Chinese AI firm MiniMax released a new video-generation model on Friday that can process text, images, video and audio, ​stepping up competition in a fast-growing market led by rivals ‌ByteDance and Kuaishou.

The Shanghai-based company said its H3 model could generate videos of up to 15 seconds in 2K resolution with native stereo sound. It can also edit ​existing content and transfer movements from one video to another ​using instructions and reference material supplied in different formats.

MiniMax said ⁠it planned to release H3’s model weights within days, allowing users to ​download and customise the underlying system. The move would extend the open-weight ​approach increasingly adopted by Chinese AI developers into video generation, where many prominent models remain proprietary.

Founded in 2022, MiniMax is one of China’s “AI tigers”, a group of well-funded ​startups competing with domestic tech giants and U.S. leaders in the crowded ​market for foundation models. It became the second of the group to list publicly ‌when ⁠it floated in Hong Kong in January, following Z.AI.

Reuters reported in early July, citing a person with direct knowledge, that MiniMax planned to launch H3 later in the month and that it was developing a 2.7-trillion-parameter language model.

Competition among ​Chinese video-model developers has ​intensified since ⁠ByteDance released Seedance 2.0 earlier this year, drawing widespread attention for its ability to produce sophisticated clips from combinations of ​text, images, audio and video. Its launch followed Kuaishou’s ​release ⁠of Kling 3.0.

MiniMax said H3 was aimed at commercial applications including advertising, e-commerce, product design and games. It said generating 2K video would cost less ⁠than one-third ​of mainstream rival products.

Amid a growing push in ​China’s AI sector to reduce its dependence on U.S. semiconductors, MiniMax said H3 was designed ​to work with several Chinese-made chips.