Download
1 variant available
Went through the dataset multiple times to clean it up thoroughly, custom block weights to apply style and keep anatomy. I recommend using turbo LoRA with this version.
Show more

2.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
1.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
28.2K0 1 2 3 4 5 6 7 8 90 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
Anima-2.9B based (v=>5).
Anima based (v=<4).
Main parameters:
Steps: 28
CFG: 5
Sampler-scheduler: er_sde-sgm_uniform
Turbo LoRAs (Anima-2.9B, Anima):
Steps: 12
CFG: 1
Sampler-scheduler: er_sde-sgm_uniform
Positive prompt:
masterpiece, best quality, score_9, [meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]some heavily stylized characters might require prompt: realistic, nose in Detailer
Negative prompt:
worst quality, low quality, score_1don't overdo it with negative prompt
Enjoy..


