Nunchux AI demonstrated its inference stack running MiniMax-H3 video generation on AMD MI355X GPUs, achieving 21.8× to 26.7× speedup over SGLang baseline. On eight GPUs, the system generates 5-second videos in 1.33 seconds and 15-second videos in 5.39 seconds, faster than real-time playback.
HyperFlow is an 8-step LoRA for MiniMax-H3 video generation that reduces computational steps from 49 to 8 using data-free flow self-distillation, compatible with official diffusers Modular Pipeline for text-to-video, frame-to-video, and reference-to-video tasks.