Regularisation images are used... Will double the number of steps required...
max_train_steps = 1920
stop_text_encoder_training = 0
lr_warmup_steps = 192
accelerate launch --num_cpu_threads_per_process=2 "train_db.py" --enable_bucket --pretrained_model_name_or_path="C:/SD/stable-diffusion-webui/models/Stable-diffusion/realisticVisionV20_v20.safetensors" --train_data_dir="C:/SD/training/Kohya video/img" --reg_data_dir="C:/SD/training/Kohya video/reg" --resolution=512,512 --output_dir="C:/SD/training/Kohya video/model" --logging_dir="C:/SD/training/Kohya video/log" --save_model_as=safetensors --output_name="test1" --max_data_loader_n_workers="0" --learning_rate="0.0001" --lr_scheduler="cosine" --lr_warmup_steps="192" --train_batch_size="1" --max_train_steps="1920" --save_every_n_epochs="1" --mixed_precision="no" --save_precision="float" --optimizer_type="AdamW8bit" --max_data_loader_n_workers="0" --bucket_reso_steps=64 --mem_eff_attn --gradient_checkpointing --bucket_no_upscale
prepare tokenizer
prepare images.
found directory C:\SD\training\Kohya video\img\40_FHDMNSX manchester united player portrait contains 8 image files
found directory C:\SD\training\Kohya video\reg\1_manchester united player portrait contains 323 image files
320 train images with repeating.
323 reg images.
some of reg images are not used / 正則化画像の数が多いので、一部使用されない正則化画像があります
[Dataset 0]
  batch_size: 1
  resolution: (512, 512)
  enable_bucket: True
  min_bucket_reso: 256
  max_bucket_reso: 1024
  bucket_reso_steps: 64
  bucket_no_upscale: True

  [Subset 0 of Dataset 0]
    image_dir: "C:\SD\training\Kohya video\img\40_FHDMNSX manchester united player portrait"
    image_count: 8
    num_repeats: 40
    shuffle_caption: False
    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: FHDMNSX manchester united player portrait
    caption_extension: .caption

  [Subset 1 of Dataset 0]
    image_dir: "C:\SD\training\Kohya video\reg\1_manchester united player portrait"
    image_count: 323
    num_repeats: 1
    shuffle_caption: False
    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: True
    class_tokens: manchester united player portrait
    caption_extension: .caption


[Dataset 0]
loading image sizes.
100%|██████████████████████████████████████████████████████████████████████████████| 328/328 [00:00<00:00, 2232.92it/s]
make buckets
min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is 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
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, 512), count: 640
mean ar error (without repeats): 0.0
prepare accelerator
Using accelerator 0.15.0 or above.
load StableDiffusion checkpoint
loading u-net: <All keys matched successfully>
loading vae: <All keys matched successfully>
loading text encoder: <All keys matched successfully>
Replace CrossAttention.forward to use FlashAttention (not xformers)
prepare optimizer, data loader etc.

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link
================================================================================
CUDA SETUP: Loading binary C:\kohya_ss\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda116.dll...
use 8-bit AdamW optimizer | {}
running training / 学習開始
  num train images * repeats / 学習画像の数×繰り返し回数: 320
  num reg images / 正則化画像の数: 323
  num batches per epoch / 1epochのバッチ数: 640
  num epochs / epoch数: 3
  batch size per device / バッチサイズ: 1
  total train batch size (with parallel & distributed & accumulation) / 総バッチサイズ（並列学習、勾配合計含む）: 1
  gradient ccumulation steps / 勾配を合計するステップ数 = 1
  total optimization steps / 学習ステップ数: 1920
steps:   0%|                                                                                  | 0/1920 [00:00<?, ?it/s]epoch 1/3
Error an illegal memory access was encountered at line 167 in file D:\ai\tool\bitsandbytes\csrc\ops.cu
Traceback (most recent call last):
  File "C:\Users\Kashyap\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\Kashyap\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>
  File "C:\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
    args.func(args)
  File "C:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
    simple_launcher(args)
  File "C:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher
    raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['C:\\kohya_ss\\venv\\Scripts\\python.exe', 'train_db.py', '--enable_bucket', '--pretrained_model_name_or_path=C:/SD/stable-diffusion-webui/models/Stable-diffusion/realisticVisionV20_v20.safetensors', '--train_data_dir=C:/SD/training/Kohya video/img', '--reg_data_dir=C:/SD/training/Kohya video/reg', '--resolution=512,512', '--output_dir=C:/SD/training/Kohya video/model', '--logging_dir=C:/SD/training/Kohya video/log', '--save_model_as=safetensors', '--output_name=test1', '--max_data_loader_n_workers=0', '--learning_rate=0.0001', '--lr_scheduler=cosine', '--lr_warmup_steps=192', '--train_batch_size=1', '--max_train_steps=1920', '--save_every_n_epochs=1', '--mixed_precision=no', '--save_precision=float', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--mem_eff_attn', '--gradient_checkpointing', '--bucket_no_upscale']' returned non-zero exit status 1.