Open jonathanhecl opened 1 year ago
try pip install xformers
I did it, and it didn't work
cd sd-scripts
python -m venv venv
venv\Scripts\activate
pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116
pip install --upgrade -r requirements.txt
pip install -U -I --no-deps https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl
copy .\bitsandbytes_windows\*.dll .\venv\Lib\site-packages\bitsandbytes\
copy .\bitsandbytes_windows\cextension.py .\venv\Lib\site-packages\bitsandbytes\cextension.py
copy .\bitsandbytes_windows\main.py .\venv\Lib\site-packages\bitsandbytes\cuda_setup\main.py
accelerate config
Did you run the code in here? I changed the commands to work with windows
Is this problem solved? I'm having the same issue too
You need to install xformers using the code above the mainline xformers doesn't work I believe unless your on pytorch 2.0
You can however disable xformers if you have enough vram
Not solved yet, my training environment is M1 - macos, I have installed it,But the error is still reported
您需要使用主线上方的代码安装 xformers 我相信 xformers 不起作用,除非您使用 pytorch 2.0
hi,how can I disable xformers?
hi,how can I disable xformers?
training parameters - advanced configuration - use xformers
I can't train a model with LoRA...
..... [Dataset 0] loading image sizes. 100%|████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 1537.39it/s] make buckets min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is set, because bucket reso is defined by image size automatically / bucket_no_upscaleが指定された場合は、bucketの解像度は画像サイズから自動計算されるため、min_bucket_resoとmax_bucket_resoは無視されます 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: 1500 mean ar error (without repeats): 0.0 prepare accelerator Using accelerator 0.15.0 or above. loading model for process 0/1 load StableDiffusion checkpoint loading u-net: <All keys matched successfully> loading vae: <All keys matched successfully> loading text encoder: <All keys matched successfully> Replace CrossAttention.forward to use xformers Traceback (most recent call last): File "H:\StableDiffusion\Kohya\kohya_ss\library\train_util.py", line 1764, in replace_unet_cross_attn_to_xformers import xformers.ops ModuleNotFoundError: No module named 'xformers' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "H:\StableDiffusion\Kohya\kohya_ss\train_network.py", line 760, in <module> train(args) File "H:\StableDiffusion\Kohya\kohya_ss\train_network.py", line 167, in train train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers) File "H:\StableDiffusion\Kohya\kohya_ss\library\train_util.py", line 1718, in replace_unet_modules replace_unet_cross_attn_to_xformers() File "H:\StableDiffusion\Kohya\kohya_ss\library\train_util.py", line 1766, in replace_unet_cross_attn_to_xformers raise ImportError("No xformers / xformersがインストールされていないようです") ImportError: No xformers / xformersがインストールされていないようです Traceback (most recent call last): File "C:\Users\GS\miniconda3\lib\runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\GS\miniconda3\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "H:\StableDiffusion\Kohya\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module> File "h:\stablediffusion\kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main args.func(args) File "h:\stablediffusion\kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command simple_launcher(args) File "h:\stablediffusion\kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['h:\\stablediffusion\\kohya\\kohya_ss\\venv\\scripts\\python.exe', 'train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=H:/StableDiffusion/SD-Models/v1-5-pruned-emaonly.ckpt', '--train_data_dir=H:/StableDiffusion/Kohya/image', '--resolution=512,512', '--output_dir=H:/StableDiffusion/Kohya/models', '--logging_dir=H:/StableDiffusion/Kohya/logs', '--network_alpha=1', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=5e-5', '--unet_lr=0.0001', '--network_dim=8', '--output_name=hidezone', '--lr_scheduler_num_cycles=1', '--learning_rate=0.0001', '--lr_scheduler=constant', '--train_batch_size=1', '--max_train_steps=1500', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--cache_latents', '--optimizer_type=AdamW', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--xformers', '--bucket_no_upscale']' returned non-zero exit status 1.
Hi friend, I have the same troblem. Have you solve it, if do, please tell me how you solve it.
Remove - -xformers from your command or install xformers with this command
pip install -U -I --no-deps https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl
Thanks a lot, it worked, finally.
从 Windows 版邮件https://go.microsoft.com/fwlink/?LinkId=550986发送
发件人: TingTingin @.> 发送时间: Tuesday, May 16, 2023 4:26:56 PM 收件人: kohya-ss/sd-scripts @.> 抄送: kingsdy @.>; Comment @.> 主题: Re: [kohya-ss/sd-scripts] ModuleNotFoundError: No module named 'xformers' (Issue #420)
Remove - -xformers from your command
― Reply to this email directly, view it on GitHubhttps://github.com/kohya-ss/sd-scripts/issues/420#issuecomment-1549224034, or unsubscribehttps://github.com/notifications/unsubscribe-auth/A7LBQ6VOYKNREETBLTEFHY3XGM25BANCNFSM6AAAAAAW74IAQ4. You are receiving this because you commented.Message ID: @.***>
hi,how can I disable xformers?
training parameters - advanced configuration - use xformers
it's woking for me, thanks!
My training environment: Macbook Pro M1 Pro
Same issue here.
I'm using kohya_ss
.
Training Dreambooth is good with xformers, and the package is actually there.
But training LoRA will have this error...
It seems the script is not using the venv
:
python -V
Python 3.10.11
but the output shows it is using my base environment python:
System Information:
System: Windows, Release: 10, Version: 10.0.22621, Machine: AMD64, Processor: Intel64 Family 6 Model 165 Stepping 5, GenuineIntel
Python Information:
Version: 3.10.10, Implementation: CPython, Compiler: MSC v.1934 64 bit (AMD64)
Virtual Environment Information:
Path: C:\xLibraries\kohya_ss\venv
GPU Information:
Name: NVIDIA GeForce RTX 3090, VRAM: 24576 MiB
I can't train a model with LoRA...