Uploaded August 2025 | Updated September 2026, 2 weeks ago

---

Wan 2.2 Lightning is super fast. In this Wan 2.2 Lightning Comfyui tutorial I show you how to use it with the GGUF model for LOW Vram and how to SAVE even more time with a extra trick

#### Links from the Video ####

My Wan 2.2 Lightning GGUF Workflow:
drive.google.com/file/d/105kmoS65kdYtVDnAi-V1kLWVcmxZVIUb/view?usp=sharing

My Other Wan 2.2 Video: youtu.be/geSIepK8ekQ

Model download into UNET folder:
Wan 2.2 GGUF Models + VAE:
huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main

Lora Download into Lora Folder:
huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1

Text encoder Moderl into the text_encoder folder:
huggingface.co/chatpig/encoder/blob/main/umt5_xxl_fp8_e4m3fn_scaled.safetensors

TRICK!!!!!
To get a super fast preview, fix the seed on the first Ksampler and set image res to half the size (in my cas 320 x 320)


#### Join and Support me ####
Buy me a Coffee: buymeacoffee.com/oliviotutorials
Join my Facebook Group: facebook.com/groups/theairevolution
Joint my Discord Group: discord.gg/XKAk7GUzAW
Support me on Patreon: patreon.com/sarikas