MiniMax H3 lands on Together AI: 33B omni-modal model generates 2K clips with native stereo audio
togethercompute · x · 2026-09-16
MiniMax's H3 video generation model is now live on Together AI. The 33B omni-modal model generates 4–15 second clips at up to 2K resolution with native stereo audio.
It accepts text, images, video, and audio as context, enabling multimodal reference-driven generation.
Related event: MiniMax H3 Omni-Modal Video Model Lands on Together AI(2 posts)→
More from Multimodal
- Midjourney wallpaper recipe: sref + profile mix for eerie film-blur portraits — michaelrabone · 2026-11-02
- Cavallaero Teaser: A Painterly Rider Races Through a Golden Forest — CommunicationTop4244 · 2026-11-02
- Anima's snapref Offers a New Reference-Based Fix for Character Consistency — Intrepid_Swim_8669 · 2026-11-02
- Pencil-textured folding fan: surreal product concept render goes viral — Delahuntagram · 2026-11-02
- Free Midjourney SREF gallery adds 1,200+ handpicked style codes overnight — tisch_eins · 2026-11-02
- Adobe's EditAgent beats prior image-editing agents but needs ~10x the compute — emmanuelvivier · 2026-11-02