Not loaded
Download
1 variant available
bf16 SafeTensor
anima_yuming_li_style-v2.safetensors
BF16, good balance • 132.24 MB
Verified: 2 days ago
14
53
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
This LoRA was trained on a set of 87 curated images of the artist Yuming Li, with both booru-style tags and natural language.
A style LoRA for soft, painterly fantasy illustrations with expressive brushwork, deep shadows, and luminous color.
The training set includes portraits, fantasy characters, angels, animals, and a few wider scenes. Many images use violet and blue shadows with warm highlights, but the style can also work with brighter colors when prompted.
Base model: Anima Base v1.0
Trigger: @yumingli
Starting LoRA strength: 0.6
I would recommend you to start with 0.6, you can bump it up to like 1.0 with the right conditions (quality tags).
For a stronger style effect, I trained it with additional style tags, try adding:
painterly, soft brushwork, dramatic lighting,
Example prompt:masterpiece, best quality, score_9, score_8, score_7, year 2025, newest, highres, absurdres, very aesthetic,
@yumingli, painterly, soft brushwork, dramatic lighting,
1girl, dark-skinned female, long purple hair, sitting beside a window, blue dress, warm lamplight