Error After updated today.

[KisakuKK77]

=============================================================
Modules installed outside the virtual environment were found.
This can cause issues. Please review the installed modules.

You can uninstall all local modules with:

deactivate
pip freeze > uninstall.txt
pip uninstall -y -r uninstall.txt

=============================================================

And Output Lora:
17:39:39-085515 INFO nVidia toolkit detected
17:39:41-513735 INFO Torch 2.0.1+cu118
17:39:41-529682 INFO Torch backend: nVidia CUDA 11.8 cuDNN 8700
17:39:41-531676 INFO Torch detected GPU: NVIDIA GeForce RTX 3080 VRAM 12288 Arch (8, 6) Cores 70
17:39:41-532672 INFO Verifying requirements
17:39:43-560372 INFO headless: False
17:39:43-562911 INFO Load CSS...
Running on local URL: http://127.0.0.1:7861

To create a public link, set share=True in launch().
17:39:55-644836 INFO Loading config...
17:39:55-693673 INFO LoRA type changed...
17:40:41-622154 INFO Start training LoRA Kohya LoCon ...
17:40:41-627137 INFO Folder 100_EAV P: 46 images found
17:40:41-628134 INFO Folder 100_EAV P: 4600 steps
17:40:41-629130 INFO Total steps: 4600
17:40:41-630126 INFO Train batch size: 2
17:40:41-632120 INFO Gradient accumulation steps: 1.0
17:40:41-633117 INFO Epoch: 1
17:40:41-634113 INFO Regulatization factor: 1
17:40:41-635110 INFO max_train_steps (4600 / 2 / 1.0 * 1 * 1) = 2300
17:40:41-636107 INFO stop_text_encoder_training = 0
17:40:41-637103 INFO lr_warmup_steps = 230
17:40:41-639097 INFO accelerate launch --num_cpu_threads_per_process=2 "train_network.py"
--pretrained_model_name_or_path="E:\Game
2023\AIWAIFU\SD15\stable-diffusion-webui\models\Stable-diffusion\yesmix_v16Original.safetensors " --train_data_dir="C:\Test\Aya_Kujyou_Final_Gear\2" --resolution=512,512
--output_dir="C:\Test\Aya_Kujyou_Final_Gear\2" --network_alpha="128"
--save_model_as=safetensors --network_module=networks.lora --network_args conv_dim="1"
conv_alpha="1" --text_encoder_lr=5e-05 --unet_lr=0.0001 --network_dim=16
--output_name="Aya_Kujyou_Final_Gear-KK77-V1" --lr_scheduler_num_cycles="1"
--learning_rate="0.0001" --lr_scheduler="cosine" --lr_warmup_steps="230" --train_batch_size="2" --max_train_steps="2300" --save_every_n_epochs="1" --mixed_precision="fp16"
--save_precision="fp16" --seed="1" --caption_extension=".txt" --cache_latents
--optimizer_type="AdamW8bit" --max_data_loader_n_workers="1" --clip_skip=2
--bucket_reso_steps=64 --xformers --bucket_no_upscale --wandb_api_key="False"
Traceback (most recent call last):
File "C:\Users\admin\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\admin\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\Scripts\accelerate.exe_main.py", line 4, in
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate_init.py", line 3, in
from .accelerator import Accelerator
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate\accelerator.py", line 39, in
from .tracking import LOGGER_TYPE_TO_CLASS, GeneralTracker, filter_trackers
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate\tracking.py", line 42, in
from torch.utils import tensorboard
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\torch\utils\tensorboard_init.py", line 12, in
from .writer import FileWriter, SummaryWriter # noqa: F401
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\torch\utils\tensorboard\writer.py", line 16, in
from ._embedding import (
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\torch\utils\tensorboard_embedding.py", line 9, in
_HAS_GFILE_JOIN = hasattr(tf.io.gfile, "join")
File "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\venv\lib\site-packages\tensorboard\lazy.py", line 65, in getattr
return getattr(load_once(self), attr_name)
AttributeError: module 'tensorflow' has no attribute 'io'

[KisakuKK77]

Now, Kohya ss is really bad. It is too slow to make lora.

Before 2023-06-03 I still can use Torch 2 and cudnn, It so fast,

But now It's dead...So sad

[KisakuKK77]

Now, what is this?

