MiniMax launches H3, open-weights omni-modal video generator
MiniMax H3 generates video with native stereo audio at up to 2K resolution and 15-second durations, released as open weights on Hugging Face. The system uses three modules: H3-Context-IR, H3-Base for 768p generation, and H3-Regenerate-2K for 2K upscaling. Day 0 support spans LMSYS, NVIDIA and AMD hardware, and Vercel AI Gateway.
How this story unfolded
3 weeks · 10 reports · 128 community posts · 138 of 150 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 6
- Aug 7
- Aug 8
- Aug 9
- Aug 10
- Aug 11
- Aug 12
- Aug 13
- Aug 14
- Aug 16
- Aug 19
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- NVIDIA demos local Hermes agent debugging with RTX Spark
- NVIDIA explains omni-models: unified text, image, audio, video
- Anthropic Plans to Change Data Retention Policy for Advanced AI
- ATDev updates progress on autonomous wheelchair with robotic arm
- Claude Code demo generates full MP4 videos with Qwen3-TTS and FLUX.2