Open kakachiex2 opened 5 months ago
Here is the setting
An I get this after using the normal train node
got prompt
[rgthree] Using rgthree's optimized recursive execution.
[]
K:\ComfyUI\ComfyUI\custom_nodes\Lora-Training-in-Comfy/sd-scripts/train_network.py
The following values were not passed to accelerate launch
and had defaults used instead:
--num_processes
was set to a value of 0
--num_machines
was set to a value of 1
--mixed_precision
was set to a value of 'no'
--dynamo_backend
was set to a value of 'no'
To avoid this warning pass in values for each of the problematic parameters or run accelerate config
.
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.1.2+cu121 with CUDA 1201 (you have 2.1.2+cpu)
Python 3.11.7 (you have 3.11.6)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
prepare tokenizer
vocab.json: 100%|████████████████████████████████████████████████████████████████████| 961k/961k [00:00<00:00, 3.11MB/s]
C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\huggingface_hub\file_download.py:149: UserWarning: huggingface_hub
cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in K:\ComfyUI\huggingface\hub\models--openai--clip-vit-large-patch14. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the HF_HUB_DISABLE_SYMLINKS_WARNING
environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
warnings.warn(message)
merges.txt: 100%|████████████████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 5.93MB/s]
special_tokens_map.json: 100%|█████████████████████████████████████████████████████████████████| 389/389 [00:00<?, ?B/s]
tokenizer_config.json: 100%|███████████████████████████████████████████████████████████████████| 905/905 [00:00<?, ?B/s]
update token length: 225
Using DreamBooth method.
prepare images.
0 train images with repeating.
0 reg images.
no regularization images / 正則化画像が見つかりませんでした
[Dataset 0]
batch_size: 1
resolution: (512, 512)
enable_bucket: False
[Dataset 0] loading image sizes. 0it [00:00, ?it/s] make buckets number of images (including repeats) / 各bucketの画像枚数(繰り返し回数を含む) C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\numpy\core\fromnumeric.py:3464: RuntimeWarning: Mean of empty slice. return _methods._mean(a, axis=axis, dtype=dtype, C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\numpy\core_methods.py:192: RuntimeWarning: invalid value encountered in scalar divide ret = ret.dtype.type(ret / rcount) mean ar error (without repeats): nan No data found. Please verify arguments (train_data_dir must be the parent of folders with images) / 画像がありません。引 数指定を確認してください(train_data_dirには画像があるフォルダではなく、画像があるフォルダの親フォルダを指定する必要があ ります) Train finished Prompt executed in 15.35 seconds
I reinstall requirement and process it again and get this::
[]
K:\ComfyUI\ComfyUI\custom_nodes\Lora-Training-in-Comfy/sd-scripts/train_network.py
The following values were not passed to accelerate launch
and had defaults used instead:
--num_processes
was set to a value of 0
--num_machines
was set to a value of 1
--mixed_precision
was set to a value of 'no'
--dynamo_backend
was set to a value of 'no'
To avoid this warning pass in values for each of the problematic parameters or run accelerate config
.
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.1.2+cu121 with CUDA 1201 (you have 2.1.2+cpu)
Python 3.11.7 (you have 3.11.6)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
prepare tokenizer
update token length: 225
Using DreamBooth method.
prepare images.
found directory C:\database\5_Niji contains 91 image files
455 train images with repeating.
0 reg images.
no regularization images / 正則化画像が見つかりませんでした
[Dataset 0]
batch_size: 1
resolution: (512, 512)
enable_bucket: True
min_bucket_reso: 256
max_bucket_reso: 1584
bucket_reso_steps: 64
bucket_no_upscale: False
[Subset 0 of Dataset 0] image_dir: "C:\database\5_Niji" image_count: 91 num_repeats: 5 shuffle_caption: True keep_tokens: 0 caption_dropout_rate: 0.0 caption_dropout_every_n_epoches: 0 caption_tag_dropout_rate: 0.0 caption_prefix: None caption_suffix: None color_aug: False flip_aug: False face_crop_aug_range: None random_crop: False token_warmup_min: 1, token_warmup_step: 0, is_reg: False class_tokens: Niji caption_extension: .txt
[Dataset 0]
loading image sizes.
100%|████████████████████████████████████████████████████████████████████████████████| 91/91 [00:00<00:00, 2027.07it/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, 704), count: 205
bucket 1: resolution (384, 640), count: 115
bucket 2: resolution (512, 512), count: 135
mean ar error (without repeats): 0.03732933732933733
preparing accelerator
loading model for process 0/1
load StableDiffusion checkpoint: K:\Automatic111\stable-diffusion-webui\models/Stable-diffusion\rundiffusionFX25D_v10.safetensors
UNet2DConditionModel: 64, 8, 768, False, False
loading u-net:
Dude, are you done with this?
Hi Larry I create this worflow to train Lora base in your tutorila but wen executing looks like it do nothing and finish to fast.
Her is the console log:: got prompt [rgthree] Using rgthree's optimized recursive execution. [rgthree] First run patching recursive_output_delete_if_changed and recursive_will_execute. [rgthree] Note: If execution seems broken due to forward ComfyUI changes, you can disable the optimization from rgthree settings in ComfyUI. K:\ComfyUI\ComfyUI\custom_nodes\Lora-Training-in-Comfy/sd-scripts/train_network.py The following values were not passed to", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\accelerate\commands\launch.py", line 996, in
main()
File "C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\accelerate\commands\launch.py", line 992, in main
launch_command(args)
File "C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\accelerate\commands\launch.py", line 986, in launch_command
simple_launcher(args)
File "C:\Users\rafae\AppData\Local\Programs\Python\Python311\Lib\site-packages\accelerate\commands\launch.py", line 628, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['C:\Users\rafae\AppData\Local\Programs\Python\Python311\python.exe', 'custom_nodes/Lora-Training-in-Comfy/sd-scripts/train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=K:\Automatic111\stable-diffusion-webui\models/Stable-diffusion\rundiffusionFX25D_v10.safetensors', '--train_data_dir=C:/database', '--output_dir=models/loras', '--logging_dir=./logs', '--log_prefix=Kakachiex_Niji_LoRA.', '--resolution=768,768', '--network_module=networks.lora', '--max_train_epochs=40', '--learning_rate=1e-4', '--unet_lr=1.e-4', '--text_encoder_lr=1.e-4', '--lr_scheduler=cosine_with_restarts', '--lr_warmup_steps=0', '--lr_scheduler_num_cycles=1', '--network_dim=32', '--network_alpha=32', '--output_name=Kakachiex_Niji_LoRA.', '--train_batch_size=1', '--save_every_n_epochs=10', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=14', '--cache_latents', '--prior_loss_weight=1', '--max_token_length=225', '--caption_extension=.txt', '--save_model_as=safetensors', '--min_bucket_reso=256', '--max_bucket_reso=1584', '--keep_tokens=0', '--xformers', '--shuffle_caption', '--clip_skip=2', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard']' returned non-zero exit status 2.
Train finished
Prompt executed in 5.58 seconds
accelerate launch
and had defaults used instead:--num_processes
was set to a value of0
--num_machines
was set to a value of1
--mixed_precision
was set to a value of'no'
--dynamo_backend
was set to a value of'no'
To avoid this warning pass in values for each of the problematic parameters or runaccelerate config
. C:\Users\rafae\AppData\Local\Programs\Python\Python311\python.exe: can't open file 'K:\ComfyUI\custom_nodes\Lora-Training-in-Comfy\sd-scripts\train_network.py': [Errno 2] No such file or directory Traceback (most recent call last): File "