✨ 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
Base version
FAQ
Comments (14)
Hi. is this to increase the duration of video. can you please explain.
I'm having trouble finding the right words to explain in English: but to explain simply, you import a video and the workflow will automatically retrieve the last frame and the frame rate to generate a continuation of the video. Then the continuation is merged with the original.
@UmeAiRT ok. thanks for your response, dear. i got it.
Love the workflow! Thank you
I'm having some problems running the workflow mostly on the upscaling part. always have error on low memory however the spec are GPU 5070 TI / 192 Memory ram xeon CPU 🥲at the moment in running the workflow with out scaling
Your settings are too high or you are running too big of a model.
Upscaling long videos requires a lot of VRAM
@UmeAiRT thank for the replay, I find out the problem. I was upscaling the video without limiting the framerate 👍
thank you very much
Hi mate, thanks for the workflow and the guide. I was using it this morning and it helped me a lot!
Thank you, with pleasure
So, the "OG" output plays at the correct frame rate (16fps), but the EXT version is playing the new portion at double speed for some reason? I'm looking at the nodes and can't see where that is happening.