Minimax H3 Ref2Vid model runs locally
Users are running the Minimax H3 Ref2Vid model locally for video generation. A 10-second, 1920-resolution generation takes approximately 28 minutes on an RTX PRO 6000 GPU.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Brad Lightcap, OpenAI's longtime COO, is leaving to 'start something new'
- General Catalyst leads $1.1B round into 2-month-old River AI
- Grok Bot praised for local/cloud agent fleet integration
- BlackRock CEO Larry Fink calls for $500 billion in AI infrastructure funding
- PlusAI reports progress toward 2027 autonomous truck deployments