MiniMax releases H3 open-weights video generation model
MiniMax H3 features native stereo audio support and generates up to 15-second clips at 2K resolution. The model is currently ranked as the SOTA open video generation model on both the LMSYS Arena and Artificial Analysis benchmarks.
How this story unfolded
8 days · 12 reports · 131 community posts · 143 of 151 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 6
- Aug 7
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- CPUs and the rise of neurosymbolic AI
- Mollick asks for plan on cyber threats from open-weight Mythos/Astra models
- Dwarkesh Patel discusses the implications of continual learning for AI
- NoimosAI launches Social Agent, an AI research agent for social trends
- Stanford researchers deploy 37,000 AI agents as a virtual biotech