Update README.md

2024-02-14 15:17:58 +01:00
parent 748d1a8ff0
commit 5503505926
1 changed files with 2 additions and 0 deletions
@@ -9,6 +9,8 @@ The CFG behavior during the sampling being automatically set for each channel ma
 From my observations by printing the results while testing, it seems to be going from around 16 at the beginning, to something like 4 near the middle and ends up near ~7. 
 These values might have changed since I've done a thousand tests with different ways but that's to give you an idea, it's just me eyeballing the CLI's output.

+I use the upper and lower 25% topk mean value as a reference to have some margin of manoeuver.
+
 It makes the sampling generate overall better quality images. I get much less if not any artifacts anymore and my more creative prompts also tends to give more random, in a good way, different results.

 I attribute this more random yet positive behavior to the fact that it seems to be starting high and then since it becomes lower, it self-corrects and improvise, taking advantage of the sampling process a lot more.