v001 スクリプトのテスト

アップデートしてsqlデータベースから非推奨タグを推奨タグに置き換える処理を追加

その後dataset tag edditerで重複タグの削除とトリガー｢shiromuku｣とだけ追加して学習

画像から余計な情報のクリーンナップとかもやってない

v002

既存タグに対してクリーンナップしたタグを追加してたので修正したスクリプトを使用

タグが大文字･小文字混在なのを全て小文字に統一

asian､ Chinese､ korean など文化圏を判別できてないタグの手動削除

sd-script/dev の '--alpha_mask' を使用

トリガーを 'shiromuku, 白無垢'へ､'japanese clothing'を'kimono'へ変更

手動でタグ整理､とても手間な割には出来が満足とも言えない

角隠しを理解させようとその画像を増やしたが学ばない

Seasonal for June

This time, it's the traditional Japanese bridal attire, Shiromuku.

There is no distinction between tsunokakushi and wataboshi, and as usual, v001 tends to distort the face.

Image preprocessing script

Updated to include a process that replaces deprecated tags with recommended tags from the SQL database.

After that, duplicate tags were removed using the dataset tag editor, and only the trigger "shiromuku" was added for training.

No cleanup of unnecessary information from the images was done either.

Added cleaned-up tags to existing tags, using a corrected script.

Unified tags to lowercase as they were mixed case.

Manually removed tags like "asian", "Chinese", "korean" which could not distinguish cultural regions.

Used --alpha_mask from sd-script/dev.

Changed trigger from "shiromuku, 白無垢" to "shiromuku" and "japanese clothing" to "kimono".

Manually organized tags; despite the effort, the results are unsatisfactory.

Increased images to make the model understand "角隠し" (horn concealing headdress), but it did not learn.