【AI绘画】最佳人物模型训练！保姆式LoRA模型训练教程 一键包发布

prepare tokenizer

update token length: 225

Use DreamBooth method.

prepare train images.

found directory 6_qubit contains 113 image files

678 train images with repeating.

loading image sizes.

100%|██████████████████████████████████████████████████████████████████████████████| 113/113 [00:00<00:00, 3149.99it/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 (320, 320), count: 678

mean ar error (without repeats): 0.0

prepare accelerator

Using accelerator 0.15.0 or above.

load Diffusers pretrained models

Traceback (most recent call last):

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\diffusers\configuration_utils.py", line 326, in load_config

  config_file = hf_hub_download(

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn

  validate_repo_id(arg_value)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 166, in validate_repo_id

  raise HFValidationError(

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './sd-models/model.ckpt'. Use `repo_type` argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

 File "D:\stable diffusion\lora训练\lora-scripts\sd-scripts\train_network.py", line 548, in <module>

  train(args)

 File "D:\stable diffusion\lora训练\lora-scripts\sd-scripts\train_network.py", line 156, in train

  text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype)

 File "D:\stable diffusion\lora训练\lora-scripts\sd-scripts\library\train_util.py", line 1587, in load_target_model

  pipe = StableDiffusionPipeline.from_pretrained(args.pretrained_model_name_or_path, tokenizer=None, safety_checker=None)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\diffusers\pipeline_utils.py", line 454, in from_pretrained

  config_dict = cls.load_config(

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\diffusers\configuration_utils.py", line 363, in load_config

  raise EnvironmentError(

OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like ./sd-models/model.ckpt is not the path to a directory containing a model_index.json file.

Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Traceback (most recent call last):

 File "C:\Users\1\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\1\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code

  exec(code, run_globals)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main

  args.func(args)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command

  simple_launcher(args)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher

  raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)

subprocess.CalledProcessError: Command '['D:\\stable diffusion\\lora训练\\lora-scripts\\venv\\Scripts\\python.exe', './sd-scripts/train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=./sd-models/model.ckpt', '--train_data_dir=./train/qubit', '--output_dir=./output', '--logging_dir=./logs', '--resolution=350,350', '--network_module=networks.lora', '--max_train_epochs=15', '--learning_rate=1e-4', '--unet_lr=1e-4', '--text_encoder_lr=1e-5', '--lr_scheduler=cosine_with_restarts', '--lr_warmup_steps=0', '--network_dim=32', '--network_alpha=32', '--output_name=qubit', '--train_batch_size=1', '--save_every_n_epochs=2', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1337', '--cache_latents', '--clip_skip=2', '--prior_loss_weight=1', '--max_token_length=225', '--caption_extension=.txt', '--save_model_as=ckpt', '--min_bucket_reso=256', '--max_bucket_reso=1024']' returned non-zero exit status 1.

Train finished

大佬们！求求帮忙看看问题！！刚开始运行就不行了，翻译过来好像看中间有一个错误：

OSError:我们无法连接到'https://huggingface.co'加载此模型，在缓存文件中找不到它，它看起来像/sd models/model.ckpt不是包含modelindex.json文件的目录的路径。

全部代码是这些：

prepare tokenizer

update token length: 225

Use DreamBooth method.

prepare train images.

found directory 6_qubit contains 113 image files

678 train images with repeating.

loading image sizes.

100%|██████████████████████████████████████████████████████████████████████████████| 113/113 [00:00<00:00, 3061.75it/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 (320, 320), count: 678

mean ar error (without repeats): 0.0

prepare accelerator

Using accelerator 0.15.0 or above.

load Diffusers pretrained models

Traceback (most recent call last):

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\diffusers\configuration_utils.py", line 326, in load_config

  config_file = hf_hub_download(

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn

  validate_repo_id(arg_value)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 166, in validate_repo_id

  raise HFValidationError(

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './sd-models/model.ckpt'. Use `repo_type` argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

 File "D:\stable diffusion\lora训练\lora-scripts\sd-scripts\train_network.py", line 548, in <module>

  train(args)

 File "D:\stable diffusion\lora训练\lora-scripts\sd-scripts\train_network.py", line 156, in train

  text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype)

 File "D:\stable diffusion\lora训练\lora-scripts\sd-scripts\library\train_util.py", line 1587, in load_target_model

  pipe = StableDiffusionPipeline.from_pretrained(args.pretrained_model_name_or_path, tokenizer=None, safety_checker=None)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\diffusers\pipeline_utils.py", line 454, in from_pretrained

  config_dict = cls.load_config(

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\diffusers\configuration_utils.py", line 363, in load_config

  raise EnvironmentError(

OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like ./sd-models/model.ckpt is not the path to a directory containing a model_index.json file.

Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Traceback (most recent call last):

 File "C:\Users\1\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\1\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code

  exec(code, run_globals)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main

  args.func(args)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command

  simple_launcher(args)

 File "D:\stable diffusion\lora训练\lora-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher

  raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)

subprocess.CalledProcessError: Command '['D:\\stable diffusion\\lora训练\\lora-scripts\\venv\\Scripts\\python.exe', './sd-scripts/train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=./sd-models/model.ckpt', '--train_data_dir=./train/qubit', '--output_dir=./output', '--logging_dir=./logs', '--resolution=350,350', '--network_module=networks.lora', '--max_train_epochs=15', '--learning_rate=1e-4', '--unet_lr=1e-4', '--text_encoder_lr=1e-5', '--lr_scheduler=cosine_with_restarts', '--lr_warmup_steps=0', '--network_dim=32', '--network_alpha=32', '--output_name=qubit', '--train_batch_size=1', '--save_every_n_epochs=2', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1337', '--cache_latents', '--clip_skip=2', '--prior_loss_weight=1', '--max_token_length=225', '--caption_extension=.txt', '--save_model_as=ckpt', '--min_bucket_reso=256', '--max_bucket_reso=1024']' returned non-zero exit status 1.

Train finished