Does it work on Intel GPUs?

[Jaeha47]

It just stuck at " 0%| | 0/15 [00:00<?, ?it/s] " Is it because of my Intel Arc? Or did i do something wrong?

*edit ok now it gave the error

 raise ValueError(err.format(mode="fp16", requirement="a GPU"))
ValueError: fp16 mixed precision requires a GPU

So guess it doesnt with with Intel GPUs

/edit After setting Mixed Precision to no and Save Precision to float it in training parameter settings the first step worked but it then gives me a bounch of errors during the optimization.

E:\Arc Diffusion\Kohya\kohya_ss\venv\lib\site-packages\torch\utils\checkpoint.py:25: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
  warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
E:\Arc Diffusion\Kohya\kohya_ss\venv\lib\site-packages\torch\amp\autocast_mode.py:198: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
  warnings.warn('User provided device_type of \'cuda\', but CUDA is not available. Disabling')
Error CUDA driver version is insufficient for CUDA runtime version at line 167 in file D:\ai\tool\bitsandbytes\csrc\ops.cu
Traceback (most recent call last):
  File "C:\Users\denni\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\denni\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "E:\Arc Diffusion\Kohya\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>
  File "E:\Arc Diffusion\Kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
    args.func(args)
  File "E:\Arc Diffusion\Kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
    simple_launcher(args)
  File "E:\Arc Diffusion\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 '['E:\\Arc Diffusion\\Kohya\\kohya_ss\\venv\\Scripts\\python.exe', 'train_network.py', '--pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5', '--train_data_dir=C:/Users/PC/Desktop/Stamp/CharLORA/image', '--resolution=512,512', '--output_dir=C:/Users/PC/Desktop/Stamp/CharLORA/model', '--logging_dir=C:/Users/PC/Desktop/Stamp/CharLORA/log', '--network_alpha=128', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=5e-5', '--unet_lr=0.0001', '--network_dim=128', '--output_name=Feste', '--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=no', '--save_precision=float', '--seed=1234', '--caption_extension=.txt', '--cache_latents', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=1', '--clip_skip=2', '--bucket_reso_steps=64', '--mem_eff_attn', '--gradient_checkpointing', '--xformers', '--bucket_no_upscale']' returned non-zer

[bmaltais]

The solution is only supported under NVidia and (maybe) MacOS gpu... but I am not 100% sure if it work properly on MacOS Mx CPU/GPU

[nonetrix]

Really would like to see Intel Arc support since they have way more VRAM than the competition for cheaper despite the performance

[Disty0]

Intel ARC is working now: https://www.technopat.net/sosyal/konu/installing-kohya-ss-with-intel-arc-gpus.2869152/

[ep150de]

I'm still running into issues with getting kohya training to run on intel arc A770 gpu after following the --use-ipex flag for setup and running the gui.

error traceback: Traceback (most recent call last): File "C:\Users\Demo\kohya_ss\sdxl_train_network.py", line 189, in trainer.train(args) File "C:\Users\Demo\kohya_ss\train_network.py", line 242, in train vae.set_use_memory_efficient_attention_xformers(args.xformers) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 263, in set_use_memory_efficient_attention_xformers fn_recursive_set_mem_eff(module) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 259, in fn_recursive_set_mem_eff fn_recursive_set_mem_eff(child) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 259, in fn_recursive_set_mem_eff fn_recursive_set_mem_eff(child) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 259, in fn_recursive_set_mem_eff fn_recursive_set_mem_eff(child) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 256, in fn_recursive_set_mem_eff module.set_use_memory_efficient_attention_xformers(valid, attention_op) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\diffusers\models\attention_processor.py", line 255, in set_use_memory_efficient_attention_xformers raise ValueError( ValueError: torch.cuda.is_available() should be True but is False. xformers' memory efficient attention is only available for GPU Traceback (most recent call last): File "C:\Users\Demo\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\Demo\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "C:\Users\Demo\kohya_ss\venv\Scripts\accelerate.exe__main__.py", line 7, in File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 47, in main args.func(args) File "C:\Users\Demo\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 986, in launch_command simple_launcher(args) File "C:\Users\Demo\kohya_ss\venv\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\Demo\kohya_ss\venv\Scripts\python.exe', './sdxl_train_network.py', '--enable_bucket', '--min_bucket_reso=256', '--max_bucket_reso=2048', '--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0', '--train_data_dir=C:/Users/Demo/Desktop/pat/round2 training\img', '--resolution=1024,1024', '--output_dir=C:/Users/Demo/Desktop/pat/round2 training\model', '--logging_dir=C:/Users/Demo/Desktop/pat/round2 training\log', '--network_alpha=1', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=0.0004', '--unet_lr=0.0004', '--network_dim=256', '--output_name=patgv7_arc', '--lr_scheduler_num_cycles=4', '--no_half_vae', '--learning_rate=0.0004', '--lr_scheduler=constant', '--train_batch_size=2', '--max_train_steps=1680', '--save_every_n_epochs=1', '--mixed_precision=bf16', '--save_precision=bf16', '--cache_latents', '--cache_latents_to_disk', '--optimizer_type=Adafactor', '--optimizer_args', 'scale_parameter=False', 'relative_step=False', 'warmup_init=False', '--max_grad_norm=1', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--save_state', '--gradient_checkpointing', '--xformers', '--bucket_no_upscale', '--noise_offset=0.0']' returned non-zero exit status 1.

[Disty0]

Guide i sent tells you to use SDPA. Follow the guide.