Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- =============================================================
- Modules installed outside the virtual environment were found.
- This can cause issues. Please review the installed modules.
- You can uninstall all local modules with:
- deactivate
- pip freeze > uninstall.txt
- pip uninstall -y -r uninstall.txt
- =============================================================
- 12:36:37-242693 INFO Version: v21.8.8
- 12:36:37-246701 INFO nVidia toolkit detected
- 12:36:38-654884 INFO Torch 2.0.1+cu118
- 12:36:38-677883 INFO Torch backend: nVidia CUDA 11.8 cuDNN 8700
- 12:36:38-679883 INFO Torch detected GPU: NVIDIA GeForce RTX 2080 SUPER VRAM 8192 Arch (7, 5) Cores 48
- 12:36:38-680892 INFO Verifying modules instalation status from requirements_windows_torch2.txt...
- 12:36:38-681883 INFO Verifying modules instalation status from requirements.txt...
- 12:36:40-930009 INFO headless: False
- 12:36:40-936022 INFO Load CSS...
- Running on local URL: http://127.0.0.1:7860
- To create a public link, set `share=True` in `launch()`.
- 12:41:45-191609 INFO Skipping folder .gitkeep because it does not match kohya_ss expected syntax...
- 12:41:45-192619 INFO Skipping folder Kc.01.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-193608 INFO Skipping folder Kc.02.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-194608 INFO Skipping folder Kc.03.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-195608 INFO Skipping folder Kc.04.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-195608 INFO Skipping folder Kc.05.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-196617 INFO Skipping folder Kc.06.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-197608 INFO Skipping folder Kc.07.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-197608 INFO Skipping folder Kc.08.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-198608 INFO Skipping folder Kc.09.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-199608 INFO Skipping folder Kc.10.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-200608 INFO Skipping folder Kc.11.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-200608 INFO Skipping folder Kc.12.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-201608 INFO Skipping folder Kc.13.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-202617 INFO Skipping folder Kc.14.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-202617 INFO Skipping folder Kc.15.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-203609 INFO Skipping folder Kc.16.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-203609 INFO Skipping folder Kc.17.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-204947 INFO Skipping folder Kc.18.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-205938 INFO Skipping folder Kc.20.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-205938 INFO Skipping folder Kc.21.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-206938 INFO Skipping folder Kc.22.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-207947 INFO Skipping folder Kc.23.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-208948 INFO Skipping folder Kc.24.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-209938 INFO Skipping folder Kc.25.jpg because it does not match kohya_ss expected syntax...
- 12:41:45-210947 INFO Skipping folder Kc.26.jpg because it does not match kohya_ss expected syntax...
- 12:44:06-051960 INFO Copy F:\sd.CΩDE\FaceDataSets\kc\512 to F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img/20_Kc
- woman...
- 12:44:06-066519 INFO Regularization images directory is missing... not copying regularisation images...
- 12:44:06-067517 INFO Done creating kohya_ss training folder structure at F:\sd.CΩDE\FaceDataSets\kc\Training
- Directory...
- 12:56:47-210913 INFO Start training LoRA Standard ...
- 12:56:47-212432 INFO Checking for duplicate image filenames in training data directory...
- 12:56:47-214449 INFO Valid image folder names found in: F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img
- 12:56:47-215449 INFO Folder 20_Kc woman: 25 images found
- 12:56:47-216451 INFO Folder 20_Kc woman: 500 steps
- 12:56:47-217450 INFO Total steps: 500
- 12:56:47-218450 INFO Train batch size: 1
- 12:56:47-219443 INFO Gradient accumulation steps: 1
- 12:56:47-219443 INFO Epoch: 10
- 12:56:47-220449 INFO Regulatization factor: 1
- 12:56:47-221955 INFO max_train_steps (500 / 1 / 1 * 10 * 1) = 5000
- 12:56:47-222960 INFO stop_text_encoder_training = 0
- 12:56:47-223959 INFO lr_warmup_steps = 0
- 12:56:47-225959 INFO Saving training config to F:\sd.CΩDE\FaceDataSets\kc\Training
- Directory\model\Kc_person_mine_20230826-125647.json...
