Sign In

[Anima] Shachi (Live2D Model) - Indie VTuber

8

Recently loaded

Download

1 variant available

fp16 SafeTensor

ShachiL2DAnima.safetensors

Half precision, best balance • 87.6 MB

Verified:

Type
LoRA
Stats

75

8

8

Reviews
Published

Oct 19, 2026

Base Model
Hash
AutoV2FD37B35837
Trigger Words
ShachiL2D, very long hair, hair past waist, ahoge, pink hair, pink eyes, medium breasts, baggy turtleneck sweater, white and black sweater, sweater decal, "O7" decal on sweater, black thighhighs, shaped thighhighs,

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

Obligatory Disclaimer: This LoRA is intended to be used alongside style LoRAs and/or artist style tags to bring out its full potential. All example images use WAI-Anima and the "haku89" artist style tag.

If you don't see all 5 example media, make sure you're logged in and try changing Browsing Level.

Start with a model strength of 1.0. If you find the model to be too stiff, try lowering it to 0.80.

A character LoRA for the indie VTuber Shachi's Live2D model. Trained on a dataset of 40 images that consists largely of cut up screenshots, images generated/enhanced by ChatGPT, and a few fanarts.

The decal on the sweater can have issues generating clearly, especially at distance. If you're looking to make actual art pieces using this model, I recommend doing the decal manually. True hair length generation can also be a problem since, in my experience, Anima doesn't like super long hair in non-standing full-body poses. The tops of the thighhighs can also have strange generation if not given a few negative triggers. For whatever reason, the model likes to generate hearts, stars, and any other number of things at the base of the curve despite there being nothing in the training data encouraging such behavior. Ultimately, not very glaring issues in practice but still something to keep in mind. The below and attached triggers are general suggestions. You can almost certainly get better and more consistent results by more specific prompting. I'm just lazy. Play around with it to see what works for you. Remember, Anima loves natural language so converting the listed triggers into natural language can result in more consistent generation.

Detailers are highly recommended for the face and eyes.

Manual inpainting or image refinement through ChatGPT are recommended if you're looking to generate small details.

Probably won't be updated.

All example images were generated without a refiner step. You can probably make your generations look much better with improved workflows.

Triggers:

ShachiL2D, very long hair, hair past waist, ahoge, pink hair, pink eyes, medium breasts,

baggy turtleneck sweater, white and black sweater, sweater decal, "O7" decal on sweater, black thighhighs, shaped thighhighs,