Introducing H3 Max, new post-trained video model by fal Research.
H3 Max ranks #1 for overall quality, prompt understanding, and aesthetics against leading video models, on both first-party and third-party independent evaluations while generating a 5-second 720p video under 3
fal.live is back!
It now runs continuously, with LLM-generated prompts that anyone watching can upvote to decide what gets created next.
We’ve been experimenting with what faster-than-real-time AI models like H3 Max make possible for entirely new forms of content
Three weeks until our GenMedia Conference 2026.
It's happening on September 24 in San Francisco. Registration is closing soon, so apply for your spot.
We'll be announcing our speaker lineup very soon.
Reference-to-Video is now live for MiniMax H3 Max on fal!
This is an early preview that can achieve up to RTF=1 (and with references around RTF=1.5) on 768p, and we aim to improve the speed by 2x while slashing costs during this week. Quality wise it delivers the same
