Sign In

anima-sharpen v1.1

0

Updated: May 25, 2026

sharpen

Download

1 variant available

SafeTensor

87.6 MB

Verified:

Type

LoRA

Stats

102

0

Reviews

Published

May 24, 2026

Base Model

Anima

Hash

AutoV2
E0D08B99FC
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-sharpen v1.1

This is a LoRA slider for adjusting sharpness.

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.

For sharper images, a LoRA weight of around +0.45 is recommended.

For blurred images, a LoRA weight of around -0.45 is recommended.

It seems to be working, but it might be a bit finicky with Anima Base v1.0.

Judging from the case of -0.75, the intention to affect only the subject may be achieved.

It is difficult to determine if this tendency exists at +0.75.

シャープネスを調整するスライダーLoRAです。

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。

シャープにしたい場合、LoRAのウェイトは+0.45位が良いと思います。

ボカしたい場合、LoRAのウェイトは-0.45位が良いと思います。

一応効いてはいる様ですが、Anima Base v1.0ではピーキーかもしれません。

-0.75の場合を見る限り、被写体のみに作用する目論見は実現しているかもしれません。

+0.75ではその傾向があるのか判断が難しいです。

Notes:

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

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。