=============================================================
Modules installed outside the virtual environment were found.
This can cause issues. Please review the installed modules.

You can uninstall all local modules with:

deactivate
pip freeze > uninstall.txt
pip uninstall -y -r uninstall.txt

=============================================================

12:14:18-662189 INFO nVidia toolkit detected
12:14:19-685163 INFO Torch 1.12.1+cu116
12:14:19-702673 INFO Torch backend: nVidia CUDA 11.6 cuDNN 8901
12:14:19-704670 INFO Torch detected GPU: NVIDIA GeForce RTX 3080 VRAM 12288 Arch (8, 6) Cores 70
12:14:19-705672 INFO Verifying requirements
12:14:19-751183 WARNING Package wrong version: huggingface-hub 0.15.1 required 0.13.3
12:14:19-752182 INFO Installing package: huggingface-hub==0.13.3
12:14:26-545070 INFO headless: False
12:14:26-549068 INFO Load CSS...
Running on local URL: http://127.0.0.1:7861

To create a public link, set share=True in launch().
12:14:50-182032 INFO Loading config...
12:14:50-261548 INFO LoRA type changed...
12:14:59-552952 INFO Start training LoRA Kohya LoCon ...
12:14:59-555950 INFO Folder 50_EAV P: 46 images found
12:14:59-556952 INFO Folder 50_EAV P: 2300 steps
12:14:59-557950 INFO Total steps: 2300
12:14:59-558950 INFO Train batch size: 2
12:14:59-559950 INFO Gradient accumulation steps: 1.0
12:14:59-560950 INFO Epoch: 1
12:14:59-561950 INFO Regulatization factor: 1
12:14:59-562949 INFO max_train_steps (2300 / 2 / 1.0 * 1 * 1) = 1150
12:14:59-564952 INFO stop_text_encoder_training = 0
12:14:59-565951 INFO lr_warmup_steps = 115
12:14:59-567952 INFO accelerate launch --num_cpu_threads_per_process=2 "train_network.py"
--pretrained_model_name_or_path="E:\Game
2023\AIWAIFU\SD15\stable-diffusion-webui\models\Stable-diffusion\yesmix_v16Original.safetensors
" --train_data_dir="E:\Game
2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\YMAKELORA\Model\20230605\Aya_Kujyou_Final_Gear
Aya_Kujyou_Final_Gear" --resolution=512,512 --output_dir="E:\Game
2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\YMAKELORA\Model\20230605\Aya_Kujyou_Final_Gear
Aya_Kujyou_Final_Gear" --network_alpha="128" --save_model_as=safetensors
--network_module=networks.lora --network_args conv_dim="1" conv_alpha="1"
--text_encoder_lr=5e-05 --unet_lr=0.0001 --network_dim=16
--output_name="Aya_Kujyou_Final_Gear-KK77-V3" --lr_scheduler_num_cycles="1"
--learning_rate="0.0001" --lr_scheduler="cosine" --lr_warmup_steps="115" --train_batch_size="2"
--max_train_steps="1150" --save_every_n_epochs="1" --mixed_precision="fp16"
--save_precision="fp16" --seed="1" --caption_extension=".txt" --cache_latents
--optimizer_type="AdamW8bit" --max_data_loader_n_workers="1" --clip_skip=2
--bucket_reso_steps=64 --xformers --bucket_no_upscale --wandb_api_key="False"
prepare tokenizer
Using DreamBooth method.
ignore directory without repeats / 繰り返し回数のないディレクトリを無視します: sample
prepare images.
found directory E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\YMAKELORA\Model\20230605\Aya_Kujyou_Final_Gear\Aya_Kujyou_Final_Gear\50_EAV P contains 46 image files
2300 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: 2
resolution: (512, 512)
enable_bucket: False

[Subset 0 of Dataset 0]
image_dir: "E:\Game 2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\YMAKELORA\Model\20230605\Aya_Kujyou_Final_Gear\Aya_Kujyou_Final_Gear\50_EAV P"
image_count: 46
num_repeats: 50
shuffle_caption: False
keep_tokens: 0
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
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: EAV P
caption_extension: .txt

