FastVideo-FastH3-8-Step-V2 distills MiniMax-H3 into an 8-step text-to-video model

solyarisoftware · x · 2026-09-18

A new model on Hugging Face, FastVideo-FastH3-8-Step-V2, is a distilled version of MiniMax-H3 that generates video from text in just 8 steps, built for speed and efficiency so creators can get quick results without sacrificing much quality.

Original post →

More from Multimodal

Multimodal channel →