v2.0

基于 967 张粉丝艺术作品，为《偶像大师 灰姑娘女孩》中的久川绫和久川千亚双胞胎角色制作的 LoRA 模型。相比 v1.1 版本风格更中性。

提供两个版本：rank 1 和 rank 4。

这表明，尽管并不意外，但 rank 1 版本确实可以承载超过一个角色的信息。

尽管训练集中包含大量双人主题的数据，该模型仍难以在图像中准确区分双胞胎的各自特征。提高模型 rank 有可能改善，也可能无明显帮助，这一点将在未来进一步研究。

使用说明

角色标签为 Hisakawa Nagi 和 Hisakawa Hayate。

若要在同一张图像中生成两位角色，请使用 Hisakawa Nagi / Hisakawa Hayate 或 Hisakawa Hayate / Hisakawa Nagi。

相关标签（Top 相关标签）：

Hiwakawa Nagi,
1girl, solo, twintails, long hair, grey hair, braid, low twintails, brown eyes, looking at viewer, ribbon, hair ribbon, braided bangs, blush, shirt, simple background, long sleeves, white background, black ribbon, very long hair, bow, white shirt, jacket, parted lips, skirt, collared shirt, closed mouth, thighhighs, hair over shoulder, :o, upper body, puffy sleeves, shorts, open mouth, breasts, red bow, black jacket, collarbone, short sleeves, holding, small breasts

Hisakawa Hayate,
1girl, solo, long hair, grey hair, braid, looking at viewer, blush, smile, jewelry, breasts, braided bangs, earrings, blue eyes, very long hair, white background, shirt, open mouth, simple background, skirt, collarbone, medium breasts, white shirt, long sleeves, cleavage, pleated skirt, jacket, collared shirt, :d, bow, bare shoulders, navel, swimsuit, closed mouth, hair between eyes, holding, upper body, puffy sleeves, dress, bikini, short sleeves

Hisakawa Nagi / Hisakawa Hayate,
2girls, multiple girls, siblings, twins, braid, long hair, sisters, grey hair, twintails, brown eyes, smile, braided bangs, open mouth, blue eyes, low twintails, ribbon, blush, looking at viewer, hair ribbon, jewelry, earrings, shirt, dress, skirt, long sleeves, black ribbon, very long hair, white shirt, bow, parted lips, breasts, :d, simple background, one eye closed, v, collarbone, white background, :o, puffy sleeves, collared shirt

如需特定服饰，请参考预览图或数据集。

训练信息

数据集：来自 Danbooru 的 967 张粉丝艺术图

• 338 张 久川绫单人图
• 341 张 久川千亚单人图
• 238 张 两位双胞胎同框图

未进行数据平衡处理，也未清理标签。

对于双角色图像，角色标签顺序在训练过程中动态打乱。

训练成本：r1 和 r4 各约 2 T4 小时

训练配置：

[model_arguments]
v2 = false
v_parameterization = false
pretrained_model_name_or_path = "animefull-final-pruned.ckpt"

[additional_network_arguments]
no_metadata = false
unet_lr = 0.0001
text_encoder_lr = 0.0001
network_module = "networks.lora"
network_alpha = 1
network_train_unet_only = false
network_train_text_encoder_only = false

[optimizer_arguments]
min_snr_gamma = 5
optimizer_type = "AdamW8bit"
learning_rate = 0.0001
max_grad_norm = 1.0
lr_scheduler = "constant"
lr_warmup_steps = 0

[dataset_arguments]
debug_dataset = false
dataset_repeats = 1
shuffle_caption = true
keep_tokens = 1
resolution = "512,512"
caption_dropout_rate = 0
caption_tag_dropout_rate = 0
caption_dropout_every_n_epochs = 0
color_aug = false
token_warmup_min = 1
token_warmup_step = 0

[training_arguments]
save_precision = "fp16"
save_every_n_epochs = 1
train_batch_size = 4
max_token_length = 225
mem_eff_attn = false
xformers = true
max_train_epochs = 9999
max_data_loader_n_workers = 8
persistent_data_loader_workers = true
gradient_checkpointing = false
gradient_accumulation_steps = 1
mixed_precision = "fp16"
clip_skip = 2
lowram = true