Download
1 variant available
bf16 SafeTensor
MB_Balsamique_Style_Anima_0_1.safetensors
BF16, good balance • 132.24 MB
Verified: a day ago
MB Balsamique Style — Anima 0.1
First train for Anima and it was hard.
I know that is not perfect style, thats why i upload new version soon

24.2K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
1.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
1.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

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
MB Balsamique Style
Style LoRA inspired by the artwork of Balsamique (David Goujard): heavy variable-weight ink contours, hard two-tone cel shading, angular faces with a heavy upper lash line, glossy highlight shapes, bold exaggerated proportions and flat colour-field backgrounds.
I need some Buzzzzz to create new styles...
Anima 0.1
Trigger word
@balsamiqueRecommended settings
Best work on Anima Turbo v1.1
LoRA strength: 0.8 (0.7–1.0)
Sampler: uni_pc, er_sde, euler
Scheduler: ddim_uniform (uni_pc), beta (er_sde), simple (euler)
Steps: 10
CFG: 1
Resolution: 1184×864, 832×1216
Example prompts
sensitive, 1girl, @balsamique, solo, adult woman, black hair, long hair, earrings, turtleneck, sweater, belt, black pants, bracelet, black nails, lipstick, looking at viewer, standing, hand on own hip, red backgroundTips
- Short booru-style tag lists work best — the LoRA was trained on tag captions, not prose.
- In multi-character scenes, attributes can attach to the wrong person; generate a few seeds or describe the second character with fewer tags.
