Yuuki Sakuna (結城さくな) - Illustrious LoRA

Version 1 description

• First Illustrious LoRA

• using Lion Scheduler

Trigger Word

• default costume

yuuki sakuna, long hair, blush, animal ears, pink hair, medium breasts, hair ornament, maid headdress, bow, maid, animal ear fluff, puffy sleeves, apron, white dress, bowtie, collarbone, hairclip, hair bow, detached collar, black footwear, shoes, black choker, white thighhighs

• remove black footwear, shoes, black choker, white thighhighs for half body

• any costume

yuuki sakuna, long hair, blush, cat ears, pink hair, medium breasts, hair ornament, bowtie, hairclip, hair bow

Limitations

• some costume cannot change properly (due to lack of datasets)

• full body still inaccurate (but much improvement)

Training Details

LoRA size

• Dimension 16

Dataset

• 42 images

parameters

• resolution = 1024

• batch size = 2

• dim,alpha = 16,12

• mix/save precision = bf16/bf16

• optmizer = Lion + weight_decay=0.1

• UNet LR = 4e-5

• TE LR = 2e-5

• scheduler = cosine_with_min_lr

• huber snr 0.85

steps

• epochs = 5

• total steps = 1575

• repeats = 15

tools

• kohya-ss GUI v24.3.0 (Forked by me)

• torch 2.5.0 cu124

• Runpod RTX 4090 24 GB + xformers + gradient_checkpointing

weight

• UNet average weights : 0.01002156006341631

• TE1 average weights : 0.008498185547068717

• TE2 average weights : 0.007135996434953993

*This LoRA is for studying LoRA training with new technique so do not use for damaging the vtuber (also support her too).

*REPOST model is not allow if you found this model please report to me.

描述:

训练词语: yuuki sakuna