Download
1 variant available
5730 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
1060 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
1570 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
(64)
Jun 12, 2026
Version 1.0 based on Anima base 1.0

4.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
2160 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
5420 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
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
LoRA trained on ZIT, Anima and Krea2 all have different trigger words. Sometimes you get the style even without using trigger words (especially on Krea2)
P.S. * I use local ComfyUI for image generation.
For Krea2:
Strength: 1.0 - 1.5.
A bit tricky on Krea2 because of prompt adherence or god knows what:
If you try to use words that creates realism, you will absolutely need 1.5 strength
If you try to use known celebrity fanart words with specific styling like Disney Princesses then you will need 1.2+ strength.
If above two is False then 1.0 is enough in most cases.
Add words like comic, 2d, flat color to help boost the lora styling
For Anima:
Strength: 0.8 recommended. 1.0 will give some anatomy issues.
Anima Version is Trained on Anima Base 1.0
For ZIT:
Strength: 0.8 - 0.9 recommended. 1.0 might give some anatomy issues.
Used 25+ images of comics style from old times, they have more like hand drawn feel but a slight exaggerated expressiveness.
Enjoy and follow me on https://www.deviantart.com/wheeman ❤️

