From 772d6bc439c6fb24d969e14ed31c614f8f07530e Mon Sep 17 00:00:00 2001 From: Victor Hall Date: Tue, 21 Nov 2023 14:07:21 -0500 Subject: [PATCH] Update ADVANCED_TWEAKING.md --- doc/ADVANCED_TWEAKING.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/ADVANCED_TWEAKING.md b/doc/ADVANCED_TWEAKING.md index b248fe9..61c3e23 100644 --- a/doc/ADVANCED_TWEAKING.md +++ b/doc/ADVANCED_TWEAKING.md @@ -2,7 +2,7 @@ This document is a bit more geared to experienced users who have trained several models. It is not required reading for new users. -Start with the [Low VRAM guide](TWEAKING.md) if you are having trouble training on a 12GB card. +Start with the [Low VRAM guide](VRAM.md) if you are having trouble training on a 12GB card. ## Resolution @@ -284,4 +284,4 @@ This is an optimizer made by stripping out non functional components of Coordina This is an implementation of pyramid noise as first introduced here https://wandb.ai/johnowhitaker/multires_noise/reports/Multi-Resolution-Noise-for-Diffusion-Model-Training--VmlldzozNjYyOTU2 -Pyramid noise can be used to improve dynamic range in short finetunes of < 2000 steps at discounts greater than 0.40. At all discount levels pyramid noise appears to improve the amount of detail generated in images. However, it is not advised to train with pyramid noise for a full training as the noise affects the whole model rapidly and can destabilize the model if trained for too many steps. At 0, pyramid noise is disabled. \ No newline at end of file +Pyramid noise can be used to improve dynamic range in short finetunes of < 2000 steps at discounts greater than 0.40. At all discount levels pyramid noise appears to improve the amount of detail generated in images. However, it is not advised to train with pyramid noise for a full training as the noise affects the whole model rapidly and can destabilize the model if trained for too many steps. At 0, pyramid noise is disabled.