Sign In

Jang Sun Yeong | Ami | Ammie | Mrs. Ahn | Queen Bee Manhwa

88

Download

1 variant available

bf16 SafeTensor

QB-Ammie-000040.safetensors

BF16, good balance • 66.27 MB

Verified:

Type
LoRA
Stats

71

7

3

Reviews
Published

Sep 23, 2026

Base Model

Anima

Training
Steps: 920
Epochs: 40
Usage Tips
Strength: 1
Hash
AutoV2
B84C18DEC8
Trigger Words
a1m33
default creator card background decoration
Followers - 21

21

Likes - 63

63

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

__00001_.png

Amiee character lora from the queen bee manhwa. Trained on Img to Img processed original images from the queen bee manhwa.

UPDATE:

Version 0.2:

Updated dataset to match the original style more closely.

Version 0.3:

The trigger word of v0.3 has more effect on getting the character right. The lora can also double as a style lora for generating other character from the same universe.
The anima preview3 base model seems to generate with the most detail.
Tested using the turbo lora, it seems to reduce quality and detail.
The RDBT lora or checkpoint 0.27 seems to have the same diminishing quality return.

Version 1.0:

Trained on Anima base v1. Improved details. Used 1024 resolution dataset.

Version 1.1:
Trained on dataset captioned with natural language