Download
1 variant available
fp16 SafeTensor
a99d3177-facc-4e3b-a8c6-613fdd331d3e.TA_trained.safetensors
Half precision, best balance • 175.22 MB
Verified: 2 months ago
525
4.4K
34.7K
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 made out of my Niji pcodes. I think I am proudest of this one. Very strong on it's own, but works the best with Elysian Radiance (if mixing with Elysian, set Elysian to 0.4)
Trigger words makes lora much stronger.
Recommended settings:
Sampler:
er_sde
euler a
Scheduler:
beta - for more drawn style
linear_quadratic - for more softened, 3d look
Sampling steps: 25
CFG: 3-4
Lora Strength: 0.6-0.8