My ComfyUI workflows for using Wan 2.2
This workflows are used by me to create my art.
They are optimized for my checkpoints and created of my latest knowledge to enhance the outcome.
"If this workflow leveled up your day, I'd purr-eciate a like! ๐ป"
Versions & Information๐๐๐๐๐๐๐๐
๐ Please read below and the file descriptions "About this version" for more info's.
๐ฌ๐Click me! HowTo + Video
๐กSome WAN 2.2 versions use high+low checkpoints, other like S2V use only a single checkpoint - make sure to read the descriptions and use the correct checkpoints.
โ ๏ธ Do not use the workflows with the "Nodes 2.0 beta" from ComfyUi or it will mess up things.
๐๐๐๐๐๐๐๐
What you get from the comfy workflows:
โจ๏ธ Easy controls
โ As less as possible dependencies
๐ชง Detailed documentation
โ๏ธ Highly automatic logic
โจ Optimized results
๐ฌ Fully automated resolution logic
๐ Bookmark-Shortcuts with number keys
Types of workflows
FastFidelity C-AiO
๐ผ๏ธ I2V and FLF2V
๐งฉ Automatic aspectโratio calculation and fitting
โจ Multiple Upscalers
Torchlanc (very fast, color correct, low VRAM)
Upscale with Model (additional detail, high quality)
RTX Super Resolution (ultra fast, very accurate)
๐ค Video resolution matching - Fully automatic scaling and resolution calculations
๐ Length automation - Fully automatic calculation of frame count
๐ซฅ Watermark option
๐งฎ Color match feature
๐พ MiniMeme feature - Create small gif's
๐ญ NAG - Negative prompting with CFG1
๐ช Interpolation feature
๐ Perfect loop feature
๐ Last Frame Extraction
๐ Bookmark-Shortcuts - with number keys

FastFidelity C-SVI
๐ผ๏ธ SVI (SVI 2.0 up to 10 samplers)
๐งฉ Automatic aspectโratio calculation and fitting
โจ Ultraโfast, colorโcorrect upscaling (torchlanc) OR Upscale with Model
๐ค Video resolution matching - Fully automatic scaling and resolution calculations
๐ Length automation - Fully automatic calculation of frame count
๐ซฅ Watermark support
๐ช Interpolation feature
๐ Bookmark-Shortcuts - with number keys
Swarm Basic
Absolute basic SwarmUI preset
Not recommended over ComfyUI for video generation
Backend Test
If this does not create the example video your ComfyUI backend is broken.
If this works, but your other workflow not, the other workflow is broken or missing dependencies
๐ฉป Known issues and advice's
โ ๏ธ Some workflows may set on webp av1 encoding (VHS node) - If your computer/setup missing drivers use any other like H265 or H264!
Install ffmpeg!
Update Comfyui and custom_nodes!
Update pytorch 2.9+cu128 or higher
Make sure to read where files/models should be placed inside the workflow
Check if the filepath for model/clip/vae match your system like Linux/Windows
The plugin ComfyUI-DD-Translation can break node connection (avoid)
All older Versions are available inside my GitHub Repo.
Spacial thanks to @Abyss_Games for a really good idea and help with the "loop"!
I got some really good ideas from @Gladas workflows!
YOU are responsible for outputs as always! If you make ToS violating content and I get aware I WILL report this.
Description
Basic High-Low i2v Workflow for ComfyUI
Version 1:
Initial release
FAQ
Comments (5)
i might be just dumb but where do i put an image into this image to video workflow ? :D
It looks like the comfyui template is messed up. Maybe it's meant for t2v? Also there are 3 ksamplers (I think there should only be two) and nothing put in for the start stop steps on any of them.
rando2048ย Yeah, I normally do not use comfy. Got a little confused. I uploaded a working version.
Okโฆ Iโm going crazy. I keep getting clip errors. Iโve been searching for what should be the correct clip model for these 2.2 GGUF models. I tried the 2.1 clip model from your lightspeed workflow. It loads THEN crashes out. What am I missing?
The clip I use is: umt5_xxl_fp8_e4m3fn_scaled
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index โ we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.