- 12:56:47-227960 INFO accelerate launch --num_cpu_threads_per_process=2 "./sdxl_train_network.py" --enable_bucket
- --min_bucket_reso=256 --max_bucket_reso=2048
- --pretrained_model_name_or_path="F:/sd.CΩDE/sd.webui/webui/models/Stable-diffusion/sd_xl_base_1 .0.safetensors" --train_data_dir="F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img"
- --resolution="1024,1024" --output_dir="F:\sd.CΩDE\FaceDataSets\kc\Training Directory\model"
- --logging_dir="F:\sd.CΩDE\FaceDataSets\kc\Training Directory\log" --network_alpha="1"
- --save_model_as=safetensors --network_module=networks.lora --text_encoder_lr=1e-05
- --unet_lr=0.0001 --network_dim=256 --output_name="Kc_person_mine"
- --lr_scheduler_num_cycles="10" --no_half_vae --learning_rate="0.0001" --lr_scheduler="cosine"
- --train_batch_size="1" --max_train_steps="5000" --save_every_n_epochs="1"
- --mixed_precision="bf16" --save_precision="bf16" --cache_latents --cache_latents_to_disk
- --optimizer_type="AdamW8bit" --optimizer_args scale_parameter=False relative_step=False
- warmup_init=False --max_data_loader_n_workers="0" --bucket_reso_steps=64 --xformers
- --bucket_no_upscale --noise_offset=0.0
- A matching Triton is not available, some optimizations will not be enabled.
- Error caught was: No module named 'triton'
- prepare tokenizers
- Downloading (…)olve/main/vocab.json: 100%|██████████████████████████████████████████| 961k/961k [00:00<00:00, 8.88MB/s]
- F:\sd.CΩDE\kohya\kohya_ss\venv\lib\site-packages\huggingface_hub\file_download.py:133: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\Users\lee\.cache\huggingface\hub. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
- To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
- warnings.warn(message)
- Downloading (…)olve/main/merges.txt: 100%|██████████████████████████████████████████| 525k/525k [00:00<00:00, 15.0MB/s]
- Downloading (…)cial_tokens_map.json: 100%|████████████████████████████████████████████████████| 389/389 [00:00<?, ?B/s]
- Downloading (…)okenizer_config.json: 100%|████████████████████████████████████████████████████| 905/905 [00:00<?, ?B/s]
- Downloading (…)olve/main/vocab.json: 100%|██████████████████████████████████████████| 862k/862k [00:00<00:00, 31.6MB/s]
- Downloading (…)olve/main/merges.txt: 100%|██████████████████████████████████████████| 525k/525k [00:00<00:00, 15.9MB/s]
- Downloading (…)cial_tokens_map.json: 100%|████████████████████████████████████████████████████| 389/389 [00:00<?, ?B/s]
- Downloading (…)okenizer_config.json: 100%|████████████████████████████████████████████████████| 904/904 [00:00<?, ?B/s]
- Using DreamBooth method.
- prepare images.
- found directory F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman contains 25 image files
- No caption file found for 25 images. Training will continue without captions for these images. If class token exists, it will be used. / 25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。
- F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman\Kc.01.jpg
- F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman\Kc.02.jpg
- F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman\Kc.03.jpg
- F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman\Kc.04.jpg
- F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman\Kc.05.jpg
- F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman\Kc.06.jpg... and 20 more
- 500 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: (1024, 1024)
- enable_bucket: True
- min_bucket_reso: 256
- max_bucket_reso: 2048
- bucket_reso_steps: 64
- bucket_no_upscale: True
- [Subset 0 of Dataset 0]
- image_dir: "F:\sd.CΩDE\FaceDataSets\kc\Training Directory\img\20_Kc woman"
- image_count: 25
- num_repeats: 20
- 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: Kc woman
- caption_extension: .caption
- [Dataset 0]
- loading image sizes.
