Using a latent consistency model for video2video is fast, but it needs control mechanisms.

The speed means you can do high frame rate video conversions. But the lack of control makes it a mess.

180 frames in 55 seconds:https://t.co/Y13KKTdAtp pic.twitter.com/CMaWM62C9A

— fofr (@fofrAI) 28 octobre 2023

Using a latent consistency model for video2video is fast, but it needs control mechanisms. The speed means you can do high frame rate video conversions. But the lack of control makes it a mess. 180 frames in 55 seconds: https://
replicate.com/p/qavcahlbjto6
6zcoq3eyubaclu
…

→ View original post on X — @fofrai