✨ WAN2.1 — Video extension — Simple Workflow
A clean, all-in-one WAN video extension 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-video 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)
Recommendation :
>24 gb Vram: base or Q8_0
16 gb Vram: Q5_K_S
<12 gb Vram: Q4_K_S
For base version
VACE Model: wan2.1_vace_14B_fp8_e4m3fn.safetensors or wan2.1_vace_1.3B_fp16.safetensors
In models/diffusion_models
CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors
in models/clip
For GGUF version
VACE Quant Model: Wan2.1-VACE-14B-QX_0.gguf
In models/diffusion_models
Quant CLIP: umt5-xxl-encoder-QX.gguf
in models/clip
VAE: wan_2.1_vae.safetensors
in models/vae
ANY upscale model (depreciated):
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in models/upscale_models
Description
What's new? :
New interface,
New upscaler,
New model optimisation,
New LoRA loader.
FAQ
Comments (6)
I import a 32 FPS vid that was interpolated from 16 FPS, and always end up with 64 FPS - the 'new' half of the video plays at twice the speed. Any help adjusting this? I tried the force_rate as well as various interpolation setups but it's always the same.
Why you dont use the base 16 fps video and interpolate after?
@UmeAiRT Oh, so just make all "parts" of the video not interpolated and then interpolate everything on last extension attempt?
Edit: I mean, if I want to have a short vid made out of 4 2-second long parts, I should turn on interpolation only on the last Extension, so whole thing is interpolated?
@terrosaurx Yes ^^ the interpolation is done on the new merged video, regardless of the number of merges that were made before
@UmeAiRT Now that makes a lot of sense, initially I thought only the added part is being interpolated. Thanks for help! Your workflows are incredible <3
Thanks for all these resources
The OG result includes the full video, but IN and UP only include the new portion. Can you change it to make IN and UP include the full video? Otherwise each extra process not in one workflow seems to make the video darker and causes mismatch.