Tensor.Art
Create

Kirazuri (Anima) Turbo - 2.0 [dp-dmd]

Kirazuri (Anima) Turbo

LORA
Original

Updated:

2.0 [dp-dmd]
v1.0 [dp-dmd]
Kirazuri (Anima) Turbo by motimalu on Tensor.Art
Kirazuri (Anima) Turbo by motimalu on Tensor.Art
Kirazuri (Anima) Turbo by motimalu on Tensor.Art
Kirazuri (Anima) Turbo by motimalu on Tensor.Art

Turbo LoRA distillation of

Important: This Turbo LoRA is not expected to work with other base models.

Created with DP-DMD diversity-preserved few-step distillation.

Thanks to sorryhyun for the trainer: https://github.com/sorryhyun/anima_lora

Dataset: Generation Settings

4 steps, CFG 1, euler sampler.

Otherwise, refer to recommendations on the Kirazuri (Anima) base model card

Version Detail

Anima
5000
sampler/scheduler: res_2s + bong_tangent res_multistep + simple dpmpp_2m + sgm_uniform Some artifacting is noticeable with samplers that work better at higher step counts i.e. euler Tried to address this a somewhat in version 2.0, and these scheduler combinations also appear work much better at the low 4 step count.

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts