# [AI Video] MiniMax-H3 All-in-One Video Generation V4 Workflow - latent chunked secondary sampling - RH Edition

# [Features] Latest acceleration scheme; official skill automatic/manual prompt optimization (can be disabled if not needed); text-to-video, image-to-video, and reference-to-video 3-in-1; latent chunked secondary sampling; small faces are neither oily nor distorted; digital human audio can be locked unchanged; clean management of image, video, and audio assets

# [Author] Astral

# [Workflow Tutorial]:https://space.bilibili.com/176339505

# [Local Workflow + Models]:https://pan.quark.cn/s/f8af7c9e64f1