Sign In

soumen / そうめん / 素麺 / ひやむぎ / 冷麦 / 冷やしうどん

201

Updated: Jul 23, 2026

posesfoodsummernoodlesjapan

Download

1 variant available

bf16 SafeTensor

soumen_anima_v1.safetensors

BF16, good balance • 87.6 MB

Verified:

Type
LoRA
Stats

221

53

84

Reviews
Published

Jul 23, 2026

Base Model

Anima

Usage Tips
Strength: 0.8
Hash
AutoV2
9EE3FDBFA2
Trigger Words
soumen
default creator card background decoration
Followers - 7517

7.5K

Likes - 80276

80.3K

Downloads - 586442

586.4K

mesugaki / メスガキ

License:

Anima

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

01908-1969876830.png

The English description is translated below the Japanese one at DeepL.

日本の夏に食べられるそうめんのLoRAです。

トリガーワードは soumen です。

重みは0.8前後推奨。

トリガーだけでも一応出ますが holding chopsticks, food, table, eating, holding bowl, sitting, noodles, summer 辺りから必要な物を入れていただくとそれっぽくなると思います。

Anima版はAnima_base Version1をベースとして学習していますので他のAnimaマージモデルでも使用できる可能性はありますが検証は行っておりません。

Illustrious版はIllustrious-XL 0.1をベースとして学習していますので他のIllustriousマージモデルやNoobマージモデルでも使用できる可能性はありますが検証は行っておりません。

Animagine XL 3.1をベースとして学習していますが3.0でも動作は確認しています。それ以外のXLモデルでは正常に機能しない可能性があります。

以下翻訳

This is LoRA for somen noodles eaten in Japan during summer.

The trigger word is “soumen.”

A weight of around 0.8 is recommended.

The trigger alone will produce results, but adding necessary items such as “holding chopsticks,” “food,” “table,” “eating,” “holding bowl,” “sitting,” “noodles,” and “summer” will produce more realistic results.

The Anima version was trained using Anima_base Version 1 as a base, so it may be usable with other Anima merge models, though this has not been verified.

The Illustrious version is trained based on Illustrious-XL 0.1, so it may be usable with other Illustrious merge models or Noob merge models, but this has not been verified.

It is trained based on Animagine XL 3.1, but functionality has been confirmed with version 3.0. It may not function properly with other XL models.