Open max-k54 opened 1 week ago
U sure that you choose LORA from tab (not Dreambooth)?
U sure that you choose LORA from tab (not Dreambooth)?
Yes i chose the lora section
Yes i chose the lora section
Are you sure? If you did, your log should contain a few mentions of train_network
but I'm seeing sdxl_train.py
which sounds like Dreambooth.
NEED HELP, getting this issue when training Lora in Kohya SS
11:00:26-382341 INFO Command executed.
2024-09-21 11:00:40 INFO Loading settings from D:\sd\oil train_util.py:4174
paint\loras\model/config_dreambooth-20240921-110026.toml...
INFO D:\sd\oil paint\loras\model/config_dreambooth-20240921-110026 train_util.py:4193
WARNING clip_skip will be unexpected / SDXL学習ではclip_skipは動作しません sdxl_train_util.py:352
2024-09-21 11:00:40 INFO prepare tokenizers sdxl_train_util.py:138
2024-09-21 11:00:42 INFO update token length: 75 sdxl_train_util.py:163
INFO Using DreamBooth method. sdxl_train.py:144
INFO prepare images. train_util.py:1815
INFO found directory D:\sd\oil paint\loras\img\20_ohwx man contains 12 image train_util.py:1762
files
WARNING No caption file found for 12 images. Training will continue without train_util.py:1793
captions for these images. If class token exists, it will be used. /
12枚の画像にキャプションファイルが見つかりませんでした。これらの画像につ
いてはキャプションなしで学習を続行します。class
tokenが存在する場合はそれを使います。
WARNING D:\sd\oil paint\loras\img\20_ohwx man\mordecai (1).png train_util.py:1800
WARNING D:\sd\oil paint\loras\img\20_ohwx man\mordecai (10).png train_util.py:1800
WARNING D:\sd\oil paint\loras\img\20_ohwx man\mordecai (11).png train_util.py:1800
WARNING D:\sd\oil paint\loras\img\20_ohwx man\mordecai (12).png train_util.py:1800
WARNING D:\sd\oil paint\loras\img\20_ohwx man\mordecai (2).png train_util.py:1800
WARNING D:\sd\oil paint\loras\img\20_ohwx man\mordecai (3).png... and 7 more train_util.py:1798
INFO 240 train images with repeating. train_util.py:1856
INFO 0 reg images. train_util.py:1859
WARNING no regularization images / 正則化画像が見つかりませんでした train_util.py:1864
INFO [Dataset 0] config_util.py:572
batch_size: 1
resolution: (768, 768)
enable_bucket: True
network_multiplier: 1.0
min_bucket_reso: 256
max_bucket_reso: 2048
bucket_reso_steps: 64
bucket_no_upscale: True
[Subset 0 of Dataset 0]
image_dir: "D:\sd\oil paint\loras\img\20_ohwx man"
image_count: 12
num_repeats: 20
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: ohwx man
caption_extension: .txt
INFO [Dataset 0] config_util.py:578
INFO loading image sizes. train_util.py:911
100%|█████████████████████████████████████████████████████████████████████████████████| 12/12 [00:00<00:00, 160.37it/s]
INFO make buckets train_util.py:917
WARNING min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is train_util.py:934
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:963
各bucketの画像枚数(繰り返し回数を含む)
INFO bucket 0: resolution (768, 768), count: 240 train_util.py:968
INFO mean ar error (without repeats): 0.0 train_util.py:973
INFO prepare accelerator sdxl_train.py:201
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/sd.webui/webui/models/Stable-diffusion/sd_xl_base_1.0.safetenso
rs
Traceback (most recent call last):
File "C:\Users\smart\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\smart\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\sd\kohya_ss\venv\Scripts\accelerate.EXEmain.py", line 7, in
File "D:\sd\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 47, in main
args.func(args)
File "D:\sd\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1017, in launch_command
simple_launcher(args)
File "D:\sd\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 637, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['D:\sd\kohya_ss\venv\Scripts\python.exe', 'D:/sd/kohya_ss/sd-scripts/sdxl_train.py', '--config_file', 'D:\sd\oil paint\loras\model/config_dreambooth-20240921-110026.toml']' returned non-zero exit status 3221225477.
11:01:00-603863 INFO Training has ended.