From da9209a6776aa8b091476ea110cc4761008f0b8a Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Fri, 9 May 2025 23:19:16 +0200 Subject: [PATCH] Update sampler_explaination.md --- sampler_explaination.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sampler_explaination.md b/sampler_explaination.md index 1c863ff..f857abc 100644 --- a/sampler_explaination.md +++ b/sampler_explaination.md @@ -4,6 +4,14 @@ I recommand to have the code on the side to follow. +But in short: + +Similarily to Heun's method or some other samplers, this sampler uses the last prediction to re-compute a new one. + +Here it loops and in each iteration uses the distances in between each values to create a new result. + +The new result is made from a weighted average (or a slerp using the same weights) where the weights are related to the proportions of proximity. + --- The fast\_distance\_weights function calculates weights for a batch of tensors based on their pairwise distances in a normalized space.