【AI绘画】最佳人物模型训练！保姆式LoRA模型训练教程 一键包发布
之前卡一个地方，关闭后再打开就一直出这个了
prepare tokenizer
update token length: 225
Use DreamBooth method.
prepare images.
found directory train\xs\10_ConceptQ contains 270 image files
2700 train images with repeating.
0 reg images.
no regularization images / 正則化画像が見つかりませんでした
[Dataset 0]
batch_size: 1
resolution: (512, 640)
enable_bucket: True
min_bucket_reso: 256
max_bucket_reso: 1024
bucket_reso_steps: 64
bucket_no_upscale: False
[Subset 0 of Dataset 0]
image_dir: "train\xs\10_ConceptQ"
image_count: 270
num_repeats: 10
shuffle_caption: True
keep_tokens: 0
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
color_aug: False
flip_aug: False
face_crop_aug_range: None
random_crop: False
token_warmup_min: 1,
token_warmup_step: 0,
is_reg: False
class_tokens: ConceptQ
caption_extension: .txt
[Dataset 0]
loading image sizes.
100%|█████████████████████████████████████████████████████████████████████████████| 270/270 [00:00<00:00, 16675.68it/s]
make buckets
number of images (including repeats) / 各bucketの画像枚数（繰り返し回数を含む）
bucket 0: resolution (512, 640), count: 2700
mean ar error (without repeats): 0.0
prepare accelerator
Using accelerator 0.15.0 or above.
loading model for process 0/1
load StableDiffusion checkpoint
Traceback (most recent call last):
File "E:\xm\lora-scripts-1.1.0\lora-scripts-1.1.0\sd-scripts\train_network.py", line 773, in <module>
train(args)
File "E:\xm\lora-scripts-1.1.0\lora-scripts-1.1.0\sd-scripts\train_network.py", line 146, in train
text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype, accelerator)
File "E:\xm\lora-scripts-1.1.0\lora-scripts-1.1.0\sd-scripts\library\train_util.py", line 2928, in load_target_model
text_encoder, vae, unet, load_stable_diffusion_format = _load_target_model(
File "E:\xm\lora-scripts-1.1.0\lora-scripts-1.1.0\sd-scripts\library\train_util.py", line 2894, in _load_target_model
text_en
有没有人知道解决方法
