Download
1 variant available
480 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
260 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
550 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(16)
May 25, 2026
Anima
Hikaru Kagemori from Yomi no Tsugai.
Dataset is limited so he was trained on a lot of dark indoors shots which can creep in during inference, might try fix it for a future version.
Show more

4750 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
1.1K0 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
Main activation tags /// Main outfit (top to bottom)
HikaruAB, 1boy /// pince-nez, round eyewear, track jacket, open jacket, white t-shirt, track pants
Style control:
for the original anime show style use positive prompt: anime coloring
for other styles remove anime coloring and use different style prompts
Recommended samplers:
- Euler Ancestral Scheduler: Simple CFG: 3.0-4.0 Steps: 30 Lora strength: 1.0
Prompt tips (green - positive, red - negative):
- fat - should correct all angles/shots where he isn't fat enough
- dark - use to negate dark/low-light images
- white hitodama, black hitodama - his demons
- creature - should give his hitodama a face like in the anime
The LoRa should work with Anima checkpoints/turbo loras:
AnimaYume v0.4
WAI-Anima v.1.0
RDBT Turbo Lora
Last image in the gallery can be imported into ComfyUI with a basic workflow:
No custom nodes required.

