it worked but now shows this error:

[Dataset 0]

loading image sizes.

100%|████████████████████████████████████████████████████████████████████████████████| 21/21 [00:00<00:00, 2632.17it/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 (1024, 1024), count: 2100

mean ar error (without repeats): 0.0

clip_skip will be unexpected / SDXL学習ではclip_skipは動作しません

Warning: SDXL has been trained with noise_offset=0.0357 / SDXLはnoise_offset=0.0357で学習されています

noise_offset is set to 0.0375 / noise_offsetが0.0375に設定されました

preparing accelerator

loading model for process 0/1

load StableDiffusion checkpoint: ./Stable-diffusion/dreamshaperXL10_alpha2Xl10.safetensors

building U-Net

loading U-Net from checkpoint

U-Net: <All keys matched successfully>

building text encoders

loading text encoders from checkpoint

text encoder 1: <All keys matched successfully>

text encoder 2: <All keys matched successfully>

building VAE

loading VAE from checkpoint

VAE: <All keys matched successfully>

Enable xformers for U-Net

import network module: networks.lora

[Dataset 0]

caching latents.

checking cache validity...

100%|█████████████████████████████████████████████████████████████████████████████████| 21/21 [00:00<00:00, 346.91it/s]

caching latents...

0it [00:00, ?it/s]

move vae and unet to cpu to save memory

[Dataset 0]

caching text encoder outputs.

checking cache existence...

100%|██████████████████████████████████████████████████████████████████████████████████████████| 21/21 [00:00<?, ?it/s]

caching text encoder outputs...

100%|██████████████████████████████████████████████████████████████████████████████████| 21/21 [00:02<00:00, 7.99it/s]

move vae and unet back to original device

create LoRA network. base dim (rank): 32, alpha: 16.0

neuron dropout: p=None, rank dropout: p=None, module dropout: p=None

create LoRA for Text Encoder 1:

create LoRA for Text Encoder 2:

create LoRA for Text Encoder: 264 modules.

create LoRA for U-Net: 722 modules.

enable LoRA for U-Net

prepare optimizer, data loader etc.

╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮

│ C:\Lora\kohya_ss\sd-scripts\sdxl_train_network.py:174 in <module> │

│ │

│ 171 │ args = train_util.read_config_from_file(args, parser) │

│ 172 │ │

│ 173 │ trainer = SdxlNetworkTrainer() │

│ ❱ 174 │ trainer.train(args) │

│ 175 │

│ │

│ C:\Lora\kohya_ss\sd-scripts\train_network.py:325 in train │

│ │

│ 322 │ │ │ ) │

│ 323 │ │ │ trainable_params = network.prepare_optimizer_params(args.text_encoder_lr, ar │

│ 324 │ │ │

│ ❱ 325 │ │ optimizer_name, optimizer_args, optimizer = train_util.get_optimizer(args, train │

│ 326 │ │ │

│ 327 │ │ # dataloaderを準備する │

│ 328 │ │ # DataLoaderのプロセス数：0はメインプロセスになる │

│ │

│ C:\Lora\kohya_ss\sd-scripts\library\train_util.py:3222 in get_optimizer │

│ │

│ 3219 │ │

│ 3220 │ elif optimizer_type.endswith("8bit".lower()): │

│ 3221 │ │ try: │

│ ❱ 3222 │ │ │ import bitsandbytes as bnb │

│ 3223 │ │ except ImportError: │

│ 3224 │ │ │ raise ImportError("No bitsandbytes / bitsandbytesがインストールされていない │

│ 3225 │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\__init__.py:6 in <module> │

│ │

│ 3 # This source code is licensed under the MIT license found in the │

│ 4 # LICENSE file in the root directory of this source tree. │

│ 5 │

│ ❱ 6 from . import cuda_setup, utils, research │

│ 7 from .autograd._functions import ( │

│ 8 │ MatmulLtState, │

│ 9 │ bmm_cublas, │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\research\__init__.py:1 in <module> │

│ │

│ ❱ 1 from . import nn │

│ 2 from .autograd._functions import ( │

│ 3 │ switchback_bnb, │

│ 4 │ matmul_fp8_global, │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\research\nn\__init__.py:1 in <module> │

│ │

│ ❱ 1 from .modules import LinearFP8Mixed, LinearFP8Global │

│ 2 │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\research\nn\modules.py:8 in <module> │

│ │

│ 5 from torch import Tensor, device, dtype, nn │

│ 6 │

│ 7 import bitsandbytes as bnb │

│ ❱ 8 from bitsandbytes.optim import GlobalOptimManager │

│ 9 from bitsandbytes.utils import OutlierTracer, find_outlier_dims │

│ 10 │

│ 11 T = TypeVar("T", bound="torch.nn.Module") │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\optim\__init__.py:6 in <module> │

│ │

│ 3 # This source code is licensed under the MIT license found in the │

│ 4 # LICENSE file in the root directory of this source tree. │

│ 5 │

│ ❱ 6 from bitsandbytes.cextension import COMPILED_WITH_CUDA │

│ 7 │

│ 8 from .adagrad import Adagrad, Adagrad8bit, Adagrad32bit │

│ 9 from .adam import Adam, Adam8bit, Adam32bit, PagedAdam, PagedAdam8bit, PagedAdam32bit │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\cextension.py:13 in <module> │

