A native finetune of anima base with a very small dataset. Trained at 1k resoultion, but seems to work decent for generations at larger image size (1.5k resolution, maybe 2k). The default style has a bolder outline than Anima base. The Artist tags and other style tags should still work as intended. This is an early version and more like a test if this works out. Usage is more or less the same as Anima base.
Recomended settings:
Sampler: ER_SDE
Scheduler: Beta
Steps: 32
CFG: 4-5
resolution: 1k-1.5k
quality tags: masterpiece, best quality, highres, absurdres, newest, year 2025
negative prompt: lowres, bad quality, worst quality, score_1, score_2, score_3, jpeg artifacts, signature, watermark
Attribution Notice
“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.”