MiniMax releases H3 video generation model with open weights
The 33B parameter H3 model supports text-to-video, image-to-video, and video editing with native stereo audio and 2K resolution. It features Day 0 support in ComfyUI and vLLM-Omni, with community-built distillations reducing sampling steps to 4–8.
How this story unfolded
9 days · 2 reports · 142 community posts · 144 of 150 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 6
- Aug 7
- Aug 8
- Aug 9
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- Mollick: ChatGPT Work, Claude Cowork should explain choices like a PM
- Deedy Das: AI-written prose can evade detection
- Podcast discusses the risks of AI-driven team velocity
- Alex Kantrowitz examines why Big Tech is falling behind in AI
- Stanford researchers change how AI agents access files