[Dataset 0]
loading image sizes.
100%|████████████████████████████████████████████████████████████████████████████████| 46/46 [00:00<00:00, 5749.39it/s]
prepare dataset
preparing accelerator
Using accelerator 0.15.0 or above.
loading model for process 0/1
load StableDiffusion checkpoint: E:\Game 2023\AIWAIFU\SD15\stable-diffusion-webui\models\Stable-diffusion\yesmix_v16Original.safetensors
loading u-net:
loading vae:
loading text encoder:
CrossAttention.forward has been replaced to enable xformers.
import network module: networks.lora
[Dataset 0]
caching latents.
0%| | 0/46 [00:00<?, ?it/s]
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ E:\Game 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\train_network.py:864 in │
│ │
│ 861 │ args = parser.parse_args() │
│ 862 │ args = train_util.read_config_from_file(args, parser) │
│ 863 │ │
│ ❱ 864 │ train(args) │
│ 865 │
│ │
│ E:\Game 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\train_network.py:194 in train │
│ │
│ 191 │ │ vae.requires_grad_(False) │
│ 192 │ │ vae.eval() │
│ 193 │ │ with torch.no_grad(): │
│ ❱ 194 │ │ │ train_dataset_group.cache_latents(vae, args.vae_batch_size, args.cache_laten │
│ 195 │ │ vae.to("cpu") │
│ 196 │ │ if torch.cuda.is_available(): │
│ 197 │ │ │ torch.cuda.empty_cache() │
│ │
│ E:\Game 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\library\train_util.py:1422 in cache_latents │
│ │
│ 1419 │ def cache_latents(self, vae, vae_batch_size=1, cache_to_disk=False, is_main_process= │
│ 1420 │ │ for i, dataset in enumerate(self.datasets): │
│ 1421 │ │ │ print(f"[Dataset {i}]") │
│ ❱ 1422 │ │ │ dataset.cache_latents(vae, vae_batch_size, cache_to_disk, is_main_process) │
│ 1423 │ │
│ 1424 │ def is_latent_cacheable(self) -> bool: │
│ 1425 │ │ return all([dataset.is_latent_cacheable() for dataset in self.datasets]) │
│ │
│ E:\Game 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\library\train_util.py:814 in cache_latents │
│ │
│ 811 │ │ │ img_tensors = torch.stack(images, dim=0) │
│ 812 │ │ │ img_tensors = img_tensors.to(device=vae.device, dtype=vae.dtype) │
│ 813 │ │ │ │
│ ❱ 814 │ │ │ latents = vae.encode(img_tensors).latent_dist.sample().to("cpu") │
│ 815 │ │ │ │
│ 816 │ │ │ for info, latent in zip(batch, latents): │
│ 817 │ │ │ │ if cache_to_disk: │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\diffusers\models\vae.py:566 in │
│ encode │
│ │
│ 563 │ │ self.use_slicing = False │
│ 564 │ │
│ 565 │ def encode(self, x: torch.FloatTensor, return_dict: bool = True) -> AutoencoderKLOut │
│ ❱ 566 │ │ h = self.encoder(x) │
│ 567 │ │ moments = self.quant_conv(h) │
│ 568 │ │ posterior = DiagonalGaussianDistribution(moments) │
│ 569 │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py:1130 │
│ in _call_impl │
│ │
│ 1127 │ │ # this function, and just call forward. │
│ 1128 │ │ if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks o │
│ 1129 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │
│ ❱ 1130 │ │ │ return forward_call(*input, **kwargs) │
│ 1131 │ │ # Do not call functions when jit is used │
│ 1132 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │
│ 1133 │ │ if self._backward_hooks or _global_backward_hooks: │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\diffusers\models\vae.py:130 in │
│ forward │
│ │
│ 127 │ │
│ 128 │ def forward(self, x): │
│ 129 │ │ sample = x │
│ ❱ 130 │ │ sample = self.conv_in(sample) │
│ 131 │ │ │
│ 132 │ │ # down │
│ 133 │ │ for down_block in self.down_blocks: │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py:1130 │
│ in _call_impl │
│ │
│ 1127 │ │ # this function, and just call forward. │
│ 1128 │ │ if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks o │
│ 1129 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │
│ ❱ 1130 │ │ │ return forward_call(*input, **kwargs) │
│ 1131 │ │ # Do not call functions when jit is used │
│ 1132 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │
│ 1133 │ │ if self._backward_hooks or _global_backward_hooks: │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\torch\nn\modules\conv.py:457 in │
