A LoRA specializing in flat color, no lineart, deformed character art.

Since this LoRA is made from a lossy differences from Fwaun Tune, I recommend using these fine-tuned models unless there is a specific reason to use LoRA.
For details on each version, please refer to the release note of original fine-tuned model.

フラットカラー・主線なし、（ちびというほどではない）デフォルメ画風を学習させたLoRAです。

このLoRAは Fwaun Tune のロッシーな差分から作られているので、特段の理由がなければファインチューンモデルのほうの利用を推奨します。

各バージョンの詳細は対応するオリジナルのファインチューンモデルのリリースノートをご確認ください。

Changelog

Krea2 v5.0

モノクロと写実的な背景を出せるようになりました。
データセットやトレーニング時のパラメータについての詳細はこちら（Fanbox）。

You can now produce monochrome and realistic backgrounds.
For more details on the dataset and training parameters, click here (Patreon).

Anima v5.1

I thought it might be overfitting, so I lowered the learning rate.

過学習っぽい気がしたので学習率を下げました。

Anima v5.0

You can now produce monochrome and realistic backgrounds.

モノクロと写実的な背景を出せるようになりました。

About Anima V4.0 / Krea2 v2.0 and Later

Starting with this version, I have decided to create these LoRAs by extracting the differences between the fine-tuned model and the base model.

このバージョンから、このLoRAは対応するファインチューンモデルのベースモデルとの差分を抽出して作成するようになりました。

Before v3.x

It uses the same dataset as Fwaun Anima and Fwaun Krea2.

Unless there is a specific reason to use LORA, I recommend using Fwaun Anima and Fwaun Krea2. instead of this LORA model.

v3.1 krea2

• First lora for krea2.

• Dataset images are not changed but captions are updated for training krea2.

• Please place the trigger word at the end like comfyUI's official template.

• Compared to the Anima model, the stylization is less deformed.

• The "stylized proportion" tag falls between "realistic" and "chibi"

v3.0

To help body proportions, I’ve added super deformed, chibi-style illustrations to the training data.

You can decrease the body-to-head ratio using the “chibi, super deformed” tags and you can also use "realistic" tag to increase it.

Trigger word

flat color, no lineart, deformed

Optional tags

chibi, super deformed

realistic

v2.0

To help adjust color tones and body proportions, I’ve added non-deformed flat color no lineart illustrations to the training data.

You can increase the body-to-head ratio using the “realistic” tag. If you don't want to increase it, set it to a negative value.

Trigger word

flat color, no lineart, deformed

Negative word

chibi, realistic