已解決！我 用的是比較老的顯卡，新的顯卡不會(huì)出現(xiàn)這個(gè)問(wèn)題。

舊版本刪除 --use_8bit_adam ：

新版本直接關(guān)掉：

----------------分界線---------------

大佬們，幫幫忙吧??！[大哭][大哭][大哭]

煉一步就報(bào)錯(cuò)

Error no kernel image is available for execution on the device at line 167 in file D:\ai\tool\bitsandbytes\csrc\ops.cu

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 "H:\SD-WebUI\lora-scripts\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>

?File "H:\SD-WebUI\lora-scripts\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main

??args.func(args)

?File "H:\SD-WebUI\lora-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command

??simple_launcher(args)

?File "H:\SD-WebUI\lora-scripts\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:\\SD-WebUI\\lora-scripts\\venv\\Scripts\\python.exe', './sd-scripts/train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=./sd-models/naifu4g.ckpt', '--train_data_dir=./train', '--output_dir=./output', '--logging_dir=./logs', '--resolution=512,512', '--network_module=networks.lora', '--max_train_epochs=20', '--learning_rate=1e-4', '--unet_lr=1e-4', '--mixed_precision=no', '--save_precision=fp16', '--text_encoder_lr=1e-5', '--network_dim=32', '--network_alpha=32', '--output_name=beatrice', '--lr_scheduler=cosine_with_restarts', '--train_batch_size=1', '--save_every_n_epochs=1', '--seed=1337', '--cache_latents', '--clip_skip=2', '--prior_loss_weight=1', '--max_token_length=225', '--caption_extension=.txt', '--save_model_as=safetensors', '--shuffle_caption', '--use_8bit_adam']' returned non-zero exit status 1.

Train finished