updates Seia LoRA to v1b

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

seia/README.md

@@ -1,7 +1,7 @@
 # Yurizono Seia (Blue Archive)
 百合園セイア (ブルーアーカイブ) / 유리조노 세이아 (블루 아카이브) / 百合園圣娅 (蔚藍檔案)
 
-[**Download here.**](https://huggingface.co/khanon/lora-training/blob/main/seia/chara-seia-v1.safetensors)
+[**Download here.**](https://huggingface.co/khanon/lora-training/blob/main/seia/chara-seia-v1b.safetensors)
 
 ## Table of Contents
 - [Preview](#preview)
@@ -11,8 +11,8 @@
 
 ## Preview
 ![Seia portrait](chara-seia-v1.png)
-![Seia preview 1](example-001-DefmixRed-v1.png)
-![Seia preview 2](example-003-DefmixRed-v1.png)
+![Seia preview 1](example-001-DefmixRed-v1b.png)
+![Seia preview 2](example-003-DefmixRed-v1b.png)
 
 ## Usage
 Use any or all of the following tags to summon Arona: `seia, 1girl, fox ears, parted bangs, halo, multicolored eyes, flower wreath, blonde hair`
@@ -37,10 +37,19 @@ For her expressions: `expressionless` / `light smile` / `parted lips`
 - 1.5e-4 unet LR
 - 1e-5 optimizer LR
 - Used network_dimension 128 (same as usual) / network alpha 128 (default)
+  - Resized to 32 after training
 - Training resolution 832x832.
 - Trained without VAE.
 - [Dataset can be found on the mega.co.nz repository.](https://mega.nz/folder/SupXFCiC#C992OYnVa8svZt3PdUObww)
 
 ## Revisions
+- v1b (2023-02-12)
+  - Resized v1 from network rank 128 >>> 32. This has no negative impact on image quality/coherency, and provides these advantages:
+    - Reduced LoRA file size from 144mb to 36mb
+    - Slightly reduced overfitting on training data
+      - Less darkening/vignetting of backgrounds
+      - Improved color saturation
+      - Halo is a bit more consistent
+      - Seia's hair gets confused with details on her clothing less frequently
 - v1 (2023-02-12)
   - Initial release.