【赛博Coser】定制你的模特！LoRA手把手教学，让你也能训练专属于自己的AI
求教
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 (320, 640), count: 100
bucket 1: resolution (320, 704), count: 200
bucket 2: resolution (384, 512), count: 100
bucket 3: resolution (448, 448), count: 100
bucket 4: resolution (512, 384), count: 200
bucket 5: resolution (640, 384), count: 200
mean ar error (without repeats): 0.03227657071391427
prepare accelerator
Traceback (most recent call last):
File "H:\ai\1\kohya_ss\train_db.py", line 346, in <module>
train(args)
File "H:\ai\1\kohya_ss\train_db.py", line 62, in train
accelerator, unwrap_model = train_util.prepare_accelerator(args)
File "H:\ai\1\kohya_ss\library\train_util.py", line 1817, in prepare_accelerator
accelerator = Accelerator(gradient_accumulation_steps=args.gradient_accumulation_steps, mixed_precision=args.mixed_precision,
File "H:\ai\1\kohya_ss\venv\lib\site-packages\accelerate\accelerator.py", line 355, in __init__
raise ValueError(err.format(mode="fp16", requirement="a GPU"))
ValueError: fp16 mixed precision requires a GPU
Traceback (most recent call last):
File "C:\Users\35646\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\35646\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "H:\ai\1\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>
File "H:\ai\1\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "H:\ai\1\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
simple_launcher(args)
File "H:\ai\1\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['H:\\ai\\1\\kohya_ss\\venv\\Scripts\\python.exe', 'train_db.py', '--enable_bucket', '--pretrained_model_name_or_path=H:/ai/stable d/stable-diffusion-webui/models/Stable-diffusion/chilloutmix_NiPrunedFp32Fix.safetensors', '--train_data_dir=H:/ai/LORABASE/TEST1/image', '--resolution=512,512', '--output_dir=H:/ai/LORABASE/TEST1/model', '--logging_dir=H:/ai/LORABASE/TEST1/log', '--save_model_as=safetensors', '--output_name=last', '--learning_rate=1e-5', '--lr_scheduler=cosine', '--lr_warmup_steps=45', '--train_batch_size=2', '--max_train_steps=450', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1234', '--cache_latents', '--optimizer_type=AdamW', '--bucket_reso_steps=64', '--mem_eff_attn', '--gradient_checkpointing', '--xformers', '--use_8bit_adam', '--bucket_no_upscale']' returned non-zero exit status 1.
