From 86eba1d2cfad38a3ddb61d826787fd324e6d83d8 Mon Sep 17 00:00:00 2001
From: Kohya S <52813779+kohya-ss@users.noreply.github.com>
Date: Sun, 29 Jan 2023 21:23:05 +0900
Subject: [PATCH] Update README.md

---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index 70fdebf1..4497a3c2 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,11 @@ __Stable Diffusion web UI now seems to support LoRA trained by ``sd-scripts``.__
 
 Note: The LoRA models for SD 2.x is not supported too in Web UI.
 
+- 29 Jan. 2023, 2023/1/29
+  - Add ``--lr_scheduler_num_cycles`` and ``--lr_scheduler_power`` options for ``train_network.py`` for cosine_with_restarts and polynomial learning rate schedulers.
+  - Fixed U-Net ``sample_size`` parameter to ``64`` when converting from SD to Diffusers format, in ``convert_diffusers20_original_sd.py``
+  - ``--lr_scheduler_num_cycles`` と ``--lr_scheduler_power`` オプションを ``train_network.py`` に追加しました。前者は cosine_with_restarts、後者は polynomial の学習率スケジューラに有効です。
+  - ``convert_diffusers20_original_sd.py`` で SD 形式から Diffusers に変換するときの U-Net の ``sample_size`` パラメータを ``64`` に修正しました。
 - 26 Jan. 2023, 2023/1/26
   - Add Textual Inversion training. Documentation is [here](./train_ti_README-ja.md) (in Japanese.)
   - Textual Inversionの学習をサポートしました。ドキュメントは[こちら](./train_ti_README-ja.md)。