kohya-ss / kohya-ss/sd-scripts

error running sdxl_train_network.py in WSL

Open
#1,069 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

i am trying to run sd_scripts in windows subsystem for linux because windows doesn't have support for all the optimization libraries, but the sdxl_train_network.py command does not work for me. here is the error that i get when i try to run it

prepare tokenizers
update token length: 225
Using DreamBooth method.
Traceback (most recent call last):
  File "/home/antrobot/sd-scripts/./sdxl_train_network.py", line 184, in <module>
    trainer.train(args)
  File "/home/antrobot/sd-scripts/train_network.py", line 193, in train
    train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
  File "/home/antrobot/sd-scripts/library/config_util.py", line 460, in generate_dataset_group_by_blueprint
    dataset = dataset_klass(subsets=subsets, **asdict(dataset_blueprint.params))
  File "/home/antrobot/sd-scripts/library/train_util.py", line 1771, in __init__
    self.dreambooth_dataset_delegate = DreamBoothDataset(
TypeError: DreamBoothDataset.__init__() missing 1 required positional argument: 'debug_dataset'
Traceback (most recent call last):
  File "/home/antrobot/sd-scripts/venv/bin/accelerate", line 8, in <module>
    sys.exit(main())
  File "/home/antrobot/sd-scripts/venv/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 47, in main
    args.func(args)
  File "/home/antrobot/sd-scripts/venv/lib/python3.10/site-packages/accelerate/commands/launch.py", line 1017, in launch_command
    simple_launcher(args)
  File "/home/antrobot/sd-scripts/venv/lib/python3.10/site-packages/accelerate/commands/launch.py", line 637, in simple_launcher
    raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/antrobot/sd-scripts/venv/bin/python3', './sdxl_train_network.py', '--logging_dir=logs', '--log_prefix=Welwraith', '--network_module=networks.lora', '--max_data_loader_n_workers=1', '--persistent_data_loader_workers', '--caption_extension=.txt', '--shuffle_caption', '--keep_tokens=1', '--max_token_length=225', '--prior_loss_weight=1', '--mixed_precision=bf16', '--save_precision=bf16', '--xformers', '--cache_latents', '--cache_latents_to_disk', '--save_model_as=safetensors', '--train_data_dir=./.image-dir/', '--output_dir=./.output/Welwraith_1', '--reg_data_dir=./.reg-dir/', '--pretrained_model_name_or_path=/mnt/d/Stable Diffusion Projects/stable-diffusion-webui/models/Stable-diffusion/ponyDiffusionV6XL_v6StartWithThisOne.safetensors', '--output_name=Welwraith_1', '--learning_rate=5E-05', '--text_encoder_lr=5E-05', '--max_train_steps=2000', '--resolution=768', '--enable_bucket', '--min_bucket_reso=576', '--max_bucket_reso=960', '--train_batch_size=1', '--network_dim=64', '--network_alpha=64', '--optimizer_type=AdamW8Bit', '--lr_scheduler=cosine', '--noise_offset=0.01', '--seed=0', '--sample_sampler=k_euler_a', '--gradient_accumulation_steps=1', '--save_every_n_steps=400', '--sample_every_n_steps=200', '--sample_prompts=./.output/prompt.txt', '--gradient_checkpointing', '--flip_aug', '--network_dropout=0.3', '--scale_weight_norms=3', '--min_snr_gamma=5', '--fp8_base', '--optimizer_args', 'betas=0.9, 0.99', 'weight_decay=0']' returned non-zero exit status 1.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the command in WSL, then read sdxl_train_network.py, train_network.py, library/config_util.py, and library/train_util.py around the traceback. Trace how DreamBoothDataset is instantiated and verify that dataset setup completes without the missing-argument TypeError.

Written by the indexing model from the issue text.

Assessment

Tech stack
linux, python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.