Windows SDXL Lora Training with error: Optimizer got an empty parameter list, what I can do to fix this error?

Python环境:

(base) PS C:\Users\Administrator> python --version
Python 3.12.3

配置文件:

model_train_type = "sdxl-lora"
pretrained_model_name_or_path = "D:/sd-webui-aki-v4.10/models/Stable-diffusion/SDXL/AnythingXL_xl.safetensors"
train_data_dir = "D:/lora-scripts-v1.10.0/train/Zelenskyi"
prior_loss_weight = 1
resolution = "512,512"
enable_bucket = true
min_bucket_reso = 256
max_bucket_reso = 1024
bucket_reso_steps = 64
bucket_no_upscale = true
output_name = "Zelenskyi"
output_dir = "./output"
save_model_as = "safetensors"
save_precision = "bf16"
save_every_n_epochs = 2
save_state = false
max_train_epochs = 10
train_batch_size = 1
gradient_checkpointing = false
network_train_unet_only = true
network_train_text_encoder_only = true
learning_rate = 0.0001
unet_lr = 0.0001
text_encoder_lr = 0.00001
lr_scheduler = "cosine_with_restarts"
lr_warmup_steps = 0
lr_scheduler_num_cycles = 3
optimizer_type = "AdamW8bit"
network_module = "networks.lora"
network_dim = 64
network_alpha = 64
log_with = "tensorboard"
logging_dir = "./logs"
caption_extension = ".txt"
shuffle_caption = false
keep_tokens = 0
max_token_length = 255
seed = 1337
mixed_precision = "bf16"
full_bf16 = true
no_half_vae = false
xformers = true
lowram = false
cache_latents = true
cache_latents_to_disk = true
persistent_data_loader_workers = true

完整日志如下:

23:26:55-130764 INFO Starting SD-Trainer Mikazuki GUI...
23:26:55-136935 INFO Base directory: D:\lora-scripts-v1.10.0, Working directory: D:\lora-scripts-v1.10.0
23:26:55-138486 INFO Windows Python 3.10.11 D:\lora-scripts-v1.10.0\python\python.exe
23:26:55-139521 INFO detected locale zh_CN, use pip & huggingface mirrors
23:26:55-205895 INFO SD-Trainer Version: v1.10.0-44-gbf945ed
23:26:55-207440 INFO Starting tageditor...
23:26:55-210565 INFO Starting tensorboard...
23:26:55-294396 INFO Server started at http://127.0.0.1:28000
23:26:56-486149 INFO Loading config from D:\lora-scripts-v1.10.0\assets\config.json
23:26:59-117446 INFO Torch 2.4.1+cu124
23:26:59-139052 INFO Torch backend: nVidia CUDA 12.4 cuDNN 90100
23:26:59-144729 INFO Torch detected GPU: NVIDIA GeForce RTX 4060 Ti VRAM 16380 Arch (8, 9) Cores 34
TensorBoard 2.10.1 at http://127.0.0.1:6006/ (Press CTRL+C to quit)
23:29:48-772837 INFO Found 2 legal dataset
23:29:48-778993 INFO Training started with config file / 训练开始，使用配置文件:
D:\lora-scripts-v1.10.0\config\autosave\20250313-232948.toml
23:29:48-780523 INFO Task f906a3d3-f49e-41ee-928f-d8cd2660e841 created
2025-03-13 23:30:00 INFO Loading settings from train_util.py:4012
D:\lora-scripts-v1.10.0\config\autosave\20250313-232948.toml...
INFO D:\lora-scripts-v1.10.0\config\autosave\20250313-232948 train_util.py:4031
2025-03-13 23:30:00 INFO prepare tokenizers sdxl_train_util.py:138
2025-03-13 23:30:01 INFO update token length: 255 sdxl_train_util.py:163
INFO Using DreamBooth method. train_network.py:172
2025-03-13 23:30:02 INFO prepare images. train_util.py:1686
INFO found directory D:\lora-scripts-v1.10.0\train\Zelenskyi\50_photo_body train_util.py:1633
contains 33 image files
INFO found directory D:\lora-scripts-v1.10.0\train\Zelenskyi\50_photo_face train_util.py:1633
contains 28 image files
INFO 3050 train images with repeating. train_util.py:1727
INFO 0 reg images. train_util.py:1730
WARNING no regularization images / 正則化画像が見つかりませんでした train_util.py:1735
INFO [Dataset 0] config_util.py:572
batch_size: 1
resolution: (512, 512)
enable_bucket: True
network_multiplier: 1.0
min_bucket_reso: 256
max_bucket_reso: 1024
bucket_reso_steps: 64
bucket_no_upscale: True

[Subset 0 of Dataset 0]
image_dir: "D:\lora-scripts-v1.10.0\train\Zelenskyi\50_photo_body"
image_count: 33
num_repeats: 50
shuffle_caption: False
keep_tokens: 0
keep_tokens_separator:
caption_separator: ,
secondary_separator: None
enable_wildcard: False
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
caption_prefix: None
caption_suffix: None
color_aug: False
flip_aug: False
face_crop_aug_range: None
random_crop: False
token_warmup_min: 1,
token_warmup_step: 0,
alpha_mask: False,
is_reg: False
class_tokens: photo_body
caption_extension: .txt