│ forward │
│ │
│ 454 │ │ │ │ │ │ self.padding, self.dilation, self.groups) │
│ 455 │ │
│ 456 │ def forward(self, input: Tensor) -> Tensor: │
│ ❱ 457 │ │ return self._conv_forward(input, self.weight, self.bias) │
│ 458 │
│ 459 class Conv3d(_ConvNd): │
│ 460 │ doc = r"""Applies a 3D convolution over an input signal composed of several inpu │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\torch\nn\modules\conv.py:453 in │
│ _conv_forward │
│ │
│ 450 │ │ │ return F.conv2d(F.pad(input, self._reversed_padding_repeated_twice, mode=sel │
│ 451 │ │ │ │ │ │ │ weight, bias, self.stride, │
│ 452 │ │ │ │ │ │ │ _pair(0), self.dilation, self.groups) │
│ ❱ 453 │ │ return F.conv2d(input, weight, bias, self.stride, │
│ 454 │ │ │ │ │ │ self.padding, self.dilation, self.groups) │
│ 455 │ │
│ 456 │ def forward(self, input: Tensor) -> Tensor: │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ C:\Users\admin\AppData\Local\Programs\Python\Python310\lib\runpy.py:196 in _run_module_as_main │
│ │
│ 193 │ main_globals = sys.modules["main"].dict │
│ 194 │ if alter_argv: │
│ 195 │ │ sys.argv[0] = mod_spec.origin │
│ ❱ 196 │ return _run_code(code, main_globals, None, │
│ 197 │ │ │ │ │ "main", mod_spec) │
│ 198 │
│ 199 def run_module(mod_name, init_globals=None, │
│ │
│ C:\Users\admin\AppData\Local\Programs\Python\Python310\lib\runpy.py:86 in _run_code │
│ │
│ 83 │ │ │ │ │ loader = loader, │
│ 84 │ │ │ │ │ package = pkg_name, │
│ 85 │ │ │ │ │ spec = mod_spec) │
│ ❱ 86 │ exec(code, run_globals) │
│ 87 │ return run_globals │
│ 88 │
│ 89 def _run_module_code(code, init_globals=None, │
│ │
│ in :7 │
│ │
│ 4 from accelerate.commands.accelerate_cli import main │
│ 5 if name == 'main': │
│ 6 │ sys.argv[0] = re.sub(r'(-script.pyw|.exe)?$', '', sys.argv[0]) │
│ ❱ 7 │ sys.exit(main()) │
│ 8 │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_c │
│ li.py:45 in main │
│ │
│ 42 │ │ exit(1) │
│ 43 │ │
│ 44 │ # Run │
│ ❱ 45 │ args.func(args) │
│ 46 │
│ 47 │
│ 48 if name == "main": │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py:11 │
│ 04 in launch_command │
│ │
│ 1101 │ elif defaults is not None and defaults.compute_environment == ComputeEnvironment.AMA │
│ 1102 │ │ sagemaker_launcher(defaults, args) │
│ 1103 │ else: │
│ ❱ 1104 │ │ simple_launcher(args) │
│ 1105 │
│ 1106 │
│ 1107 def main(): │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py:56 │
│ 7 in simple_launcher │
│ │
│ 564 │ process = subprocess.Popen(cmd, env=current_env) │
│ 565 │ process.wait() │
│ 566 │ if process.returncode != 0: │
│ ❱ 567 │ │ raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) │
│ 568 │
│ 569 │
│ 570 def multi_gpu_launcher(args): │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
CalledProcessError: Command '['E:\Game 2023\AIWAIFU\kohya_ss20230606_1\kohya_ss\venv\Scripts\python.exe',
'train_network.py', '--pretrained_model_name_or_path=E:\Game
2023\AIWAIFU\SD15\stable-diffusion-webui\models\Stable-diffusion\yesmix_v16Original.safetensors',
'--train_data_dir=E:\Game
2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\YMAKELORA\Model\20230605\Aya_Kujyou_Final_Gear\Aya_Kujyou_Final
_Gear', '--resolution=512,512', '--output_dir=E:\Game
2023\AIWAIFU\kohya_ss20230512\kohya_ss\kohya_ss\YMAKELORA\Model\20230605\Aya_Kujyou_Final_Gear\Aya_Kujyou_Final
_Gear', '--network_alpha=128', '--save_model_as=safetensors', '--network_module=networks.lora', '--network_args',
'conv_dim=1', 'conv_alpha=1', '--text_encoder_lr=5e-05', '--unet_lr=0.0001', '--network_dim=16',
'--output_name=Aya_Kujyou_Final_Gear-KK77-V3', '--lr_scheduler_num_cycles=1', '--learning_rate=0.0001',
'--lr_scheduler=cosine', '--lr_warmup_steps=115', '--train_batch_size=2', '--max_train_steps=1150',
'--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1', '--caption_extension=.txt',
'--cache_latents', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=1', '--clip_skip=2',
'--bucket_reso_steps=64', '--xformers', '--bucket_no_upscale', '--wandb_api_key=False']' returned non-zero exit status
1.

