Firm aims to ‘support open-source community’ and a ‘broad range of hardware’, as H3 model bests Seedance 2.0 in some tasks.

Seedance 2.5 and H3 have been designed to create longer content as both companies double down on multimodal context understanding

Chinese AI firm MiniMax launched its advanced H3 video-generation model, capable of processing text, images, video, and audio, intensifying competition with ByteDance and Kuaishou.