bmaltais
commented
4 months ago Does this image exist? the sd-script complain it can't find it: D:\github\lora\images\10_level\1.jpg
You may have to open an issue with kohya directly at https://github.com/kohya-ss/sd-scripts as this appear to be something his script is reporting and not the GUI.
Can't use finetune after updating to latest version.
2024-05-22 19:14:33 INFO found 140 images. prepare_buckets_latents.py:70 INFO loading existing metadata: meta_cap.json prepare_buckets_latents.py:73 INFO load VAE: model_util.py:1268 D:/github/stable-diffusion-webui/models/Stable-diffusion/sd1.5/v1-5-prun ed-emaonly.safetensors 100%|████████████████████████████████████████████████████████████████████████████████| 140/140 [00:30<00:00, 4.54it/s] 2024-05-22 19:15:04 INFO bucket 0 (640, 384): 140 prepare_buckets_latents.py:194 INFO mean ar error: 0.11111111111111094 prepare_buckets_latents.py:196 INFO writing metadata: meta_lat.json prepare_buckets_latents.py:199 INFO done! prepare_buckets_latents.py:202 19:15:05-197253 INFO image_num = 140 19:15:05-198252 INFO repeats = 140 19:15:05-199252 INFO Max train steps: 875 19:15:05-200252 INFO lr_warmup_steps = 0 19:15:05-202252 INFO Saving training config to D:/github/lora/models\newstyle_20240522-191505.json... 19:15:05-203252 INFO Executing command: D:\github\kohya_ss\venv\Scripts\accelerate.EXE launch --dynamo_backend no --dynamo_mode default --mixed_precision fp16 --num_processes 1 --num_machines 1 --num_cpu_threads_per_process 2 D:/github/kohya_ss/sd-scripts/fine_tune.py --config_file D:/github/lora/models/config_finetune-20240522-191505.toml 19:15:05-207254 INFO Command executed. 2024-05-22 19:15:13 INFO Loading settings from train_util.py:3744 D:/github/lora/models/config_finetune-20240522-191505.toml... INFO D:/github/lora/models/config_finetune-20240522-191505 train_util.py:3763 2024-05-22 19:15:13 INFO prepare tokenizer train_util.py:4227 2024-05-22 19:15:14 INFO update token length: 75 train_util.py:4244 INFO loading existing metadata: /meta_lat.json train_util.py:1679 Traceback (most recent call last): File "D:\github\kohya_ss\sd-scripts\fine_tune.py", line 526, in
train(args)
File "D:\github\kohya_ss\sd-scripts\fine_tune.py", line 85, in train
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
File "D:\github\kohya_ss\sd-scripts\library\config_util.py", line 482, in generate_dataset_group_by_blueprint
dataset = dataset_klass(subsets=subsets, **asdict(dataset_blueprint.params))
File "D:\github\kohya_ss\sd-scripts\library\train_util.py", line 1714, in init
assert abs_path is not None, f"no image / 画像がありません: {image_key}"
AssertionError: no image / 画像がありません: D:\github\lora\images\10_level\1.jpg
Traceback (most recent call last):
File "C:\Users\This PC\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\This PC\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\github\kohya_ss\venv\Scripts\accelerate.EXE__main__.py", line 7, in
File "D:\github\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 47, in main
args.func(args)
File "D:\github\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1017, in launch_command
simple_launcher(args)
File "D:\github\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 637, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['D:\github\kohya_ss\venv\Scripts\python.exe', 'D:/github/kohya_ss/sd-scripts/fine_tune.py', '--config_file', 'D:/github/lora/models/config_finetune-20240522-191505.toml']' returned non-zero exit status 1.
19:15:16-504837 INFO Training has ended.
I do not know where does it get the D:\github\lora\images\10_level\1.jpg , it is not in anywhere . Tried reinstalling, deleting all data, still it gives same error with D:\github\lora\images\10_level\1.jpg.