Update README.md

README.md

@@ -9,7 +9,7 @@ Naively applying the formulas from the paper gave poor results when trying to ad
 The goal is to estimate which parameters of each model are very important and which parameters are less important. The way I did this was by first computing gradients with respect to this objective:
 
 $$
-L = E_{x \sim p(x), t \propto \frac{1}{snr_t}} \big[\frac{L_0(x, t)}{C(x, t)}\big]
+L = E_{x \sim p(x), t \propto \frac{1}{snr_t^2}} \big[\frac{L_0(x, t)}{C(x, t)}\big]
 $$
 
 where L_0 expresses what we are trying to optimize (A corresponds to NoobAI, B corresponds to Animagine):
@@ -30,7 +30,7 @@ x_t and snr_t were taken from the DDPM paper (https://arxiv.org/abs/2006.11239):
 
 $$
 x_t = \sqrt{\bar{\alpha}_t} x + \sqrt{1 - \bar{\alpha}_t} \epsilon \\
-snr_t = \frac{\bar{\alpha}_t}{1 - \bar{\alpha}_t}
+snr_t = \frac{\sqrt{\bar{\alpha}_t}}{\sqrt{1 - \bar{\alpha}_t}}
 $$
 
 It's important to note that L is not used to train any model here. Instead, we accumulate absolute gradients to estimate the importance of each parameter (explained below):