Download
1 variant available
fp32 SafeTensor
p0r$hacry$al_ani_v1.safetensors
Full precision, largest file • 87.61 MB
Verified: 14 days ago
built using https://civitai.red/models/2502969/anima-lora-trainer-for-comfyui?modelVersionId=2813599
Trained on Anima Base 1

6080 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
770 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
Heeeeyyyy!!!
For those of you that do not know. She is an artic wolf who starts out as a spoiled brat that cannot act but can sing good.
Tips and Tricks
If you get a human or partial, try adding "wolf girl" or "animated wolf girl".
Using "paws" instead of "hands" can make her hands more accurate. (even though I trained using "handpaws"
Sampler and Scheduler Combos for Z-Image
dpmpp_2m_sde & beta
dpmpp_2m_sde & simple
dpmpp_sde & beta
dpmpp_sde & simple
res_multistep & simple
Anyways, I have spent a good while trying to fine tune the dataset and the training parameters.
I am open to any suggestions on improving the model.
If you create an image of Porsha that looks movie accurate, I might add it to the dataset and toss some yellow buzz your way.
This cannot be used for any commercial purposes since I do not own the character. This is purely for fun. I have only posted this on Civitai.
