Sign In

iwatomushi style

3

Updated: Oct 8, 2026

style

Not loaded

Download

1 variant available

bf16 SafeTensor

iwamushi_anima_v5_e6.safetensors

BF16, good balance • 66.25 MB

Verified:

Type
LoRA
Stats

129

3

Generation

Not loaded

Reviews
Published

Oct 6, 2026

Base Model

Anima

Training
Steps: 474
Epochs: 6
Usage Tips
Strength: 1
Hash
AutoV2
56C4EE746C
Trigger Words
@iwamushi
default creator card background decoration
Followers - 6

6

Likes - 25

25

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

20261006_00023_.png

Style LoRA for CircleStone Anima, based on illustrations by iwamushi (岩虫).

Flat print color, olive and muted palettes, rough uneven linework, dirty halftone texture.

Usage

Trigger: @iwamushi (put it at the start of the prompt)

Optional style tags: flat print color, olive muted palette, rough uneven linework, dirty halftone texture

This is a style, not a character. The training set was heavy on Re:Zero, so name the character you actually want.

Version

Epoch 6 of the v5 run (474 steps), not the final epoch.

Training

Base: Anima Base v1.0 only. DiT with AdaLN trained, text encoder and LLM adapter frozen.

Rank/alpha 16/16 · 79 images · 1024 res, buckets 512-1536 · AdamW8bit · LR 5e-5, constant, 5% warmup

Notes

Trained on Anima Base v1.0 only. Behavior on Anima Turbo and third-party merges is unknown.

Not an official model by the artist.