Sign In

anima-flat v1.2

21

Updated: May 29, 2026

styleflat

Download

1 variant available

SafeTensor

87.6 MB

Verified:

Type

LoRA

Stats

293

8

11

Reviews

Published

May 29, 2026

Base Model

Anima

Hash

AutoV2
5496C00823
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-flat v1.2

This is a LoRA slider similar to sdxl-flat, used to flatten the fill or increase the drawing density.

It has been retrained to coincide with the release of Anima Base V1.0. Since it no longer trains the TextEncoder, it should work with Forge Neo as well. Also, the training resolution has been changed from 512x512 to 1024x1024.

For flattening, a LoRA weight of around +0.25 to +0.75 is recommended.

For increasing density, a LoRA weight of around -0.25 to -0.75 is recommended.

sdxl-flatの様に塗りをフラットにしたり描画密度を上げるするスライダーLoRAです。

Anima Base V1.0のリリースに合せ再学習しました、今回からTextEncoderの学習は行っていないのでForge Neoでも使えると思います。また学習解像度を512x512から1024x1024に変更しています。

フラットしたい場合、LoRAのウェイトは+0.25~+0.75位が良いと思います。

密度を上げたい場合、LoRAのウェイトは-0.25~-0.75位が良いと思います。

Notes:

Please note that there will be some variation in style and composition; even with the same seed, the composition will not be exactly the same.

It doesn't seem to have as many problems as anima-sharpen v1.1, but we are visually checking for overfitting LoRA and selecting the best epoch to merge.

We've decided to introduce a fox character starting from this episode.

画風や構図に多少なりとも変化が加わります、同一シードであっても全く同一の構図にはならない点に注意して下さい。

anima-sharpen v1.1程問題は無い様子ですが、過学習LoRAを目視で確認しベストなエポックを選びマージしています。

今回からキツネさんに登場してもらう事にしました。