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! 😻"
Versions & Information👇👇👇👇👇👇👇👇
👉 Please read below and the file descriptions "About this version" for more info's.
🎬🐈Click me! HowTo + Video
💡Some 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.
⚠️ Do not use the workflows with the "Nodes 2.0 beta" from ComfyUi or it will mess up things.
👇👇👇👇👇👇👇👇
What you get from the comfy workflows:
♨️ Easy controls
✅ As less as possible dependencies
🪧 Detailed documentation
⛓️ Highly automatic logic
✨ Optimized results
🎬 Fully automated resolution logic
🔖 Bookmark-Shortcuts with number keys
Types of workflows
FastFidelity C-AiO
🖼️ I2V and FLF2V
🧩 Automatic aspect‑ratio calculation and fitting
✨ Multiple Upscalers
Torchlanc (very fast, color correct, low VRAM)
Upscale with Model (additional detail, high quality)
RTX Super Resolution (ultra fast, very accurate)
🤝 Video resolution matching - Fully automatic scaling and resolution calculations
🕠 Length automation - Fully automatic calculation of frame count
🫥 Watermark option
🧮 Color match feature
👾 MiniMeme feature - Create small gif's
🎭 NAG - Negative prompting with CFG1
🪄 Interpolation feature
🌀 Perfect loop feature
🃏 Last Frame Extraction
🔖 Bookmark-Shortcuts - with number keys
FastFidelity C-SVI
🖼️ SVI (SVI 2.0 up to 10 samplers)
🧩 Automatic aspect‑ratio calculation and fitting
✨ Ultra‑fast, color‑correct upscaling (torchlanc) OR Upscale with Model
🤝 Video resolution matching - Fully automatic scaling and resolution calculations
🕠 Length automation - Fully automatic calculation of frame count
🫥 Watermark support
🪄 Interpolation feature
🔖 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
🩻 Known issues and advice's
⚠️ 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
## Requirements
- https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite
- https://github.com/rgthree/rgthree-comfy
- https://github.com/Artificial-Sweetener/comfyui-WhiteRabbit
packaging, torchlanc
- https://github.com/phazei/ComfyUI-HunyuanVideo-Foley
- The corresponding models see notes
---
## Features
- 🧩 Combine multiple videos
- 🔊 Add audio foley or MMAudio to videos
---
## Changes
- Added MMaudio or Foley
- More descriptions
## Fixes
- none
FAQ
Comments (15)
So will 1.6 use less of my 64GB of ram?
Don't think so, except for the upscaling part.
Very stunning workflow, hope there is a Duration Extension or loop workflow.
It is build in, you just activate this.
@darksidewalker I have activate it and gain a 5 second(frame length = 97) loop, I wonder how to get more than 5 s output (for example:10s) ,increase the frame length?
@yazi6393wy136 yes more frames = more seconds
The best workflow I tested for now, I just need to pray and do multiple try to launch it the 1st time, with 64gb of ram it's pixel. But after that, everything is perfect! Only 2 minutes for a 1024*576 video with a 5070ti
This workflow is amanzing, thanks for your great work! Will tip!
I have some issues with moving the camera - no matter what i enter, it doesn't happen. Any idea on what this could be?
No idea, the camera is controlled through the prompts, I would suggest trying to change the prompt.
I love how fast and simple your workflow is. One issue. I've notice using the last frame to continue creates a degradation in quality in the next 5sec video and so on. Is there a possible fix? Would a simple upscaling of the last image fix this?
Blame the VAE, it would be better not to reencode not to get lower quality and seams.
What's "simple upscaling"? You need vid2vid to fix artifacts
You can create your first/last frames in QwenEdit. Create a story or direction you want to happen through many clips. That way it will not look degraded. Then you combine the clips together, make sure to use the correct images so they flow to the next when you combine.
Trying to do it all in from last video frames is faster but not good at all.
You can also try SeedVR2 and use a lower res version of the completed video to upscale details back in.
Or do as qek mentioned, vid to vid latent detailer/upscaler, doesn't always keep the likeness. Try to keep the noise setting down .20 to stay closer to original video or can play around ang go higher noise.
@R3G4L SeedVR2 crashes my ComfyUI, I've been using either Compact or FlashVSR 1.1 to upscale
@R3G4L So load my initial image into qwenedit workflow and make future frames with it?
I made a overhaul of my WF and the degration for chaining is almost not visible from my initial tests. You could try the new workflow if you like.