✨ WAN2.2 — Text to video — Simple Workflow
A clean, all-in-one WAN text-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI.
Only 12 nodes. No spaghetti wires. Just load your model, write your prompt, and hit generate.
⚠️ IMPORTANT — Nodes 2.0 Required
This workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.
How to activate Nodes 2.0:
Open ComfyUI
Go to Settings (⚙️ icon, bottom-left)
Find "Use Nodes V2 (Vue)" and toggle it ON
Refresh the page
Load the workflow
If you prefer the classic interface, check out my Legacy version of this workflow instead (link).
🎯 Features
Text-to-Image generation
Automatic download of models in auto version
Built-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better quality
Full metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing
3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.
📦 Custom Node Required
Only one custom node to install:
Install via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer.
The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.
📂 Files you need (in manual version)
For base version
I2V Model : wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors and wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors
In models/diffusion_models
CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors
in models/clip
For GGUF version
I2V Quant Model : wan2.2_i2v_high_noise_14B_QX.gguf and wan2.2_i2v_low_noise_14B_QX.gguf
In models/unet
Quant CLIP: umt5-xxl-encoder-QX.gguf
in models/clip
For lightx2V version
lightx2V LoRA : Wan2.2-Lightning_T2V-A14B-4steps-lora_HIGH_fp16.safetensors and Wan2.2-Lightning_T2V-A14B-4steps-lora_LOW_fp16.safetensors
CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors
in models/clip
VAE: wan_2.1_vae.safetensors
in models/vae
ANY upscale model:
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in models/upscale_models
Description
🔄 Full Nodes 2.0 rewrite
Rebuilt entirely with the UmeAiRT Toolkit pipeline (only 1 custom node needed)
SeedVR2 Upscaler and metadata saver now built-in with on/off toggles
12 nodes total — clean, visual, beginner-friendly
⚠️ Requires "Nodes V2 (Vue)" enabled in ComfyUI settings
FAQ
Comments (8)
Hello, I'm using version 2.0. I noticed that LoRa only has one branch, while WAN2.2 has two types of LoRa: high and low. How do I load LoRa?
The LoRA node applies to both models, high and low noise
@UmeAiRT Thank you for your reply. So, in this node, loading both the high and low LOA values simultaneously allows them to take effect at the same time? Is that correct?
@icefox21974 It patches both models in the same way, one after the other. Do you see a relevant use of a lora node per model to create variations? the goal is to provide a simple workflow and in the vast majority of cases we want to apply the lora to both high and low noise
@ UMEAIRT I think it's better, it's simpler, it's more effective,
wow
new version !
Great Workflow, really easy to understand.
However I just wanted to know if there is a way to change the duration so that you're just creating a single image?
Yes with this workflow : https://civitai.com/models/1881883