Sign In

Mister Sinister - X-Men '97

0

Not recently loaded

Download

1 variant available

bf16 SafeTensor

mister_sinister_anima_v1.0.safetensors

BF16, good balance • 87.65 MB

Verified:

Type
LoRA
Stats

8

0

Reviews
Published

Nov 20, 2026

Base Model
Hash
AutoV29BEBCA0E03
Trigger Words
mister_sinister

The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. 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

mister_sinister_anima_v0.1.safetensors_00013_.png

Mister Sinister - Anima Character LoRA

Character LoRA for Mister Sinister, trained on Anima Base v1.0.

  • Trigger: mister_sinister

  • Type: Character

  • Base model: Anima Base v1.0

  • Recommended strength: 0.8-1.0

  • Training images: 27

Identity tags (baked into the trigger)

These describe the character and are present in every caption; you normally don't need to repeat them, but they help if a feature drifts:

1boy, black hair, widow's peak, pale skin, forehead jewel, black lips, muscular male, black eyeshadow, red sclera, no pupils, red eyes

Outfits

Add the tag set of the look you want (and its negative, when it has one, to the negative prompt):

  • classic: mister sinister classic costume, dark blue bodysuit, high collar, chest jewel, red belt, dark blue gloves, dark blue boots, shoulder pads, tattered cape, long navy-blue strips with red undersides arching up and back behind his shoulders like claws (26 imgs)

Usage

Prompt with mister_sinister, then the outfit tags, then pose / scene / background. Captions were written generically (no names), so the trigger carries the identity.

The base model already knows Mister Sinister, so on its own this LoRA can drift toward the model's generic version of the character (comic / other adaptations) instead of the look of the series. For a faithful result, add a style LoRA of the series alongside it.

Tips

  • Strength 0.8-1.0. Keep it there when stacking with the series style LoRA: lowering it lets the model's own version of the character back in.

  • Combine with a style LoRA to place the character in another art style.