forecast

Video generation inference is becoming cheaper

Video inference is currently inefficient, but distillation now lets models produce output in a few diffusion steps instead of about a hundred, and efficiency could improve by roughly an order of magnitude.

forecastpending

Speaker

Gaurav Misra

Evidence Quote

“We don’t need to do a hundred steps of diffusion for inference... It could be a factor of at least an order of magnitude, like 10x or something.”

Source

Gaurav Misra & Dwight Churchill - Building Captions - [Invest Like the Best, EP.405]— Invest Like the Best
Created: 11/12/2026, 5:01:35 AM

Your notes

Loading notes...