Update ADVANCED_TWEAKING.md

This commit is contained in:
Victor Hall 2023-11-21 14:07:21 -05:00 committed by GitHub
parent 051ecf57ad
commit 772d6bc439
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions

View File

@ -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.
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.