此版本的推荐强度：1.0 ~ 1.2

这次仅训练了700步，我想我运气不错。我认为你可以指定艺术家名称，模型会更偏向他们的风格，不过我还没试过。这个版本的阴茎尺寸有点奇怪，因为它非常敏感，要么变得过大，要么过小。这是否与训练数据中的裁剪图像有关？

我在1900~2000步时获得了不错的结果，但对整体图像风格影响较大。我更新了大量训练图像和标签，最终得到了满意的效果。

这次我使用了 LoRA_Easy_Training_Scripts，比直接使用 KohyaSS 简单得多。使用 DatasetProcessorDesktop 进行图像裁剪和分类，使用 BooruDatasetTagManager 管理标签。

以下是训练用的 TOML 文件：

[[subsets]]
caption_extension = ".txt"
image_dir = "redacted"
name = "aya_shobon"
num_repeats = 1

[[subsets]]
caption_extension = ".txt"
image_dir = "redacted"
name = "canvassolaris"
num_repeats = 2

[[subsets]]
caption_extension = ".txt"
image_dir = "redacted"
name = "elfk"
num_repeats = 1

[[subsets]]
caption_extension = ".txt"
image_dir = "redacted"
name = "manzai_sugar"
num_repeats = 2

[[subsets]]
caption_extension = ".txt"
image_dir = "redacted"
name = "nonorigo"
num_repeats = 1

[[subsets]]
caption_extension = ".txt"
image_dir = "redacted"
name = "stickyspoodge"
num_repeats = 1

[train_mode]
train_mode = "lora"

[general_args.args]
max_data_loader_n_workers = 1
persistent_data_loader_workers = true
pretrained_model_name_or_path = "illustriousXL_v01.safetensors"
vae = "sdxlVAE_sdxlVAE.safetensors"
mixed_precision = "bf16"
gradient_checkpointing = true
gradient_accumulation_steps = 1
seed = 1337
max_token_length = 225
prior_loss_weight = 1.0
xformers = true
cache_latents = true
cache_latents_to_disk = true
sdxl = true
max_train_steps = 2500

[general_args.dataset_args]
resolution = 1024
batch_size = 2

[network_args.args]
network_dim = 32
network_alpha = 32.0
min_timestep = 0
max_timestep = 1000

[optimizer_args.args]
optimizer_type = "Prodigy"
lr_scheduler = "cosine"
loss_type = "l2"
learning_rate = 1.0
max_grad_norm = 1.0
min_snr_gamma = 5

[saving_args.args]
output_dir = "redacted"
save_precision = "fp16"
save_model_as = "safetensors"
save_last_n_epochs = 1
save_every_n_steps = 100
output_name = "detached_foreskin-v4.6"

[noise_args.args]
multires_noise_iterations = 8
multires_noise_discount = 0.4

[bucket_args.dataset_args]
enable_bucket = true
min_bucket_reso = 512
max_bucket_reso = 2048
bucket_reso_steps = 64

[network_args.args.network_args]
conv_dim = 32
conv_alpha = 32.0
algo = "locon"

[optimizer_args.args.optimizer_args]
weight_decay = "0.1"
betas = "0.9, 0.99"
decouple = "True"
d_coef = "1.0"