
MiniMax H3 unifies 2K video, stereo audio and multimodal input
MiniMax has recently launched H3, a multimodal generation model that uses text, image, video, and audio context to create and edit content.
It generates video up to 15 seconds long at 2K resolution with native stereo sound, and supports natural-language references such as video motion, images, and audio.
MiniMax also says it plans to release the model weights in the coming days, subject to applicable laws and regulations.
No comments so far, maybe you want to be first?
Gu



