swumagic
commented
1 year ago Bitsandbytes was not supported windows before, but my method can support windows.οΌyuhuangοΌ 1 open folder J:\StableDiffusion\sdwebuiοΌClick the address bar of the folder and enter CMD or WIN+R, CMD γenterοΌcd /d J:\StableDiffusion\sdwebui 2 J:\StableDiffusion\sdwebui\py310\python.exe -m pip uninstall bitsandbytes
3 J:\StableDiffusion\sdwebui\py310\python.exe -m pip uninstall bitsandbytes-windows
4 J:\StableDiffusion\sdwebui\py310\python.exe -m pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl
Replace your SD venv directory fileοΌpython.exe FolderοΌ hereοΌJ:\StableDiffusion\sdwebui\py310οΌ
G:\kohya_ss\venv\lib\site-packages\accelerate\accelerator.py:249: FutureWarning:
logging_diris deprecated and will be removed in version 0.18.0 of π€ Accelerate. Useproject_dirinstead.warnings.warn( Using accelerator 0.15.0 or above. loading model for process 0/1 load Diffusers pretrained models safety_checker\model.safetensors not found Fetching 19 files: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 19/19 [00:00<00:00, 18808.54it/s] You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing
safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 . Replace CrossAttention.forward to use xformers import network module: networks.lora create LoRA network. base dim (rank): 32, alpha: 16.0 create LoRA for Text Encoder: 72 modules. create LoRA for U-Net: 192 modules. enable LoRA for text encoder enable LoRA for U-Net prepare optimizer, data loader etc.===================================BUG REPORT=================================== Welcome to bitsandbytes. For bug reports, please run
python -m bitsandbytes
and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
bin G:\kohya_ss\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda116.dll G:\kohya_ss\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:152: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {WindowsPath('G:/kohya_ss/venv/Lib/site-packages/cv2/../../x64/vc14/bin')} warn(msg) CUDA SETUP: CUDA runtime path found: G:\kohya_ss\venv\Lib\site-packages\torch\lib\cudart64_110.dll CUDA SETUP: Highest compute capability among GPUs detected: 8.6 CUDA SETUP: Detected CUDA version 116 CUDA SETUP: Loading binary G:\kohya_ss\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda116.dll... use 8-bit AdamW optimizer | {} Traceback (most recent call last): File "G:\kohya_ss\train_network.py", line 773, in
train(args)
File "G:\kohya_ss\train_network.py", line 217, in train
train_dataloader = torch.utils.data.DataLoader(
File "G:\kohya_ss\venv\lib\site-packages\torch\utils\data\dataloader.py", line 241, in init
raise ValueError('persistent_workers option needs num_workers > 0')
ValueError: persistent_workers option needs num_workers > 0
Traceback (most recent call last):
File "C:\Users\rui\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\rui\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "G:\kohya_ss\venv\Scripts\accelerate.exe__main__.py", line 7, in
File "G:\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "G:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 923, in launch_command
simple_launcher(args)
File "G:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 579, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['G:\kohya_ss\venv\Scripts\python.exe', 'train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5', '--train_data_dir=G:\AI\training_images', '--resolution=512,512', '--output_dir=G:\AI\output_folder', '--logging_dir=G:\AI\training_log', '--network_alpha=16', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=5e-05', '--unet_lr=0.0001', '--network_dim=32', '--output_name=melonav1', '--lr_scheduler_num_cycles=60', '--learning_rate=0.0001', '--lr_scheduler=constant_with_warmup', '--lr_warmup_steps=900', '--train_batch_size=1', '--max_train_steps=9000', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1234', '--caption_extension=.txt', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--color_aug', '--flip_aug', '--shuffle_caption', '--xformers', '--persistent_data_loader_workers', '--bucket_no_upscale', '--noise_offset=0.05']' returned non-zero exit status 1.
Does anyone know what is wrong with it? Please advise.