Here is the workflow pictured:

https://civitai.com/models/1112672/fasthunyuanvideo6step

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).

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

Instead of using the Fast checkpoint to lower steps, you may use this LORA.

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