This SDXL Anime Checkpoint is recommended for training LoRA characters.

The parameters that have worked for me are:

Network Module

LoRA

Use Base Model

V3 - SDXL Anime

Trigger words

-

Image Processing Parameters:

Repeat

5 (10 repeats only if the images in the dataset are few)

Epoch

10

Save Every N Epochs

1

Training Parameters:

Seed

-

Clip Skip

2

Text Encoder learning rate

0.00006

Unet learning rate

0.0003

LR Scheduler

cosine_with_restarts

lr_scheduler_num_cycles

3

num_warmup_steps

0

Optimizer

AdamW8bit

Network Dim

16

Network Alpha

8

Gradient Accumulation Steps

-

Label Parameters:

Shuffle caption

true

Keep n tokens

1

Advanced Parameters:

Noise offset

0.03

Multires noise discount

0.1

Multires noise iterations

10

conv_dim

-

conv_alpha

-

Batch Size

4

Labeling:

(in the dataset editing window)

Auto Labeling:

Image Labeling Algorithm

wd-swinv2-tagger-v3

Batch Add Labels:

Put an activation tag at the start of every text file. This is useful to make learning better and activate your Lora easier. Set keep_tokens to 1 in Parameter Settings