Check Huggingface Link Below for better sorted downloads / the latest (MEGA v3)

These are mixtures of WAN 2.2 and other WAN-like models and accelerators (with CLIP and VAE also included) to provide a fast, "all in one" solution for making videos as easily and quickly as possible.

You just need to use the basic ComfyUI "Load Checkpoint" node with these, as you can take the VAE, CLIP and Model all from one AIO safetensors (saved in your 'checkpoints' folder). All models are intended to use 1 CFG and 4 steps. See sampler recommendations for each version.

Changelog + more on Huggingface:

Latest stuff on Huggingface: https://huggingface.co/Phr00t/WAN2.2-14B-Rapid-AllInOne

New MEGA version includes VACE, does T2V/I2V/First-Last Frame etc. All in One!