Dedicated to the retired model あずまひかり (azuma hikari).
Recommended setting:
Lora weight: 0.75 - 0.80
Sampler: DPM++ SDE Karras or Euler a
CFG: 7-8
Steps: 20-25
Description
Training based on BRAV5 checkpoint
Dedicated to the retired model あずまひかり (azuma hikari).
Recommended setting:
Lora weight: 0.75 - 0.80
Sampler: DPM++ SDE Karras or Euler a
CFG: 7-8
Steps: 20-25
Training based on BRAV5 checkpoint