Update README.md

README.md

@@ -1,8 +1,8 @@
-The relationship between every version is not a version upgrade, but rather a difference in face shapes and styles.
+**The relationship between every version is not a version upgrade, but rather a difference in face shapes and styles.**
 
-各版本之间并非版本升级关系，而是不同脸型和风格的差异。
+**各版本之间并非版本升级关系，而是不同脸型和风格的差异。**
 
-各バージョンの関係はバージョンアップではなく、顔の形や雰囲気の違いです。
+**各バージョンの関係はバージョンアップではなく、顔の形や雰囲気の違いです。**
 
 ![version compare](lora-compare-v0.1-v0.2-v0.3.png)
 
@@ -13,7 +13,7 @@ v0.3 uses a different dataset from my unpublished SD2.1 768 model. It's not stri
 
 This LoRa produces better Asian beauties with unique film-like tones and natural backgrounds.
 
-Recommended weight: 0.7-1.0. Suggested settings: model weight 0.8, clip weight 0.4.
+Recommended **weight: 0.7-1.0**. Suggested settings: **model weight 0.8, clip weight 0.4**.
 
 Trigger words: Asian young woman, Japanese young woman, Chinese young woman.