Update README.md

README.md

@@ -79,6 +79,6 @@ The goal of this prompting strategy is to make sure the artists distribution of
 
 As we compare the outputs of the models directly, and not to an absolute expected epsilon noise map, this asymmetric prompting strategy does not affect too much the quality of accumulated gradients.
 
-The merge uses a value for lambda that gives equal weight to both models. The gradients of Animagine are on average larger than those of NoobAI, so we need to tweak lambda if we want a merge that includes a proportional amount of parameters from both models. I am not aware of a closed form solution for lambda, so I used bisecting until the proportion of parameters was about 0.5.
+The merge uses a value for lambda that gives equal weight to both models. The gradients of Animagine are on average larger than those of NoobAI, so we need to tweak lambda if we want a merge that includes a proportional amount of parameters from both models. I am not aware of a closed form solution for lambda, so I used a bisecting algorithm to estimate it to a reasonable precision.
 
 This gave a value of lambda = 0.224609, which corresponds to the "DeadCenter" version. Another opiniated value of lambda that I found aesthetically pleasing with some artist tags is lambda = 0.3564453125 (more a random value than an optimized one), which corresponds to the "MadHatter" version.