Prune: Difference between revisions

From Civitai Wiki
Jump to navigation Jump to search
(Created page with "A method of optimizing a Checkpoint model to increase the speed of inference (prompt generation), file size, and VRAM cost.")
 
No edit summary
 
Line 1: Line 1:
A method of optimizing a Checkpoint model to increase the speed of inference (prompt generation), file size, and VRAM cost.
A method of optimizing a [[Checkpoint]] model to increase the speed of [[inference]], while reducing file size and [[VRAM]] cost.

Latest revision as of 15:05, 11 October 2023

A method of optimizing a Checkpoint model to increase the speed of inference, while reducing file size and VRAM cost.