ベースモデルはバージョン名参照
約9000枚の画像を解像度1536(--max_bucket_reso 1728)で追加学習
推奨設定はサンプル画像内蔵のワークフロー参照
preview3-v0.26について
preview3-v0.22で画風安定のために最後にマージしていたLoraが構図の破綻率を上げていたっぽいので修正
Description
FAQ
Comments (2)
Were there additional artists added with this finetune? What was the focus?
I focused on high-resolution output and overall stability. I didn’t add any particular artist styles or characters. I prefer to use LoRAs for artist styles and characters, so I tune the base model to stay as neutral and unobtrusive as possible.