From 5eb6d209d5b28d43bf611e0934297703eb041d07 Mon Sep 17 00:00:00 2001 From: Dango233 Date: Thu, 7 Nov 2024 20:33:31 +0800 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 9273fc8f..fe7c506c 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ Nov 7, 2024: - The distribution of timesteps during SD3/3.5 training has been adjusted. This applies to both fine-tuning and LoRA training. PR [#1768](https://github.com/kohya-ss/sd-scripts/pull/1768) Thanks to Dango233! - Previously, the side closer to noise was more sampled, but now it is uniform by default. This may improve the problem of difficulty in learning details. - Specifically, the problem of double shifting has been fixed. The default for `--weighting_scheme` has been changed to `uniform` (the previous default was `logit_normal`). - - A new option `--training_shift` has been added. The default is 1.0, and all timesteps are sampled uniformly. If less than 1.0, the side closer to the image is more sampled, and if more than 1.0, the side closer to noise is more sampled. + - A new option `--training_shift` has been added. The default is 1.0, and all timesteps are sampled uniformly. If less than 1.0, the side closer to the image is more sampled (training more on image details), and if more than 1.0, the side closer to noise is more sampled (training more on overall structure). - The effect of a shift in uniform distribution is shown in the figure below. - ![Figure_1](https://github.com/user-attachments/assets/99a72c67-adfb-4440-81d4-a718985ff350)