- 100%|█████████████████████████████████████████████████████████████████████████████████| 25/25 [00:00<00:00, 238.95it/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: 500
- mean ar error (without repeats): 0.0
- preparing accelerator
- ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
- │ F:\sd.CΩDE\kohya\kohya_ss\sdxl_train_network.py:176 in <module> │
- │ │
- │ 173 │ args = train_util.read_config_from_file(args, parser) │
- │ 174 │ │
- │ 175 │ trainer = SdxlNetworkTrainer() │
- │ ❱ 176 │ trainer.train(args) │
- │ 177 │
- │ │
- │ F:\sd.CΩDE\kohya\kohya_ss\train_network.py:206 in train │
- │ │
- │ 203 │ │ │
- │ 204 │ │ # acceleratorを準備する │
- │ 205 │ │ print("preparing accelerator") │
- │ ❱ 206 │ │ accelerator = train_util.prepare_accelerator(args) │
- │ 207 │ │ is_main_process = accelerator.is_main_process │
- │ 208 │ │ │
- │ 209 │ │ # mixed precisionに対応した型を用意しておき適宜castする │
- │ │
- │ F:\sd.CΩDE\kohya\kohya_ss\library\train_util.py:3725 in prepare_accelerator │
- │ │
- │ 3722 │ │ │ if args.wandb_api_key is not None: │
- │ 3723 │ │ │ │ wandb.login(key=args.wandb_api_key) │
- │ 3724 │ │
- │ ❱ 3725 │ accelerator = Accelerator( │
- │ 3726 │ │ gradient_accumulation_steps=args.gradient_accumulation_steps, │
- │ 3727 │ │ mixed_precision=args.mixed_precision, │
- │ 3728 │ │ log_with=log_with, │
- │ │
- │ F:\sd.CΩDE\kohya\kohya_ss\venv\lib\site-packages\accelerate\accelerator.py:442 in __init__ │
- │ │
- │ 439 │ │ │ else: │
- │ 440 │ │ │ │ self.native_amp = is_bf16_available(True) │
- │ 441 │ │ │ if mixed_precision == "bf16" and not self.native_amp and not is_tpu_availabl │
- │ ❱ 442 │ │ │ │ raise ValueError(err.format(mode="bf16", requirement="PyTorch >= 1.10 an │
- │ 443 │ │ │
- │ 444 │ │ # Start of internal step tracking │
- │ 445 │ │ self.step = 0 │
- ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
- ValueError: bf16 mixed precision requires PyTorch >= 1.10 and a supported device.
- ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
- │ C:\Users\lee\AppData\Local\Programs\Python\Python310\lib\runpy.py:196 in _run_module_as_main │
- │ │
- │ 193 │ main_globals = sys.modules["__main__"].__dict__ │
- │ 194 │ if alter_argv: │
- │ 195 │ │ sys.argv[0] = mod_spec.origin │
- │ ❱ 196 │ return _run_code(code, main_globals, None, │
- │ 197 │ │ │ │ │ "__main__", mod_spec) │
- │ 198 │
- │ 199 def run_module(mod_name, init_globals=None, │
- │ │
- │ C:\Users\lee\AppData\Local\Programs\Python\Python310\lib\runpy.py:86 in _run_code │
- │ │
- │ 83 │ │ │ │ │ __loader__ = loader, │
- │ 84 │ │ │ │ │ __package__ = pkg_name, │
- │ 85 │ │ │ │ │ __spec__ = mod_spec) │
- │ ❱ 86 │ exec(code, run_globals) │
- │ 87 │ return run_globals │
- │ 88 │
- │ 89 def _run_module_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 │
- │ │
- │ F:\sd.CΩDE\kohya\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__": │
- │ │
- │ F:\sd.CΩDE\kohya\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(): │
- │ │
- │ F:\sd.CΩDE\kohya\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 '['F:\\sd.CΩDE\\kohya\\kohya_ss\\venv\\Scripts\\python.exe', './sdxl_train_network.py',
- '--enable_bucket', '--min_bucket_reso=256', '--max_bucket_reso=2048',
- '--pretrained_model_name_or_path=F:/sd.CΩDE/sd.webui/webui/models/Stable-diffusion/sd_xl_base_1.0.safetensors',
- '--train_data_dir=F:\\sd.CΩDE\\FaceDataSets\\kc\\Training Directory\\img', '--resolution=1024,1024',
- '--output_dir=F:\\sd.CΩDE\\FaceDataSets\\kc\\Training Directory\\model',
- '--logging_dir=F:\\sd.CΩDE\\FaceDataSets\\kc\\Training Directory\\log', '--network_alpha=1',
- '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=1e-05', '--unet_lr=0.0001',
- '--network_dim=256', '--output_name=Kc_person_mine', '--lr_scheduler_num_cycles=10', '--no_half_vae',
- '--learning_rate=0.0001', '--lr_scheduler=cosine', '--train_batch_size=1', '--max_train_steps=5000',
- '--save_every_n_epochs=1', '--mixed_precision=bf16', '--save_precision=bf16', '--cache_latents',
- '--cache_latents_to_disk', '--optimizer_type=AdamW8bit', '--optimizer_args', 'scale_parameter=False',
- 'relative_step=False', 'warmup_init=False', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--xformers',
- '--bucket_no_upscale', '--noise_offset=0.0']' returned non-zero exit status 1.
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement