prepare tokenizer

update token length: 225

Use DreamBooth method.

prepare train images.

found directory 5_chunmomo contains 13 image files

illegal char in file (not UTF-8) / ファイルにUTF-8以外の文字があります: ./train/chunmomo\5_chunmomo\00001-0-0a341773ef734124087e3.txt

Traceback (most recent call last):

?File "I:\BaiduYunDownload\lora-scripts\sd-scripts\train_network.py", line 497, in <module>

??train(args)

?File "I:\BaiduYunDownload\lora-scripts\sd-scripts\train_network.py", line 61, in train

??train_dataset = DreamBoothDataset(args.train_batch_size, args.train_data_dir, args.reg_data_dir,

?File "I:\BaiduYunDownload\lora-scripts\sd-scripts\library\train_util.py", line 763, in __init__

??n_repeats, img_paths, captions = load_dreambooth_dir(os.path.join(train_data_dir, dir))

?File "I:\BaiduYunDownload\lora-scripts\sd-scripts\library\train_util.py", line 752, in load_dreambooth_dir

??cap_for_img = read_caption(img_path)

?File "I:\BaiduYunDownload\lora-scripts\sd-scripts\library\train_util.py", line 727, in read_caption

??raise e

?File "I:\BaiduYunDownload\lora-scripts\sd-scripts\library\train_util.py", line 724, in read_caption

??lines = f.readlines()

?File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\codecs.py", line 322, in decode

??(result, consumed) = self._buffer_decode(data, self.errors, final)

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa3 in position 161: invalid start byte

Traceback (most recent call last):

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

??exec(code, run_globals)

?File "I:\BaiduYunDownload\lora-scripts\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>

?File "I:\BaiduYunDownload\lora-scripts\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main

??args.func(args)

?File "I:\BaiduYunDownload\lora-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command

??simple_launcher(args)

?File "I:\BaiduYunDownload\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 '['I:\\BaiduYunDownload\\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/chunmomo', '--output_dir=./output', '--logging_dir=./logs', '--resolution=512,512', '--network_module=networks.lora', '--max_train_epochs=10', '--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=chunmomo_train', '--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=safetensors', '--min_bucket_reso=256', '--max_bucket_reso=1024', '--xformers', '--shuffle_caption', '--network_train_unet_only', '--use_8bit_adam']' returned non-zero exit status 1.

Train finished

各位可以注意下訓(xùn)練集里面的TXT的格式，要求UTF-8，我不知道啥時(shí)候改掉了，然后就出了這個(gè)錯(cuò)誤，好在不算大問(wèn)題