Dataset is 4 hours of diversified and trimmed (5s) videos and 5000+ images

Recommend using 8 / 12 steps, with a Lightning LoRA ( I made some comparisons for these lightning models here )

shift 8

All previews videos was generated on the full fp16 models, with the same RTX PRO 6000.

This is my RUNPOD referal link to earn 5$, wich is about 6h of free RTX 5090 usage : https://runpod.io?ref=u7b2habt

It also helps me to train new models, thanks.