There are far more WAN 2.2 workflows than I realized, but it's too late now :) Maybe someone will find it useful.
RTX 3060 12gb | Ryzen 5 3600 | 32gb RAM | 45-98gb Page File
(With models loaded, 5 second vid)
I2V & T2V: Around 6 minutes
+MMAudio: Around 8 minutes
I set the res to 480 but you can change it using Resolution Master's presets. I considered adding an upscaler, but I couldn't notice a difference and it added an extra minute.
Downloads:
---
I don't recommend this WF if you don't want to download both the I2V and T2V models. If you want to try it still for some reason, add dummy files in your WAN checkpoint folder and use them as the undownloaded models to prevent an error.
Base models & VAE: https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main & https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main
I use Q5. You only need one VAE from either of the first links. Model-2 doesn't need the Lightx2v models below.
CLIP (UMT5): Download with ComfyUI Manager!
Lightx2v: https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/tree/main/loras
MMAudio: Links are in v3's workflow. If you're coming from LTX, MMAudio is okay, but it can't do speech and is very basic.
---
For I2V, you can use Florence and leave your prompt empty unless you want something specific.
To show video previews, turn on "Display animated previews when sampling" in VHS' settings.
If you want FLF for anything other than perfect loops, use the different image switch.
The NSFW switch was made to work with CubeyAI's NSFW lora. In v3, it only switches the MMAudio model from the NSFW one to the regular one.
Delete all the filename stuff near VAE Decode if you don't want them.
Description
Less node packs to install, and I think I fixed what looked like broken file name nodes. Fearnworks seems to corrupt other nodes into thinking they're from Fearnworks...I'm not sure if it's very trustworthy. Also a new small RIFE workflow to make videos 60fps after they've been made.