge Neo, specifically designed to run the WAN 2.2 GGUF Video Model.
 
About Forge Neo
Forge Neo is the natural progression of the last Forge release (based on Gradio 4.40.0), developed before the original maintainer became unavailable. This version supports SD, Flux, Nunchaku, WAN, and more. Its main focus is on performance and usability - keeping things streamlined, lightweight, and free from unnecessary bloat. It remains highly optimized for modern workflows without requiring ComfyUI.
GitHub Repository: https://github.com/Haoming02/sd-webui-forge-classic/tree/neo
 
Included in the Package
The installer automatically sets up: Sage, Flash Attention 2, Triton for Windows, Pytorch 2.8.0+cu128.
Default models downloaded and placed into their folders:
WAN 2.2 T2V and I2V GGUF video models: Wan2.2-T2V-A14B-GGUF (LowNoise) and Wan2.2-I2V-A14B-GGUF (LowNoise)
UMT5_xxl_fp8_e4m3fn_scaled.safetensors clip model (Updated 2-17-26, GGUF no longer works)
WAN 2.1 VAE model: Wan_2.1_ComfyUI_repackaged VAE
WAN 2.2 T2V and I2V 4steps LoRA models: Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V2.0 and Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1
 
Usage Notes
Download and place the installer files into their own folder.
Double-click to install the project locally - no additional setup needed.
Ensure FFmpeg is installed: https://www.ffmpeg.org/download.html
Once the web interface is open, follow the configuration settings shown in the images below.
Add the LoRA model under the LoRA tab.
If using Text-to-Video or Image-to-Video, confirm the correct models are selected.
I have tested generations up to 81 frames, which worked smoothly.