I need a pro in this! #2302
Replies: 2 comments 10 replies
-
|
You have accidentally selected the Dreambooth tab and attempted to train Dreambooth. In the GUI select LoRA and try again. |
Beta Was this translation helpful? Give feedback.
-
|
Ah! Ok! After the installation process did you configure accelerate? You can do it again with option 5 in the install. Just choose the defaults.
|
Beta Was this translation helpful? Give feedback.
-
|
Okay, well. It did change something. But I still dont get it because it says that it can't find a directory. Pretty weird if you ask me. 14:57:50-468118 INFO accelerate launch --mixed_precision="fp16" --num_processes=1 --num_machines=1
|
Beta Was this translation helpful? Give feedback.
-
|
OK. Are you trying to run this whole thing from OneDrive or otherwise remotely? Download the model on to your computer, along with kohya and the datafolders for training, and see if that helps. Because there are errors here which don't actually refer to anything that is really within the realm of this GUI or Kohya as far as I can tell. |
Beta Was this translation helpful? Give feedback.
-
|
I am running it complete locally. I treid it out, did not change anything, sadly. Same issue as above. |
Beta Was this translation helpful? Give feedback.
-
|
Change your computer. |
Beta Was this translation helpful? Give feedback.
-
|
Super late reply, but the problem is in this log line. If you downloaded kohya_ss as a zip file from github, it's best not to do that. You're expected to use git to clone the repo. But if you really don't care about git, then just grab sd-scripts from here and extract the contents to a folder called .... But then your next set of errors for |
Beta Was this translation helpful? Give feedback.
-
I wanted to create my own LoRa but there seems to be a problem with a file....I did not change any file locations....
Error-Code:
[Errno 2] No such file or directory
Traceback (most recent call last):
File "F:\python\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "F:\python\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "E:\ai lora ka\kohya_ss-master\venv\Scripts\accelerate.exe_main.py", line 7, in
File "E:\ai lora ka\kohya_ss-master\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 47, in main
args.func(args)
File "E:\ai lora ka\kohya_ss-master\venv\lib\site-packages\accelerate\commands\launch.py", line 1017, in launch_command
simple_launcher(args)
File "E:\ai lora ka\kohya_ss-master\venv\lib\site-packages\accelerate\commands\launch.py", line 637, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['E:\ai lora ka\kohya_ss-master\venv\Scripts\python.exe', 'E:\ai lora ka\kohya_ss-master/sd-scripts/train_db.py', '--bucket_no_upscale', '--bucket_reso_steps=64', '--cache_latents', '--caption_extension=.txt', '--enable_bucket', '--min_bucket_reso=256', '--max_bucket_reso=2048', '--huber_c=0.1', '--huber_schedule=snr', '--learning_rate=1e-05', '--learning_rate_te=1e-05', '--logging_dir=E:/ai lora ka/kohya_ss-master/outputs\log', '--loss_type=l2', '--lr_scheduler=cosine', '--lr_scheduler_num_cycles=1', '--lr_warmup_steps=160', '--max_data_loader_n_workers=0', '--resolution=512,512', '--max_train_steps=1600', '--min_timestep=0', '--mixed_precision=fp16', '--optimizer_type=AdamW8bit', '--output_dir=E:/ai lora ka/kohya_ss-master/outputs\model', '--output_name=last', '--pretrained_model_name_or_path=stabilityai/stable-diffusion-2-1-base', '--save_every_n_epochs=1', '--save_model_as=safetensors', '--save_precision=fp16', '--train_batch_size=1', '--train_data_dir=E:/ai lora ka/kohya_ss-master/outputs\img', '--v2', '--xformers']' returned non-zero exit status 2.
Beta Was this translation helpful? Give feedback.
All reactions