Download
1 variant available
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
Main activation tags /// Main outfit (top to bottom)
shinoAP, 1boy, furry male, dog boy, hair over one eye /// fur-trimmed vest with bone print, red bow, kote, green kimono, blue torn kimono, sarashi, layered clothes, white hakama, shin guards, sandalsWaiter outfit:
peony print bandana, black kimono, clothes writing, blue wallet tucked in kimono, tasuki, sleeves rolled up, floral waist apron, black socks
Recommended samplers:
- Euler Ancestral Scheduler: Simple CFG: 4.0 Steps: 30-40 Lora strength: 1.0
Prompt tips (green - positive, red - negative):
- peony hand tattoo - his flower tattoo on his right hand. Sometimes Anima will flip hands randomly or confuse it with other things (like a paw logo)
- (peony hand tattoo:1.5) - higher weight can potentially help with the shape of his tattoo [haven't tested too much]
- weapon over shoulder, sheathed katana, hand on hilt, holding sword, multiple swords, sheathed, katana, flaming weapon, dark magic - all katana related tags (dont use all at once)
- clothes writing - the small name tag on his black kimono waiter outfit. I ignore it as it just generates random gibberish most of the time
- blue wallet tucked in kimono - same as above
- signature, artist name, watermark, English text - always recommended to include
- six fingers, four fingers - helps fix finger count
The LoRas should work with Anima models:
AnimaYume v0.4/WAI-Anima [Preview3]
AnimaYume v0.5 [Base 1.0]
RDBT Lora
Last image in the gallery can be imported into ComfyUI with a basic workflow:
No custom nodes required.

