fal's H3 Max: RL post-training cuts 5s video generation from 120s to under 3s

isidentical · x · 2026-09-16

fal Research launched H3 Max, a post-trained video model claiming #1 in overall quality, prompt understanding, and aesthetics against leading video models on first- and third-party evals, while generating a 5-second 720p video in under 3 seconds (50% off for a week).

Head of engineering isidentical explained the approach at MTS:

A notable release for anyone tracking real-time video generation.

Original post →

More from Multimodal

Multimodal channel →