Sign In

Waku Waku 7 - The Lombrozos

102

Recently loaded

Download

1 variant available

bf16 SafeTensor

Lulu_Anima_epoch_5.safetensors

BF16, good balance • 33.14 MB

Verified:

Type
LoRA
Stats

40

34

21

Reviews
Published

Nov 13, 2026

Base Model
Training
Steps: 2,500Epochs: 5
Hash
AutoV2DE28CCC0C1
Trigger Words
lulu lombrozo, pink hair, twintails, belt choker, maid headdress, robot ears, headphones, antennae, puffy sleeves, long sleeves, pink dress, turtleneck, juliet sleeves, white gloves, apron, white skirt, wrist belts, small breasts, black eyes, fang, hair ribbons, :D, fang, pink socks, loose socks, pink shoes

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

Anima-28-10-2026_00130_.png

A personal project of mine where I attempt to recreate the Lombrozo sisters seen in Tesse's concept art. The colors are purely made up as they have no "finalized" design and some are very loosely based off of Tesse's alternate palettes.

Most of the training data here is derived from alternate interpretations by Google Nanobanana. Obviously, being nothing more than trivia for the game, they do not have actual images to train off of.

The V1.0 LoRAs default to a specific pose unless prompted otherwise, meaning Lulu for example will be stuck with one or two hands above her hips at all times. Other V1.0 models have a pre-baked look to them that can be mitigated without much issue if the weight is set to 0.8 (sometimes 0.6). Lulu must stay at 1.0 strength for maximum accuracy.