[Subset 1 of Dataset 0]
image_dir: "D:\lora-scripts-v1.10.0\train\Zelenskyi\50_photo_face"
image_count: 28
num_repeats: 50
shuffle_caption: False
keep_tokens: 0
keep_tokens_separator:
caption_separator: ,
secondary_separator: None
enable_wildcard: False
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
caption_prefix: None
caption_suffix: None
color_aug: False
flip_aug: False
face_crop_aug_range: None
random_crop: False
token_warmup_min: 1,
token_warmup_step: 0,
alpha_mask: False,
is_reg: False
class_tokens: photo_face
caption_extension: .txt

INFO [Dataset 0] config_util.py:578
INFO loading image sizes. train_util.py:901
100%|███████████████████████████████████████████████████████████████████████████████| 61/61 [00:00<00:00, 13461.67it/s]
INFO make buckets train_util.py:907
WARNING min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is train_util.py:924
set, because bucket reso is defined by image size automatically /
bucket_no_upscaleが指定された場合は、bucketの解像度は画像サイズから自動計
算されるため、min_bucket_resoとmax_bucket_resoは無視されます
INFO number of images (including repeats) / train_util.py:953
各bucketの画像枚数（繰り返し回数を含む）
INFO bucket 0: resolution (512, 512), count: 3050 train_util.py:958
INFO mean ar error (without repeats): 0.0 train_util.py:963
INFO preparing accelerator train_network.py:225
accelerator device: cuda
INFO loading model for process 0/1 sdxl_train_util.py:33
INFO load StableDiffusion checkpoint: sdxl_train_util.py:74
D:/sd-webui-aki-v4.10/models/Stable-diffusion/SDXL/AnythingXL_xl.safe
tensors
INFO building U-Net sdxl_model_util.py:198
INFO loading U-Net from checkpoint sdxl_model_util.py:202
2025-03-13 23:30:10 INFO U-Net: sdxl_model_util.py:208
INFO building text encoders sdxl_model_util.py:211
INFO loading text encoders from checkpoint sdxl_model_util.py:264
INFO text encoder 1: sdxl_model_util.py:278
2025-03-13 23:30:11 INFO text encoder 2: sdxl_model_util.py:282
INFO building VAE sdxl_model_util.py:285
INFO loading VAE from checkpoint sdxl_model_util.py:290
2025-03-13 23:30:12 INFO VAE: sdxl_model_util.py:293
INFO Enable xformers for U-Net train_util.py:2832
import network module: networks.lora
INFO [Dataset 0] train_util.py:2195
INFO caching latents. train_util.py:1022
INFO checking cache validity... train_util.py:1049
100%|████████████████████████████████████████████████████████████████████████████████| 61/61 [00:00<00:00, 1612.72it/s]
INFO caching latents... train_util.py:1091
0it [00:00, ?it/s]
2025-03-13 23:30:13 INFO create LoRA network. base dim (rank): 64, alpha: 64 lora.py:935
INFO neuron dropout: p=None, rank dropout: p=None, module dropout: p=None lora.py:936
INFO create LoRA for Text Encoder 1: lora.py:1027
INFO create LoRA for Text Encoder 2: lora.py:1027
INFO create LoRA for Text Encoder: 88 modules. lora.py:1035
2025-03-13 23:30:15 INFO create LoRA for U-Net: 722 modules. lora.py:1043
prepare optimizer, data loader etc.
2025-03-13 23:30:16 INFO use 8-bit AdamW optimizer | {} train_util.py:4166
Traceback (most recent call last):
File "D:\lora-scripts-v1.10.0\scripts\stable\sdxl_train_network.py", line 185, in
trainer.train(args)
File "D:\lora-scripts-v1.10.0\scripts\stable\train_network.py", line 367, in train
optimizer_name, optimizer_args, optimizer = train_util.get_optimizer(args, trainable_params)
File "D:\lora-scripts-v1.10.0\scripts\stable\library\train_util.py", line 4168, in get_optimizer
optimizer = optimizer_class(trainable_params, lr=lr, **optimizer_kwargs)
File "D:\lora-scripts-v1.10.0\python\lib\site-packages\bitsandbytes\optim\adamw.py", line 114, in __init__
super().__init__(
File "D:\lora-scripts-v1.10.0\python\lib\site-packages\bitsandbytes\optim\optimizer.py", line 427, in __init__
super().__init__(params, defaults, optim_bits, is_paged)
File "D:\lora-scripts-v1.10.0\python\lib\site-packages\bitsandbytes\optim\optimizer.py", line 125, in __init__
super().__init__(params, defaults)
File "D:\lora-scripts-v1.10.0\python\lib\site-packages\torch\optim\optimizer.py", line 362, in __init__
raise ValueError("optimizer got an empty parameter list")
ValueError: optimizer got an empty parameter list
23:30:19-565608 ERROR Training failed / 训练失败

请问我是缺少什么环境组件吗? 我已经运行过install-cn.ps1文件并且已经将版本强制更新到最新版本了!