[KisakuKK77]

05:01:52-077763 INFO Stopping tensorboard process...
Traceback (most recent call last):
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\gradio\routes.py", line 422, in run_predict
output = await app.get_blocks().process_api(
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\gradio\blocks.py", line 1323, in process_api
result = await self.call_function(
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\gradio\blocks.py", line 1051, in call_function
prediction = await anyio.to_thread.run_sync(
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "E:\Game 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\library\tensorboard_gui.py", line 49, in stop_tensorboard
tensorboard_proc.kill()
AttributeError: 'NoneType' object has no attribute 'kill'

[KisakuKK77]

╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ C:\Users\admin\AppData\Local\Programs\Python\Python310\lib\runpy.py:196 in _run_module_as_main │
│ │
│ 193 │ main_globals = sys.modules["main"].dict │
│ 194 │ if alter_argv: │
│ 195 │ │ sys.argv[0] = mod_spec.origin │
│ ❱ 196 │ return _run_code(code, main_globals, None, │
│ 197 │ │ │ │ │ "main", mod_spec) │
│ 198 │
│ 199 def run_module(mod_name, init_globals=None, │
│ │
│ C:\Users\admin\AppData\Local\Programs\Python\Python310\lib\runpy.py:86 in _run_code │
│ │
│ 83 │ │ │ │ │ loader = loader, │
│ 84 │ │ │ │ │ package = pkg_name, │
│ 85 │ │ │ │ │ spec = mod_spec) │
│ ❱ 86 │ exec(code, run_globals) │
│ 87 │ return run_globals │
│ 88 │
│ 89 def _run_module_code(code, init_globals=None, │
│ │
│ in :7 │
│ │
│ 4 from accelerate.commands.accelerate_cli import main │
│ 5 if name == 'main': │
│ 6 │ sys.argv[0] = re.sub(r'(-script.pyw|.exe)?$', '', sys.argv[0]) │
│ ❱ 7 │ sys.exit(main()) │
│ 8 │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_c │
│ li.py:45 in main │
│ │
│ 42 │ │ exit(1) │
│ 43 │ │
│ 44 │ # Run │
│ ❱ 45 │ args.func(args) │
│ 46 │
│ 47 │
│ 48 if name == "main": │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py:10 │
│ 00 in launch_command │
│ │
│ 997 │ warned = [] │
│ 998 │ # Get the default from the config file. │
│ 999 │ if args.config_file is not None or os.path.isfile(default_config_file) and not args. │
│ ❱ 1000 │ │ defaults = load_config_from_file(args.config_file) │
│ 1001 │ │ if ( │
│ 1002 │ │ │ not args.multi_gpu │
│ 1003 │ │ │ and not args.tpu │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\accelerate\commands\config\confi │
│ g_args.py:64 in load_config_from_file │
│ │
│ 61 │ │ │ │ config_class = ClusterConfig │
│ 62 │ │ │ else: │
│ 63 │ │ │ │ config_class = SageMakerConfig │
│ ❱ 64 │ │ │ return config_class.from_yaml_file(yaml_file=config_file) │
│ 65 │
│ 66 │
│ 67 @DataClass │
│ │
│ E:\Game │
│ 2023\AIWAIFU\kohya_ss20230607_1\kohya_ss\venv\lib\site-packages\accelerate\commands\config\confi │
│ g_args.py:122 in from_yaml_file │
│ │
│ 119 │ │ if "dynamo_backend" not in config_dict: │
│ 120 │ │ │ config_dict["dynamo_backend"] = DynamoBackend.NO │
│ 121 │ │ │
│ ❱ 122 │ │ return cls(**config_dict) │
│ 123 │ │
│ 124 │ def to_yaml_file(self, yaml_file): │
│ 125 │ │ with open(yaml_file, "w", encoding="utf-8") as f: │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: ClusterConfig.init() got an unexpected keyword argument 'tpu_env'

