Sign In

anima-realism v1.1

30

Updated: May 23, 2026

stylerealism

Download

1 variant available

SafeTensor

87.6 MB

Verified:

Type

LoRA

Stats

107

0

Reviews

Published

May 23, 2026

Base Model

Anima

Hash

AutoV2
EF1C7201AC
default creator card background decoration
OMCCOM's Avatar

OMCCOM

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

anima-realism v1.1

This is a LoRA filter that applies a semi-realistic art style, no tagging is required.

This time, to match Anima Base 1.0, I changed the training resolution to 1024x1024 and retrained the model.

Since I disabled TextEncoder training, it may work with applications other than ComfuUI.

I used teacher images with faces that were as flat and anime-like as possible, but I haven't experimented with many characters yet, so the effect is unknown.

Increasing the weight will result in a softer overall touch.

It's recommended to apply it within the range of +0.25 to +0.45 and avoid setting the weight too high.

セミリアル画風を適用するLoRAです、タグの付与は必要ありません。

今回はAnima Base 1.0に合せて、学習解像度を1024x1024に変更し再学習しました。

TextEncoder学習を切ったのでComfuUI以外でも動作するかもしれません。

顔はなるべくフラットなアニメ調にした教師画像を使用しましたが、まだ多数のキャラクターで実験していないので効果は不明です。

ウェイトを高めにすると全体的に柔らかいタッチになります。

+0.25~+0.45の範囲で適用し余りウェイトを高くしない事をオススメします。

Notes:

Since the teacher images tend to be biased towards characters with animal ears, animal ears may appear unintentionally.

If this happens frequently, please comment so I can remake the teacher images.

Since anima-realism v1.0 was trained with Anima base Preview3, I retrained it with Anima base v1.0.

教師画像がケモ耳キャラに偏っているので、意図せず動物耳が出現するかもしれません。

頻発する様であれば教師画像を作り直すのでコメントを下さい。

anima-realism v1.0はAnima base Preview3で学習してしまった為、Anima base v1.0で学習し直しました。