Open jackylee1 opened 7 months ago
[SDN-[37mINF[0m]: [37mraise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)[0m [SDN-[37mINF[0m]: [37msubprocess.CalledProcessError: Command '['C:\Users\Administrator\AppData\Local\Programs\Python\Python310\python.exe', 'custom_nodes/Lora-Training-in-Comfy/sd-scripts/train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=F:\Blender_ComfyUI\ComfyUI\models\checkpoints\AIGODLIKE鍗庝附_4000.ckpt', '--train_data_dir=F:/Blender_ComfyUI/ComfyUI/output/LoraTest', '--output_dir=models/loras', '--logging_dir=./logs', '--log_prefix=Desired', 'name', 'for', 'LoRA.', '--resolution=512,512', '--network_module=networks.lora', '--max_train_epochs=10', '--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=Desired', 'name', 'for', 'LoRA.', '--train_batch_size=1', '--save_every_n_epochs=10', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=6', '--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=1', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard', '--clip_skip=1', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard', '--clip_skip=1', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard', '--clip_skip=1', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard', '--clip_skip=1', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard', '--clip_skip=1', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard', '--clip_skip=2', '--optimizer_type=AdamW8bit', '--persistent_data_loader_workers', '--log_with=tensorboard']' returned non-zero exit status 1.[0m
[SDN-[37mINF[0m]: [37mTrain finished[0m
[SDN-[37mINF[0m]: [37mPrompt executed in 1.88 seconds[0m
prepare optimizer, data loader etc. False The following directories listed in your path were found to be non-existent: {WindowsPath('D'), WindowsPath('/ComfyUI-aki/ComfyUI-aki-v1.2/.ext/lib')} D:\ComfyUI-aki\ComfyUI-aki-v1.2\python\lib\site-packages\bitsandbytes\cuda_setup\main.py:167: UserWarning: D:\ComfyUI-aki\ComfyUI-aki-v1.2.ext did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths... warn(msg) The following directories listed in your path were found to be non-existent: {WindowsPath('//gitcode.net/overbill1683/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1'), WindowsPath('git+https')} The following directories listed in your path were found to be non-existent: {WindowsPath('https'), WindowsPath('//modelscope.cn/api/v1/studio/hanamizukiai/resolver/gradio/wheel/depth_anything-2024.1.22.0-py2.py3-none-any.whl')} The following directories listed in your path were found to be non-existent: {WindowsPath('//gitcode.net/overbill1683/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379'), WindowsPath('git+https')} The following directories listed in your path were found to be non-existent: {WindowsPath('https'), WindowsPath('//www.modelscope.cn/api/v1/studio/hanamizukiai/resolver/gradio/wheel/handrefinerportable-2024.1.18.0-py2.py3-none-any.whl')} The following directories listed in your path were found to be non-existent: {WindowsPath('git+https'), WindowsPath('//gitcode.net/overbill1683/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b')} The following directories listed in your path were found to be non-existent: {WindowsPath('https'), WindowsPath('//mirror.sjtu.edu.cn/pytorch-wheels/torch_stable.html https'), WindowsPath('//www.modelscope.cn/api/v1/studio/hanamizukiai/resolver/gradio/pypi-index/index.html'), WindowsPath('//mirrors.aliyun.com/pytorch-wheels/torch_stable.html https')} The following directories listed in your path were found to be non-existent: {WindowsPath('https'), WindowsPath('//mirrors.aliyun.com/pypi/simple')} The following directories listed in your path were found to be non-existent: {WindowsPath('https'), WindowsPath('//www.modelscope.cn/api/v1/studio/hanamizukiai/resolver/gradio/wheel/xformers-0.0.14.dev0+torch12-cp310-cp310-win_amd64.whl')} CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths... The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')} DEBUG: Possible options found for libcudart.so: set() CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.6. CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
D:\ComfyUI-aki\ComfyUI-aki-v1.2.cache\pycache\ComfyUI-aki\ComfyUI-aki-v1.2\custom_nodes\Lora-Training-in-Comfy/sd-scripts/train_network.py
D:\ComfyUI-aki\ComfyUI-aki-v1.2\custom_nodes\Lora-Training-in-Comfy/sd-scripts/train_network.py
D:\ComfyUI-aki\ComfyUI-aki-v1.2\Lora-Training-in-Comfy-main/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 1
--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
.
D:\ComfyUI-aki\ComfyUI-aki-v1.2\python\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
D:\ComfyUI-aki\ComfyUI-aki-v1.2\python\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
prepare tokenizer
update token length: 225
Using DreamBooth method.
prepare images.
found directory F:\Blender_ComfyUI\ComfyUI\output\LoraTest\10_TTTEST contains 24 image files
No caption file found for 1 images. Training will continue without captions for these images. If class token exists, it will be used. / 1枚の画像にキャプションファイルが見つかりませんでした。これらの画像についてはキャプションなしで学習を続行します。class tokenが存在する場合はそれを使います。
F:\Blender_ComfyUI\ComfyUI\output\LoraTest\10_TTTEST\T100001.png
240 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: "F:\Blender_ComfyUI\ComfyUI\output\LoraTest\10_TTTEST"
image_count: 24
num_repeats: 10
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: TTTEST
caption_extension: .txt
[Dataset 0]
loading image sizes.
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 (512, 512), count: 240
mean ar error (without repeats): 0.0
preparing accelerator
loading model for process 0/1
load StableDiffusion checkpoint: D:\ComfyUI-aki\ComfyUI-aki-v1.2\models\checkpoints\revAnimated_v122.safetensors
UNet2DConditionModel: 64, 8, 768, False, False
loading u-net:
Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues
Traceback (most recent call last):
File "D:\ComfyUI-aki\ComfyUI-aki-v1.2\python\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "D:\ComfyUI-aki\ComfyUI-aki-v1.2\python\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\ComfyUI-aki\ComfyUI-aki-v1.2\python\lib\site-packages\accelerate\commands\launch.py", line 996, in
Hey there. Video tutorial here: https://www.youtube.com/watch?v=mDMYbCz2t-c&t=106s&ab_channel=LarryJane
The errors your code is showing are new ones for me. But the core problem seems to be the same as the other open issues: it's a Python dependency problem. I can only suggest installing a virtual environment for your ComfyUI, and install everything there.
loading u-net:
new error
so there are no fixed for these errors ? whats the use of even having this lib if now one can fix these !!
i amvery frustrated on this comifyui been on this for 1 week and tried all types of things nothing works fk !!!
Any video tutorial on training?thanjs