Sign In

Coria style

2

Updated: Nov 19, 2026

style

Recently loaded

Download

1 variant available

bf16 SafeTensor

coria_style_anima_3444175_epoch_13.safetensors

BF16, good balance • 132.24 MB

Verified:

Type
LoRA
Stats

96

2

Reviews
Published

Nov 19, 2026

Base Model
Training
Steps: 1,950Epochs: 13
Hash
AutoV2855B0C12BC

The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. 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_00062111_.png

🎨 Coria Style LoRA

🌐 Base Model / 训练底模: Anima Base 1.0

🔑 Trigger Word / 触发词: @c0r1a

📝 Description / 简介

[ZH] 这是一个基于画师 Coria 画风训练的 LoRA 模型。

[EN] This is a style LoRA based on the artwork of the artist Coria.

✨ Features / 特点

[ZH]

  • 出色的视觉特效: 在模仿画师标志性的色差(Chromatic Aberration)效果上表现非常优秀。

  • 易于出图: 本模型极易上手,封面的所有示例图均由非常简单的提示词生成,无需堆砌复杂的长句即可获得极具张力的画面。

[EN]

  • Great Visual Effects: It performs exceptionally well at replicating the artist's signature chromatic aberration effect.

  • Easy to Prompt: Very beginner-friendly. All the cover and showcase images were generated using extremely simple prompts. You don't need complex prompt engineering to get highly expressive results.

⚠️ Known Issues & Tips / 已知问题与建议

[ZH] 手部生成偶尔会不稳定,可能会出现指头数量错误,或者人物手里拿着意义不明的物体。 💡 建议: 建议主要依靠提示词来进行规避。可以在负面提示词中加入 bad hands, missing fingers, extra fingers 等,或在正面提示词中明确手部动作(如 hands in pockets, arms crossed 等)。

[EN] Hand generation can sometimes be inconsistent, occasionally resulting in an incorrect number of fingers or characters holding meaningless objects. 💡 Tips: It is highly recommended to rely on prompts to mitigate this issue. You can add terms like bad hands, missing fingers, extra fingers to your negative prompts, or specify clear hand poses in your positive prompts (e.g., hands in pockets, arms crossed).

💬 Creator's Note / 作者的话

[ZH] 顺便在评论区向各位大佬请教一个问题:如果有人知道为什么 Anima 的画风 LoRA 不仅不会过拟合,反而会越炼越“欠拟合”,请一定告诉我,非常感谢!

[EN] A quick question for the community: If anyone knows why style LoRAs trained on the Anima base model don't overfit, but instead seem to get more underfitted the longer you train them, please let me know in the comments. Any insights would be greatly appreciated! Thanks!