Download
1 variant available
fp16 SafeTensor
b529e7df-a73b-4735-8f70-a2377685975a.TA_trained.safetensors
Half precision, best balance • 87.71 MB
Verified: 3 days ago
2610 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
180 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
180 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(62)
Aug 12, 2026

5250 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
4.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
34.6K0 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
Ars Goetia is series of loras made on a whim, on variety of images, made from mix of Midjourney, Tumblr, NijiJourney and many more things. Each Demon brings something different. Quality might vary between loras - it's small experiment for me.
I recommend using "cartoon" in the prompt. In the end of showcase you can see difference between trigger word alone and adding few more stylized words.
Recommended settings:
Sampler:
er_sde
euler
dpmpp_sde_gpu
Scheduler:
beta - for more drawn style
linear_quadratic - for more softened, 3d look
Sampling steps: 25-40
CFG: 4-5
Lora Strength: 0.6-0.8

