Sign In

Bagaponchi Style for Anima

9

Recently loaded

Download

1 variant available

bf16 SafeTensor

Bagaponchi Style LoRA for Anima_merged3000-4000.safetensors

BF16, good balance • 132.24 MB

Verified:

Type
LoRA
Stats

131

9

2

Reviews
Published

Nov 16, 2026

Base Model
Training
Steps: 4,000
Usage Tips
Strength: 1
Hash
AutoV2E5C0297609
Trigger Words
velqorabagaponchi

The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. 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

ComfyUI_temp_uuqos_00002_.png

The model is trained on 4000 steps, and the model here is a merge between 3000, 3250, 3500, 3750 and 4000 step saves.

Trigger words: velqora, bagaponchi

Steps, sampler, scheduler - to be frank, I found that to almost not matter with Anima so use whichever things you like. I personally have settings like these:
Sampler: euler a
Scheduler: simple
Steps: 25
CFG: 5

It generally helps putting "ai generated" in negative and adding "messy lines", "sketch" to positive in order for style to flaunder. Please tell me your feedback, use on site generation if by any chance you wanna support me and reach out to me if you are willing to commission a lora.

P.S. Dont pay mind to prompts in the image metadata - it carried all over from one part of the batch workflow