88Z AI, 31 July — LibTV and MiniMax have jointly released the new multimodal video model MiniMax H3, which supports 5 to 15-second video generation, 24 FPS output, and native dual-channel audio. The model features unified understanding of text, images, audio, and video, enabling an integrated creation workflow from reference materials to final editing, targeting commercial scenarios such as short dramas, advertising, and film production.
At a glance
- Supports 5-15 second video generation, 24 FPS output, and native dual-channel audio
- Features unified understanding of text, image, audio, and video for commercial scenarios like short dramas and ads
The update
LibTV has partnered with MiniMax to officially launch the new general multimodal generation model, MiniMax H3. This model achieves significant technical breakthroughs, capable of generating high-quality video clips ranging from 5 to 15 seconds in length. It supports standard 24 FPS output and native dual-channel audio synthesis, ensuring the integrity and fluidity of the audiovisual experience. In terms of core capabilities, MiniMax H3 possesses a unified understanding of text, images, audio, and video. This feature enables users to achieve an integrated creation process from reference materials to final edited videos, greatly simplifying the workflow. The model is primarily targeted at professional commercial scenarios such as short drama production, commercial advertising, and film creation, aiming to provide efficient and high-quality video generation solutions.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 哩布哩布AISource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.