FastH3 Preview v0.1: Four open-weight H3 models cut transformer calls to four
FastVideo released four FastH3 Preview v0.1 checkpoints that reduce MiniMax H3 from 49 transformer calls to four, generating 768p video with 32 kHz stereo audio. Variants explore prompt-only and synthetic-video training, plus sparse and dense attention. Fast motion and fine audio remain weaker than Base H3; first/last-frame and reference workflows are unsupported.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Uber builds uReview, a multi-agent code review engine
- Mistral shows how to build HTML5 games with agents
- YouTube restricts views of AI music, Suno users report
- Defining an AI Kill Switch Is Hard, But Necessary
- AI-driven hiring freeze leaves job seekers rejected