Sign In

Real Anima

6

Updated: Oct 5, 2026

style

Loaded

Download

1 variant available

fp16 SafeTensor

real_anima-000014.safetensors

Half precision, best balance • 87.64 MB

Verified:

Type
LoRA
Stats

115

6

8

Generation

Loaded

Reviews
Published

Oct 5, 2026

Base Model

Anima

Training
Steps: 2,200
Epochs: 14
Usage Tips
Strength: 0.8
Hash
AutoV2
B2FCA95C40
default creator card background decoration
Uploads - 1

1

Followers - 604

604

Likes - 9

9

License:

Anima

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

Anima__00151_.png

v0.1

  • 需要加入触发词"Real_Anima"
    trigger word: Real_Anima

  • 强度0.8-1左右即可
    strength: around 0.8–1.0

  • 这是我第一次训练Lora,数据集共使用了120张图片+120张正则数据(几乎全为SFW的图片),在NSFW上可能表现不佳。在RTX5090上训练了大约2200步,训练用参数在附件中。
    This is my first time training a LoRA; the dataset consisted of 120 images and 120 regularization images (almost SFW dataset), It may not perform well with NSFW contents. It was trained for approximately 2,200 steps on a RTX5090. The training parameters are in the attachment.