LaunchVisual AIAugust 2, 2026

MiniMax H3 open-weights video model with native audio arrives in ComfyUI

MiniMax H3 is supported in ComfyUI 0.30.0+ with open weights, adding text-to-video, image-to-video, and reference-to-video nodes with a resolution selector. It also natively generates stereo audio — dialogue, sound effects, and music — synced in one MP4, and locks character, style, motion, or voice from reference materials.

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed
MiniMax H3 open-weights video model with native audio arrives in ComfyUI — AIBriefs