MiniMax launches H3 video model with open weights, undercutting rivals on price
AI video model releases
MiniMax launches H3 video model with open weights, undercutting rivals on price
MiniMax released H3, a video-generation model that processes text, images, video and audio, and can generate clips up to 15 seconds in 2K resolution with native stereo sound.
H3 can edit existing footage and transfer movements between videos using instructions and reference material in different formats.
MiniMax plans to release H3's model weights within days, extending China's open-weight trend into video generation, where most major models stay proprietary.
MiniMax says generating 2K video with H3 costs less than one-third of mainstream rival products, and the model is built to run on several Chinese-made chips.
The release intensifies competition following ByteDance's Seedance 2.0 and Kuaishou's Kling 3.0, and comes weeks after Reuters reported MiniMax was also developing a 2.7-trillion-parameter language model.
cho.sh