[DigitalToday reporter Chi-gyu Hwang (황치규)] Chinese AI company MiniMax on Thursday unveiled a new video generation model that processes text, images, video and audio together and has moved to compete with ByteDance and Kuaishou, Reuters reported.
According to the report, the Shanghai-based company said the new model, H3, can generate videos up to 15 seconds long in 2K resolution with native stereo sound. It also offers functions including video editing and transferring motion from one video to another using different-format prompts and reference materials.
MiniMax plans to release the H3 model weights within days so users can download the system and modify it themselves. Many video generation models are closed, but Chinese AI companies appear to be seeking to expand the open-weight approach in this area as well.
MiniMax, founded in 2022, listed in Hong Kong in January, following Z.ai as the second such listing.
Reuters has previously reported, citing sources in early July, that MiniMax plans to launch H3 within this month and is also developing a language model with 2.7 trillion parameters.
Chi-gyu Hwang (황치규)
delight@d-today.co.kr