✨ WAN2.1 — Video loop — Simple Workflow
A clean, all-in-one WAN video loop workflow built entirely with the UmeAiRT Toolkit for ComfyUI.
It allows you to use a video to create a sequence that ends at the beginning of the source video, thereby creating a loop.
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 (4)
Great job.
If you have time I'd like to see more simplified (even barebone) versions of your workflows.
I just saw the first and last frame models today, and the workflow came
The concept feels like some kind of video extension due to the way it continues or ends the clip, which isn’t a smooth transition—though sometimes it works well depending on the prompt, action, and the Loras used.
Your other flow, StartEndFrames gguf, seems to create better loops by using two identical images.
To fix the issue of the final frames darkening, you need to add the kj "Color Match" node. I connected it after Merge Video, added a reference image from the first frame, and routed it to the VHS Output (it can also go to ClearVram—personally, I do interpolations separately).
There’s also a "Color Match Image" node, but I haven’t done enough comparisons yet.
The 720p model seems to reduce this color shift, and Color Match might do a better job.
Thanks for your feedback. I've been pretty busy so I haven't made any progress on this workflow, but the new version incorporates your suggestion.