MiniMax H3 Max hits fal: 15-second video generated in just 15 seconds
Hailuo_AI · x · 2026-08-27
A Japanese creator benchmarked MiniMax H3 Max (text-to-video) on fal:
- Speed: a 15-second clip rendered in 15 seconds; near-zero wait makes "tweak prompt → regenerate" loops effortless — the author argues this iteration speed matters more than quality
- Pricing: $0.04/second (90 JPY per 15s clip); 50% discount ends Sept 1
- Capabilities: audio support, prompts up to 7,000 characters
- Limit: max 768p resolution (2K/4K only on the regular H3), so upscaling is assumed
He also notes it can be mass-produced via the API from Claude Code, with more tests coming.
Related event: fal's H3 Max: Post-trained MiniMax H3 Tops Image-to-Video Leaderboards(29 posts)→
More from Multimodal
- Priming Models: Teacher-Free One-Step Generation Hits FID 1.19 With 12x Less Compute — du_yilun · 2026-10-15
- Same prompt, three takes: Claude vs ChatGPT vs Figma Make UI showdown — Tegadesigns · 2026-10-15
- Designer finds Opus 5.5 picks up nuanced aesthetic taste with startling speed — floguo · 2026-10-15
- The math: 5 rerolls at 480p plus a 4K upscale costs $5 vs $9 at 720p — HeyAmit_ · 2026-10-15
- Dreamina workflow: generate at 480p, upscale to 4K, cut video costs 44% — HeyAmit_ · 2026-10-15
- One-prompt GPT-6 Astra writes two Palestrina-style motets in LilyPond — deanwball · 2026-10-15