From 63db50c06af5e4fc0fc697400ad9ddfd79cd61d1 Mon Sep 17 00:00:00 2001
From: Bingsu <ks2515@naver.com>
Date: Fri, 5 May 2023 08:30:43 +0900
Subject: [PATCH] docs: changelog, install

---
 CHANGELOG.md | 31 +++++++++++++++++++++++++++++++
 README.md    | 41 ++++++++++++++---------------------------
 2 files changed, 45 insertions(+), 27 deletions(-)
 create mode 100644 CHANGELOG.md

diff --git a/CHANGELOG.md b/CHANGELOG.md
new file mode 100644
index 0000000..6bd3198
--- /dev/null
+++ b/CHANGELOG.md
@@ -0,0 +1,31 @@
+# Changelog
+
+### 2023-05-05 (어린이날)
+
+- v23.5.5
+- `Save images before ADetailer` 옵션 추가
+- 입력으로 들어온 인자와 ALL_ARGS의 길이가 다르면 에러메세지
+- README.md에 설치방법 추가
+
+### 2023-05-04
+
+- v23.5.4
+- use pydantic for arguments validation
+- revert: ad_model to `None` as default
+- revert: `__future__` imports
+- lazily import yolo and mediapipe
+
+### 2023-05-03
+
+- v23.5.3.post0
+- remove `__future__` imports
+- change to copy scripts and scripts args
+
+- v23.5.3.post1
+- change default ad_model from `None`
+
+### 2023-05-02
+
+- v23.5.3
+- Remove `None` from model list and add `Enable ADetailer` checkbox.
+- install.py `skip_install` fix.
diff --git a/README.md b/README.md
index 482368a..cb77f64 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,20 @@
 
 !After Detailer is a extension for stable diffusion webui, similar to Detection Detailer, except it uses ultralytics instead of the mmdet.
 
+## Install
+
+(from Mikubill/sd-webui-controlnet)
+
+1. Open "Extensions" tab.
+2. Open "Install from URL" tab in the tab.
+3. Enter `https://github.com/Bing-su/adetailer.git` to "URL for extension's git repository".
+4. Press "Install" button.
+5. Wait 5 seconds, and you will see the message "Installed into stable-diffusion-webui\extensions\adetailer. Use Installed tab to restart".
+6. Go to "Installed" tab, click "Check for updates", and then click "Apply and restart UI". (The next time you can also use this method to update extensions.)
+7. Completely restart A1111 webui including your terminal. (If you do not know what is a "terminal", you can reboot your computer: turn your computer off and turn it on again.)
+
+You **DON'T** need to download any model from huggingface.
+
 ## Model
 
 | Model                | Target              | mAP 50 | mAP 50-95 |
@@ -13,8 +27,6 @@
 
 The yolo models can be found on huggingface [Bingsu/adetailer](https://huggingface.co/Bingsu/adetailer).
 
-You DON'T need to download models from huggingface.
-
 ### Dataset
 
 Datasets used for training the yolo face detection models are:
@@ -40,28 +52,3 @@ On the ControlNet tab, select a ControlNet inpaint model and set the model weigh
 
 ![image](https://i.imgur.com/i74ukgi.png)
 ![image](https://i.imgur.com/I5VVkoh.png)
-
-## Changelog
-
-### 2023-05-04
-
-- v23.5.4
-- use pydantic for arguments validation
-- revert: ad_model to `None` as default
-- revert: `__future__` imports
-- lazily import yolo and mediapipe
-
-### 2023-05-03
-
-- v23.5.3.post0
-- remove `__future__` imports
-- change to copy scripts and scripts args
-
-- v23.5.3.post1
-- change default ad_model from `None`
-
-### 2023-05-02
-
-- v23.5.3
-- Remove `None` from model list and add `Enable ADetailer` checkbox.
-- install.py `skip_install` fix.