Updated: Sep 8, 2026
conceptDownload
9 variants available
Other Formats
ComfyUI_temp_dpeyg_00037_.png
Verified: a day ago
ComfyUI_temp_dpeyg_00038_.png
Verified: a day ago
ComfyUI_temp_dpeyg_00029_.png
Verified: a day ago
ComfyUI_temp_dpeyg_00039_.png
Verified: a day ago
ComfyUI_temp_dpeyg_00032_.png
Verified: a day ago
ComfyUI_temp_dpeyg_00033_.png
Verified: a day ago
ComfyUI_temp_dpeyg_00028_.png
Verified: a day ago

60 1 2 3 4 5 6 7 8 9
220 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
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
A LoRA designed to prevent human ears from appearing on kemonomimi and animal-eared characters when using Anima models.
Bounty rewarded to https://civitai.red/user/baizuobusi
Observations:
Weight Range
The slider can be safely adjusted within a range of -2.0 to +2.0 without causing noticeable side effects to the overall image (no distortion, no collapse, no artifacts).
Weight Direction by Viewing Angle
In front-facing or semi-front-facing views, the Anima model by default does not readily generate human ears (or they are not prominent). Using a positive weight further reduces the probability of human ears appearing, resulting in a cleaner image. Using a negative weight, by contrast, disrupts the model's default state and tends to induce human ears.
In side or profile views, the Anima model by default readily generates clear human ears. Using a negative weight effectively reduces or even eliminates human ears. Using a positive weight, by contrast, further reinforces human ears and makes them more pronounced.
