fal ships H3 Max, generating five-second videos in roughly three seconds

The post-trained MiniMax H3 variant pairs fal's model research with its serving stack to generate five-second videos in roughly three seconds.

By · Published · Updated

Primary source: PR Newswire

Why it matters

Gur and Yurtseven are moving fal up the stack from hosting other labs' models to modifying weights and serving systems together. H3 Max tests whether model-specific optimization can give a generative-media platform an edge over broader inference providers and better-funded video labs.

A tiny figure views a fast-playing, five-second video on a smartphone, representing fal's H3 Max model, against a vast, muted urban landscape.

Burkay Gur and Gorkem Yurtseven, the co-founders of San Francisco-based fal, released H3 Max on September 1st, pushing their generative media platform beyond hosting other labs' models and deeper into developing the systems that determine how those models perform.…

Reader comments

Conversation for this story loads after sign-in.