Download
1 variant available
bf16 SafeTensor
wanwan_mlbb_anima_hardov_v1.safetensors
BF16, good balance • 54.79 MB
Verified: 3 days ago
510 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
00 1 2 3 4 5 6 7 8 9
(7)
Aug 18, 2026
LoRA is trained on 37 images. 3700 steps. On RTX 3060TI.

300 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
700 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5490 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
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
LoRA of Wanwan from Mobile Legends: Bang Bang.
v1.0
Trained on Illustrious-XL v0.1
(ANIMA) Trained on Anima-base v1.0
Recomended prompt:
wanwan_mlbb, 1girl, solo, brown hair, hair bun, double bun, hair ornament, bell, bangs, hair bell, short hair, yellow eyes, whisker markings, tail, bow hair, bow ribbon, jingle bell, tiger tail, hair ribbonClothing tags:
blue dress, chinese clothes, tiger print, fur trim, animal print, sandals, sleevelessRecommended model:
waiNSFWillustrious v17 (or any Illustrious-based model)
(ANIMA) WAI-ANIMA (or any Anima-based model)
Recommended settings:
Weight: 0.8
Steps: 20–28
Tips:
Recommend using ADetailer