Sign In

MagnaLuna Style [Anima/Pony]

1.4k

Not loaded

Download

1 variant available

bf16 SafeTensor

MagmaLunaStyle_Anima_anima_3359053_epoch_10.safetensors

BF16, good balance • 132.24 MB

Verified:

Type
LoRA
Stats

27

0

Generation

Not loaded

Reviews
Published

Sep 26, 2026

Base Model

Anima

Training
Steps: 1,500
Usage Tips
Strength: 1
Hash
AutoV2
3E85D71CBD
default creator card background decoration
Followers - 22

22

Likes - 60

60

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

0KVVDK2J5EGKE8P70CJ0XCR9T0.jpeg

I love MagnaLuna's art style, but I wasn't very satisfied with the other PDXL Lora available on this site, so I decided to make my own. From my testing this should capture the style better while also having a more diverse range of generations - and being less biased to certain characters.

Base trigger word is "magnaluna"

"pony" - Regular ponies

"anthro pony" - They have hands

"furry" - Everything else

Use "luna" and "celestia" by themselves without princess for MagnaLuna style bias, include princess to decrease bias

This Lora also (somewhat) understands different Luna versions;

luna + white hair

luna + purple hair

luna + dark purple hair

luna + blue hair

I recommend a lower strength for vague or less specific prompts, otherwise 0.8-1 is good.