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
Version 1.1:
Added optimisations to:
Sampler/Scheduler
Consolidate some nodes
Support for up to 2 LoRAs
FAQ
Comments (12)
Can people stop using node that are not available in the node manager when there's tons of alternative available.
I mixed it with the swarm preset by uploading, except that I just use the standard nodes. Corrected that, but ... You could just change that 2 KSamplers and all would be fine instead of complaining or make your own WF ...
If you do not like what others do, you are always free to do it better and submit it.๐
@darksidewalkerย If people knew how to make workflows they wouldn't have to download yours. It's there to make people life easy. My critic goes in the same direction. Be mad all you want, in the end you improved it for everyone benefit. Also thanks for blocking me, it's a very mature reaction.
@razzzย Yeah, I think a lot of people who post workflows think it's a sense of entitlement when people ask for them to change out custom gear so that it's production-ready.
It really isn't.
The same issue happens with new devs. They put something forward as being usable when it's not, which eats into the time and effort of people who would have built their own workflow that works if it weren't smarter not to re-invent the wheel.
This is probably the most stupid place for me to point that out, but it's probably worth you swapping the ksamplers for ones we know are secure and don't pose a malware threat, and then repost the workflow on your own account so that others don't waste their time here, too.
@thelustriaiย You know that I did just used the samplers from swarmui (which are not a threat or maleware) and already changed them in the comfyui WF for the standard ones? Maybe you should elaborate things before posting a wall of text with false assumptions and rude things?
You know that these "dev's" you are calling out here doing most of the things for free ... "wasting your time" if it's not perfect or has some mistakes? "production ready" would mean you paid and get a professional product or it is meant for company usage.
The thing is all these super smart ppl think they can demand anything for free, but not be able to contribute a thing.
@razzzย I blocked you, bc your fake account with 4k followers and no contributions and M of downloads/generations is not someone who should benefit from something for free while demanding things from dev's.
@darksidewalkerย You really made some real mental gymnastic here. "Fake account with M of downloads/generations." Not once it crossed your mind that I removed the models from the platform, 400+ of them. Generations cannot be faked it's from other users using your models. You prefer imagining a lie than be a man with good self esteem and take some constructive criticism.
@razzzย If you are such a great contributor, you wouldn't lie here and you are not constructive. You are just passive aggressive.
Ni caso @darksidewalker se que para la gente es frustrante, me ha pasado hace un par de meses, no me enteraba de nada, usaba framepack studio, necesitaba usar ComfyUI para probar y jugar mas rapido, pero pasaron muchas noches aprendiendo a usarlo, configurarlo.
Es dificil, porque un nodo mal puesto parece que ya te jode todo el flujo de trabajo, pero lo que haces es admirable, haces tus modelos, flujos, loras sin pedir nada a cambio, al menos lo pones aqui y ya, pero es lo que te digo la gente se frustra, yo creo que es mejor que pongas algo y la gente se acostumbre a arreglarlo, asi me paso a mi, use un flujo estaba mal, otro, otro, al final, a partir de varios construi uno propio, de hecho voy mirando los vuestros para ver si puedo aprender y meter algo mejor, pero eso, en una conversacion como esta te doy las gracias por tu aportacion. Muchas gracias!
I think your 2-LoRA SwarmUI preset is actually another ComfyUI preset. The other one is good.
I uploaded a new one bc SwarmUI updated its logic with 0.9.7 for Wan 2.2
@darksidewalkerย Thank you!
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.