Anima-2.9B and Anima based.
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..
Description
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.