Posting two derivative HunyuanVideo models here for convenience for others. I originally found them here:

https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main

You can find the VAE there as well ^^^

Files Section has two files --->

1. Full model is the Regular HunyuanVideo FP8 model (CFG6, Flow 9)

2. Pruned model is the FastHunyuanVideo FP8 model (CFG 9, Flow 17) and use with the LORA below.

N.B. I realize that they are the exact same size, but they are in fact different files for different purposes.

LORA: https://huggingface.co/Kijai/HunyuanVideo_comfy/blob/main/hyvideo_FastVideo_LoRA-fp8.safetensors