MiniMax H3 Max sets new video generation speed frontier, 24x faster
JenniferHli · x · 2026-08-29
The MiniMax H3 Max model, fine-tuned by fal on the MiniMaxAI H3 base, sets a new Pareto frontier in video generation. It achieves an Image-to-Video generation time of just 6.4 seconds (18x faster than average) and Text-to-Video in 4.7 seconds (24x faster), delivering higher user preference at significantly lower latency on the arena.
Related event: MiniMax H3 Max Hands-on: Video Generation Nearing Real-Time Speeds(7 posts)→
More from Infra
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16
- Shadeform to Announce Six New Features on Oct 19: Lower GPU Costs, More Suppliers — _jaydeepkarale · 2026-10-16
- Fastino launches Training API for SFT/RL, claiming 25-85% cost cut vs Tinker — kalyan_kpl · 2026-10-16