MiniMax H3 lands on Magnific: mix 9 images, 3 videos and 3 audio refs in one prompt
AIwithGhotai · x · 2026-08-20
MiniMax H3 is now available on Magnific. Key capabilities highlighted:
- Multimodal mixed input: a single prompt can combine text, images, video and audio — up to 9 images, 3 videos and 3 audio references.
- Generation: up to 15 seconds of 2K video with synchronized sound, including voice, music and effects.
- Editing: clip editing, object removal, motion transfer, plus control over camera, character and voice.
The author's favorite is the multi-reference workflow: hand over product, character, environment and motion references together, and H3 pulls everything into a finished video — a much easier path from idea to final cut.
More from Multimodal
- MLP-Splatting (ECCV 2026) code released: MLPs as light-field primitives instead of Gaussians — AjdDavison · 2026-10-16
- Digital human Fae codes her own facial expressions frame-by-frame with Claude Opus 5.5 and FACS — repligate · 2026-10-16
- Meta's Omnilingual ASR, covering 1,600 languages, named a TIME Best Invention of 2026 — AIatMeta · 2026-10-16
- ATAS: Zhejiang-led team builds world-state memory framework for consistent agentic video generation — CSProfKGD · 2026-10-16
- Flux 3 Klein's Default Templates Are Broken Without Its Prompt Upscaler — StrictMove5839 · 2026-10-16
- Kroma Touted as the Most Well-Rounded Image Model Yet on Civitai — Different_Fix_2217 · 2026-10-16