Download
1 variant available
First ever character Lora I made, now re-trained on Anima 1.0.
The Lora is a bit more style locked than my usual Loras, forgot to caption the style in my dataset plus there is not a lot of reference material for this character. Might retrain another version but GPU rental right now is extremely limited.
Show more

4970 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
1.2K0 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
Main activation tags /// Main outfit (top to bottom)
darrellAB, lion boy, furry male, 1boy /// hawaiian shirt, open shirt, white tank top, belt, beige shorts, sneakers
Style control:
enhanced style - use score_9, score_8
original visual novel style - only use activation tags
Recommended samplers:
- Euler Ancestral Scheduler: Simple CFG: 3.0-3.5 Steps: 30 Lora strength: 1.0
Prompt tips (green - positive, red - negative):
- high ponytail - ponytail alternative hairstyle
- six fingers, six claws, four fingers, four claws - helps Anima with proper finger count
The LoRa should work with Anima checkpoints/turbo loras:
AnimaYume v0.4
RDBT Turbo Lora
Anima Turbo Lora
Last image in the gallery can be imported into ComfyUI with a basic workflow:
No custom nodes required.

