🥈 Rob Cheung’s Parallel Video Control Net edits videos at top speed by running inference pipelines in parallel with serverless GPUs and video preprocessors.

Instead of taking 4 minutes to edit a 30-second video using prompts, this does it in just 5 seconds.

See it in action: pic.twitter.com/3uWMUjXIM2

— Replit ⠕ (@Replit) 12 mai 2023

Rob Cheung’s Parallel Control Net edits videos at top speed by running inference pipelines in parallel with serverless GPUs and video preprocessors. Instead of taking 4 minutes to edit a 30-second video using prompts, this does it in just 5 seconds. See it in action:

→ View original post on X — @replit