| Mobile Web

MiniMax unveils H3 video generation model amid open-weight push

Chinese AI company MiniMax on Thursday unveiled H3, a new video generation model that can process text, images, video and audio together, Reuters reported. The Shanghai-based company said H3 can create videos up to 15 seconds long in 2K resolution with native stereo sound. It also supports editing and transferring motion from one video to another using different prompts and reference material. MiniMax plans to release the model weights within days.