Download
1 variant available
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
Artist style lora by Hara Tetsuo, author of Fist of the North star.
Please keep in mind that this is a style LoRA, not a character LoRA.
▼ Anima
■ Kenshiro may sometimes appear with yellow/blond hair. If that happens, add blonde hair to the negative prompt.
■ I tried my best to recreate the comic style rather than the anime style.
■ Please refer to the example prompts for the characters. Not all characters may be reproduced accurately.
▽ Illustrious / Noob
Due to the dataset issue, if the character's distance is too far (ex. full body), there is a possibility that the face will be crushed, so we highly recommend using Facedetailer (or adetailer).
Recommend settings
V 1.0
MODEL : NOOB-Epsilon 1.1
step-30
cfg-5
dpm-2m / sgm-uniform
Use Facedetailer / Adetailer
V 1.5
MODEL : NOOB-Epsilon 1.1
step-30
cfg- 4 - 6
dpm-2m / sgm-uniform
Use Facedetailer / Adetailer
Recommended eyes prompt - intense eyes, *Constructed Puppils
*if you use Constructed Puppils, it's more badass-like.
Sketch prompt expresses a line more like the original-cartoon.
If the hairstyle or face, you want isn't working well,
you try adding "kenshiro" in the negative, it's likely to be resolved.
I recommend don't adding greyscale and monochrome prompts in negatives.
The character is not supported because it is a LORA whose purpose is to only train-style.
But, Kenshiro & yuria can be easily created.
v1.7
MODEL: NOOB-Epsilon 1.1
step-30
cfg: 4–6
Euler a
Lora strength 0.6~0.8
------------
This LoRA is also somewhat experimental.
That’s because the Fist of the North Star dataset is hard to obtain — most of it is low-resolution and in monochrome.
In such cases, one could extract frames from the anime, but my goal for this LoRA is to make it as close as possible to the original artwork. So I won’t be doing that.
It may receive a few more updates until I achieve a result I’m satisfied with.
------------
UPDATE
- V 1.5
This time, Made it feel more like a cartoon if use a dpm-2m sampler.
If you don't like cartoonish lines, use eular_a sampler or use lora of Version 1.0.
I changed some of the datasets that I used in version 1.0, and added some female data. Now we can create a Yuria.
also create of char Lin, but it wasn't easy.
And the overall style is stronger than version 1.0, so use the weights between 0.6 and 0.8.
- v1.7
The dataset has been reorganized and training has been performed again.The female data has not been included.
A few character datasets have been added, but the probability is not high. Kenshiro still comes out well.
The issue of the face getting distorted in full-body shots has been slightly improved, and the problem of the hairstyle being fixed has been mitigated.
Since the Hara Tetsuo dataset is difficult to organize, it is currently being checked for other issues and may be updated again.