[KisakuKK77]

2023-06-07T18:47:51.630ZE [8784:ShellIpcClient] shell_ipc_client.cc:138:Connect Can't connect to socket at: \.\Pipe\GoogleDriveFSPipe_admin_shell
2023-06-07T18:47:51.633ZE [8784:ShellIpcClient] shell_ipc_client.cc:621:operator() Failed to connect to the server: NOT_FOUND: Can't connect to socket at: \.\Pipe\GoogleDriveFSPipe_admin_shell [type.googleapis.com/drive.ds.Status='UNAVAILABLE_RESOURCE']
=== Source Location Trace: ===
apps/drive/fs/ipc/shell_ipc_client.cc:139

2023-06-07T18:47:51.633ZE [13980:ShellIpcClient] shell_ipc_client.cc:138:Connect Can't connect to socket at: \.\Pipe\GoogleDriveFSPipe_admin_shell
2023-06-07T18:47:51.634ZE [13980:ShellIpcClient] shell_ipc_client.cc:621:operator() Failed to connect to the server: NOT_FOUND: Can't connect to socket at: \.\Pipe\GoogleDriveFSPipe_admin_shell [type.googleapis.com/drive.ds.Status='UNAVAILABLE_RESOURCE']
=== Source Location Trace: ===
apps/drive/fs/ipc/shell_ipc_client.cc:139

2023-06-07T18:47:51.634ZE [8944:ShellIpcClient] shell_ipc_client.cc:138:Connect Can't connect to socket at: \.\Pipe\GoogleDriveFSPipe_admin_shell
2023-06-07T18:47:51.634ZE [8944:ShellIpcClient] shell_ipc_client.cc:621:operator() Failed to connect to the server: NOT_FOUND: Can't connect to socket at: \.\Pipe\GoogleDriveFSPipe_admin_shell [type.googleapis.com/drive.ds.Status='UNAVAILABLE_RESOURCE']
=== Source Location Trace: ===
apps/drive/fs/ipc/shell_ipc_client.cc:139

[Omarkh12]

Im having the same error trying to install it

[KisakuKK77]

Before 2023-06-03 I still can use Torch 2 and cudnn, It so fast,

But now using Torch 1 It is extremely slow....

[KisakuKK77]

v21.7.6

Modules installed outside the virtual environment were found.
This can cause issues. Please review the installed modules.

You can uninstall all local modules with:

deactivate
pip freeze > uninstall.txt
pip uninstall -y -r uninstall.txt

=============================================================

A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'

Speed also extremely slow....

[dougvan1701]

I had this problem after running upgrade.bat yesterday, I simply deleted my kohya_ss folder and re-installed. Worked just fine. Only issue I have is it complaining about Triton missing but that hasn't affected building my models. Lora seems to work just fine and not super slow for me.

[mistermcluvin]

Yeah, I made the mistake of upgrading my old version of it yesterday and it just won't work. I got similar errors. I finally was able to get it to create a Lora (with the Triton warning), then I got... Failed to match keys when loading Lora in A1111. Argh. I wish I just stayed on the old version. Oh well, what can you do. It's not like it's paid software and I do appreciate the creators and developers. It's not like I can create these things myself.

[Lolamombobdoda]

I got similar issues after updating once and it was because it was trying to update into the wrong folder.
I don't remember exactly what it was but I think it was putting stuff directly into the kohya_ss folder instead of kohya_ss\venv, but don't quote me on that.

Reinstalling fixed it for me.
Reinstalling have fixed most issue for me, except for xformers not working but that got fixed in an update a couple of months ago!

[Boldor83]

i still get this every install i try.
following instructions:
https://github.com/bmaltais/kohya_ss under windows.
Then trying
deactivate
pip freeze > uninstall.txt
pip uninstall -y -r uninstall.txt
still gives this message and also when i try pip install -r requirements.txt afterwards.