Updated: Aug 18, 2026
styleDownload
1 variant available
bf16 SafeTensor
far off in the morning haze024064645510a_30.safetensors
BF16, good balance • 175.12 MB
Verified: 2 months ago
3690 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1850 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1350 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(39)
Jul 19, 2026

2.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
21.4K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
AnimaThe 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
About Anima v1.0~
强度:0.5-1
这是一个风格lora,主要作用是让人物风格更具有2.5D渲染风格,同时让画面表现更加平滑和柔和,配合场景光线,经常会达到朦胧美的效果,适用于各类场景表达,但尤其适用于中近景构图。
已知问题:
如果将生成的图片放大看,会发现线条有明显的锯齿感,这是训练素材所固有的;
和基础模型原生的画师风格兼容性不高,会完全掩盖住画师风格(有特殊体型风格的除外),将权重降低至0.5,可能会有一些改善;
---
Strength: 0.5–1
This is a style LoRA. It mainly makes characters look more 2.5D rendered, while making the overall image smoother and softer. Combined with scene lighting, it often creates a dreamy, hazy beauty effect. Works for all kinds of scenes, but especially shines in mid-shot and close-up compositions.
Known Issues:
If you zoom in on the generated image, you'll notice jagged edges on the lines — this is baked into the training data.
It doesn't mix well with the base model's native artist styles; it will completely override them (unless the artist has a very distinct body type style). Lowering the weight to 0.5 may help a bit.

