Minimax has officially open-sourced its new-generation general-purpose video model, MiniMax H3. This multimodal generative system can process and generate content from text, images, video, and audio, producing videos up to 2K resolution and 15 seconds in length, complete with stereo audio. The announcement was made during an event where China Securities Regulatory Commission Chairman Wu Qing discussed enhanced regulatory collaboration with Hong Kong authorities. AI
IMPACT This open-source release of a multimodal video generation model could accelerate research and development in AI-powered video creation and understanding.
RANK_REASON The item describes the open-sourcing of a new AI model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