│ │

│ 10 │

│ 11 setup = CUDASetup.get_instance() │

│ 12 if setup.initialized != True: │

│ ❱ 13 │ setup.run_cuda_setup() │

│ 14 │

│ 15 lib = setup.lib │

│ 16 try: │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:126 in run_cuda_setup │

│ │

│ 123 │ │ self.initialized = True │

│ 124 │ │ self.cuda_setup_log = [] │

│ 125 │ │ │

│ ❱ 126 │ │ binary_name, cudart_path, cc, cuda_version_string = evaluate_cuda_setup() │

│ 127 │ │ self.cudart_path = cudart_path │

│ 128 │ │ self.cuda_available = torch.cuda.is_available() │

│ 129 │ │ self.cc = cc │

╰──────────────────────────────────────────────────────────────────────────────────────────────────╯

ValueError: too many values to unpack (expected 4)

╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮

│ D:\Python\lib\runpy.py:196 in runmodule_as_main │

│ │

│ 193 │ main_globals = sys.modules["__main__"].__dict__ │

│ 194 │ if alter_argv: │

│ 195 │ │ sys.argv[0] = mod_spec.origin │

│ ❱ 196 │ return runcode(code, main_globals, None, │

│ 197 │ │ │ │ │ "__main__", mod_spec) │

│ 198 │

│ 199 def run_module(mod_name, init_globals=None, │

│ │

│ D:\Python\lib\runpy.py:86 in runcode │

│ │

│ 83 │ │ │ │ │ loader = loader, │

│ 84 │ │ │ │ │ package = pkg_name, │

│ 85 │ │ │ │ │ spec = mod_spec) │

│ ❱ 86 │ exec(code, run_globals) │

│ 87 │ return run_globals │

│ 88 │

│ 89 def runmodule_code(code, init_globals=None, │

│ │

│ in <module>:7 │

│ │

│ 4 from accelerate.commands.accelerate_cli import main │

│ 5 if name == '__main__': │

│ 6 │ sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) │

│ ❱ 7 │ sys.exit(main()) │

│ 8 │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py:45 in main │

│ │

│ 42 │ │ exit(1) │

│ 43 │ │

│ 44 │ # Run │

│ ❱ 45 │ args.func(args) │

│ 46 │

│ 47 │

│ 48 if name == "__main__": │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py:918 in launch_command │

│ │

│ 915 │ elif defaults is not None and defaults.compute_environment == ComputeEnvironment.AMA │

│ 916 │ │ sagemaker_launcher(defaults, args) │

│ 917 │ else: │

│ ❱ 918 │ │ simple_launcher(args) │

│ 919 │

│ 920 │

│ 921 def main(): │

│ │

│ c:\Lora\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py:580 in simple_launcher │

│ │

│ 577 │ process.wait() │

│ 578 │ if process.returncode != 0: │

│ 579 │ │ if not args.quiet: │

│ ❱ 580 │ │ │ raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) │

│ 581 │ │ else: │

│ 582 │ │ │ sys.exit(1) │

│ 583 │

╰──────────────────────────────────────────────────────────────────────────────────────────────────╯

CalledProcessError: Command '['c:\\Lora\\kohya_ss\\venv\\Scripts\\python.exe', './sd-scripts/sdxl_train_network.py',

'--pretrained_model_name_or_path=./Stable-diffusion/dreamshaperXL10_alpha2Xl10.safetensors', '--output_dir=./output',

'--logging_dir=./logs', '--resolution=1024,1024', '--max_train_epochs=40', '--learning_rate=2e-4',

'--lr_scheduler=constant_with_warmup', '--output_name=sdxl_8glora', '--train_batch_size=1', '--save_every_n_epochs=10',

'--save_precision=bf16', '--seed=1026', '--max_token_length=225', '--caption_extension=.txt',

'--save_model_as=safetensors', '--vae_batch_size=4', '--xformers', '--cache_text_encoder_outputs',

'--cache_text_encoder_outputs_to_disk', '--bucket_reso_steps=32', '--train_data_dir=./input/', '--clip_skip=2',

'--network_dim=32', '--network_alpha=16', "--training_comment=this LoRA model created from bdsqlsz by bdsqlsz'script",

'--persistent_data_loader_workers', '--cache_latents', '--cache_latents_to_disk', '--gradient_checkpointing',

'--noise_offset=0.0375', '--adaptive_noise_scale=0.0375', '--optimizer_type=PagedAdamW8bit', '--optimizer_args',

'weight_decay=0.01', '--network_train_unet_only', '--unet_lr=1e-5', '--text_encoder_lr=2e-5', '--keep_tokens=1',

'--min_snr_gamma=5', '--lr_scheduler_num_cycles=1', '--enable_bucket', '--min_bucket_reso=640',

'--max_bucket_reso=1536', '--full_bf16', '--mixed_precision=bf16', '--network_module=networks.lora',

'--lr_warmup_steps=50']' returned non-zero exit status 1.

Train finished

@bdsqlsz Thank you, it seems to working.

@bdsqlsz Thank you so much, I have tested it by sdxl lora and db with same parameter and datasets (high steps). 我用kohya 在我电脑跑有问题，解决起来还麻烦 要扩盘····多亏了青龙大佬的脚本了！love u.

@bdsqlsz Thank you