MiniMax's H3Max Generates 5-Second Videos in Under 3 Seconds, Sparking AI Livestream Wave
量子位 · wechat · 2026-08-31
MiniMax partnered with inference acceleration firm fal to launch H3Max, building on the open-source video model H3 (24M downloads in three weeks) with post-training and inference optimization for real-time generation: a 5-second 768p video takes under 3 seconds, with roughly 35x the throughput of H3, while ranking #1 in image-to-video on both ArtificialAnalysis and DesignArena.
Faster-than-playback generation unlocked a new category: within a week, three independent AI livestreams appeared — fal engineer Rehan Sheikh's "transdimensional TV" (5.4M views on X), Pieter Levels' on-demand livestream site, and another fal engineer's interactive continuous-story stream steered by viewer chat commands.
The author's hands-on test: a complex 5-second video took 7 seconds end-to-end via API (including queueing and 1s polling); MiniMax Design generated a 5-scene earbuds ad. H3Max currently caps at 768p with first/last-frame reference only (no subject reference), but finishes clips in 20 seconds that take H3 5 minutes. The piece argues real-time AI video is a watershed for the field, with open-source ecosystem lock-in; Morgan Stanley kept an Overweight rating (target HK$900) and the stock rose 16.18%.
Related event: MiniMax H3 Max Generates Video Faster Than Real Time(22 posts)→
More from Multimodal
- VideoGen-Agent: An 8B Multimodal Agent Turns Video Generation Into a Tool-Use Loop — jiqizhixin · 2026-10-16
- Drama-3 weights land on the Hugging Face Hub with an official demo — Gradio · 2026-10-16
- MiniCPM-V 4.5 offer open-source local image understanding to replace paid vision APIs — heyshrutimishra · 2026-10-16
- Surreal AI-generated landscape hides "another landscape inside the measurements" — piotrbinkowski · 2026-10-16
- techhalla: Building 3D scenes in Blender is the key to AI filmmaking — techhalla · 2026-10-16
- Fan animation made in Blender with Claude Code (Opus 5.5) — Icy-Appointment3583 · 2026-10-16