WAN 2.2 5B Workflow
A workflow for WAN 2.2 5B with multiple improvements for speed, flexibility, and usability:
Auto resolution calculator – automatically adjusts resolution based on a maximum dimension.
Video length in seconds – define duration in seconds instead of frames.
Fast interrupt – integrates BlehModelPatchFastTerminate to stop WAN generations more quickly.
FastWan LoRA – accelerates sampling. Recommended settings: steps = 4–6, CFG = 1.0.
Taew2.2 Preview – extremely fast (~1s) preview decode to check quality before running the slower
wan2.2_vae.2-Step Process – first run generates a preview with
taew2_2, second run applies the full higher quality VAE decode with upscale and interpolation.
2-Step Process
The wan2.2_vae is slooooooooow...
Sometimes the VAE decode process takes longer than the generation itself.
This workflow allows partially decoding the latent video using the taew2_2 model, which is extremely fast (usually ~1 second, depending on video length and resolution), but slightly reduces video quality.
By using taew2_2 to create a preview, you can quickly decide if the video is worth keeping or if it needs prompt/setting changes before running the slow wan2.2_vae. This saves a lot of time, especially on lower-end hardware.
How to Use
Step 1: On the first run, the workflow generates the video and decodes it with the
taew2_2model (fast preview).Step 2: If nothing is changed, the next run will decode the same latent video using the full
wan2.2_vaemodel. After that, further processing (upscale/interpolation) will be applied, if enabled.
Important
The seed must be fixed. If it changes, a new video will be generated, and the workflow won’t decode the same latent with the full wan2.2_vae.
Download
Get the taew2_2 model here:
https://github.com/madebyollin/taehv/blob/main/taew2_2.pth
Place the file in:ComfyUI\models\vae_approx\
FastWan Lora
In order to use lower step count and speedup the generation, download the FastWan lora and select it on the workflow.
After enabling it, set:
Steps: 4–6
CFG: 1.0
Source: Kijai
Workflow Options
The workflow includes several features you can enable or disable to customize the output:
Enable Fast taew2_2 Preview – Uses
taew2_2for fast preview decoding.Enable Sage Attention – Enables the use of Sage Attention during generation.
Enable Two Steps Process – Runs first with
taew2_2preview, then with fullwan2.2_vaedecoding.Enable Use Tiled VAE – Uses tiled VAE decoding for handling larger resolutions.
Enable Color Correction – Calibrates video colors using the first frame as reference.
Enable Interpolate – Interpolates the video to 50 FPS for smoother motion.
Enable Upscale – Upscales the video using the model selected in the “upscale” group.
Enable Upscaled Video Show/Save – Displays and saves the upscaled video.
Description
Initial version
FAQ
Comments (16)
I'm keep getting "SimpleMath.execute() got an unexpected keyword argument 'c" error.
Update: simply open your manager, search for comfyui_essentials and update it. Problem solved.
Not working
@png reinstall comfyui_essentials from github
this worked for me. i was using the nightly version of essentials. switched to stable version thru manager and works now. thanks!
This does not work. The nodes seem to be broken regardless of what version I download of comfyui essentials.
What's the minimal vram it needs?
I use it with 8GB, running a quantized WAN 5B GGUF (q4). I can generate up to 4 seconds at 1024×768. At 800×600, I've generated 7-second videos with no problem. But I've also seen reports of people using it with 6GB VRAM
@JCB2 I want you have. A working version of this workflow. I am also on 8GbVRAM and cant get the flow to work
@GrimmHelltrap Update ComfyUI and install ComfyUI Manager, then update extensions and install missing extensions
After an install of a different version of ComfyUI this is now working a treat. Thank you
Update ComfyUI and install ComfyUI Manager, then update extensions and install missing extensions
The argument 'c' is related to the "MAX SIZE" input that uses Easy Set, Easy Get and Easy Int nodes from the ComfyUI Easy Use package:
https://github.com/yolain/ComfyUI-Easy-Use
Make sure it is installed correctly
Sadly still doesn't work. Any node that uses insightface doesn't work on the current comfyui. for me at least and everyone else who is new to it. I've read it is due to python 3.13. I found an old build of comfyUI with python 3.11. Insightface and the nodes that use it work there but the manager is outdated. UPdating Comfyui there breaks insightface and the nodes. Not sure if that is causing the issue here but either way cant get past "SimpleMath.execute() got an unexpected keyword argument 'c'" Im going to try download all the extras without using comfy manager on the older Comfyui. See if that works.
@JCB2 Thanks for the help. you inspired me to push and now it works a treat for me.
@GrimmHelltrap I'm glad to hear it worked for you! If you don’t mind sharing, what did you end up doing to fix the errors? Might help others running into the same issue.
If anyone runs into the same problem I had it is likely due to the current version of comfyui coming with python 3.13. Insight face, which is requirement for many useful nodes like instantID, wont install. I found an older build of ComfyUI that came with Python 3.12 embedded and that allowed me to use this workflow along with the other useful nodes that wouldn't work on the latest Comfyui. To be fair even Comfyui states if you have issues with the latest python to try an older one.