Turbo LoRA distillation of Kirazuri (Anima) v4.0
Important: This LoRA is not expected to work with other base models.
Generation Settings:
4 steps, CFG 1
sampler/scheduler:
res_2s + bong_tangent
res_multistep + simple
dpmpp_2m + sgm_uniform
Otherwise, please refer to recommendations on the Kirazuri (Anima) base model card.
Training details (Latest - v3.0):
Created with DP-DMD diversity-preserved few-step distillation.
Training dataset of 647 images generated by the teacher model Kirazuri (Anima) v4.0 with fully synthetic and partially synthetic images generated with img2img.
Thanks to sorryhyun for the trainer: https://github.com/sorryhyun/anima_lora