这是什么原因

Question

这是什么原因

Fihade opened this issue 6 months ago · 4 comments

Answer 1 · 2024-06-26T09:20:50.000Z

报错往上拉拉,这是哪个节点爆出的

Answer 2 · 2024-06-26T10:22:33.000Z

报错往上拉拉,这是哪个节点爆出的

If execution seems broken due to forward ComfyUI changes, you can disable the optimization from rgthree settings in ComfyUI.
当前分支(current branch): 71e2c91330a9d866ec05cdd10584bbb962896a99(HEAD)
目标分支(target branch): 71e2c91330a9d866ec05cdd10584bbb962896a99
From https://githubfast.com/kohya-ss/sd-scripts

branch 71e2c91330a9d866ec05cdd10584bbb962896a99 -> FETCH_HEAD
HEAD is now at 71e2c91 Merge pull request #1230 from kohya-ss/dependabot/github_actions/crate-ci/typos-1.19.0
===========================httpd.serve_forever() start=======================================
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.3.0+cu121 with CUDA 1201 (you have 2.1.2+cu121)
Python 3.10.14 (you have 3.10.13)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
Traceback (most recent call last):
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 38, in
import hook_kohya_ss_utils
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_utils.py", line 120, in
original_snapshot_download = diffusers.loaders.single_file.snapshot_download
AttributeError: module 'diffusers.loaders.single_file' has no attribute 'snapshot_download'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 40, in
from . import hook_kohya_ss_utils
ImportError: attempted relative import with no known parent package
!!! Exception during processing!!! 训练失败!!! 具体报错信息请查看控制台... Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182017", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '60992', '--other_config_json', '{"sample_prompt": "Anya"}']' returned non-zero exit status 1.
Traceback (most recent call last):
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 416, in run_hook_kohya_ss_run_file
subprocess.run(
File "/conda/lib/python3.10/subprocess.py", line 526, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182017", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '60992', '--other_config_json', '{"sample_prompt": "Anya"}']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/root/ComfyUI/execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/root/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/init.py", line 278, in start
return mz_train_tools_core.MZ_KohyaSSTrain_call(kwargs)
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 518, in MZ_KohyaSSTrain_call
run_hook_kohya_ss_run_file(
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 426, in run_hook_kohya_ss_run_file
raise Exception(f"训练失败!!! 具体报错信息请查看控制台... {e}")
Exception: 训练失败!!! 具体报错信息请查看控制台... Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182017", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '60992', '--other_config_json', '{"sample_prompt": "Anya"}']' returned non-zero exit status 1.

Prompt executed in 15.24 seconds
===========================httpd.serve_forever() end=======================================

diffusers 是什么版本

Answer 3 · 2024-06-26T10:27:42.000Z

### 更新 diffusers 版本之后，解决 ‘AttributeError: module 'diffusers.loaders.single_file' has no attribute 'snapshot_download'这个问题，遇到了新的问题，如下：

===============================================
当前分支(current branch): 71e2c91330a9d866ec05cdd10584bbb962896a99(HEAD)
目标分支(target branch): 71e2c91330a9d866ec05cdd10584bbb962896a99
From https://githubfast.com/kohya-ss/sd-scripts

branch 71e2c91330a9d866ec05cdd10584bbb962896a99 -> FETCH_HEAD
HEAD is now at 71e2c91 Merge pull request #1230 from kohya-ss/dependabot/github_actions/crate-ci/typos-1.19.0
===========================httpd.serve_forever() start=======================================
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.3.0+cu121 with CUDA 1201 (you have 2.1.2+cu121)
Python 3.10.14 (you have 3.10.13)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
/conda/lib/python3.10/site-packages/diffusers/models/transformers/transformer_2d.py:34: FutureWarning: Transformer2DModelOutput is deprecated and will be removed in version 1.0.0. Importing Transformer2DModelOutput from diffusers.models.transformer_2d is deprecated and this will be removed in a future version. Please use from diffusers.models.modeling_outputs import Transformer2DModelOutput, instead.
deprecate("Transformer2DModelOutput", "1.0.0", deprecation_message)
master_port = 47353
Traceback (most recent call last):
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 212, in
func_maptrain_func
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 163, in run_lora_sdxl
LOG({
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 183, in LOG
raise Exception(f"LOG failed: {resp.text}")
Exception: LOG failed:

<title>ERROR: The requested URL could not be retrieved</title> <style type="text/css">

!!! Exception during processing!!! 训练失败!!! 具体报错信息请查看控制台... Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182551", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '47353', '--other_config_json', '{"sample_prompt": "KiKi\n"}']' returned non-zero exit status 1.
Traceback (most recent call last):
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 416, in run_hook_kohya_ss_run_file
subprocess.run(
File "/conda/lib/python3.10/subprocess.py", line 526, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182551", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '47353', '--other_config_json', '{"sample_prompt": "KiKi\n"}']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/root/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/root/ComfyUI/execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/root/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/init.py", line 278, in start
return mz_train_tools_core.MZ_KohyaSSTrain_call(kwargs)
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 518, in MZ_KohyaSSTrain_call
run_hook_kohya_ss_run_file(
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 426, in run_hook_kohya_ss_run_file
raise Exception(f"训练失败!!! 具体报错信息请查看控制台... {e}")
Exception: 训练失败!!! 具体报错信息请查看控制台... Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182551", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '47353', '--other_config_json', '{"sample_prompt": "KiKi\n"}']' returned non-zero exit status 1.

Prompt executed in 18.26 seconds
===========================httpd.serve_forever() end=======================================

Answer 4 · 2024-06-26T13:50:38.000Z

### 更新 diffusers 版本之后，解决 ‘AttributeError: module 'diffusers.loaders.single_file' has no attribute 'snapshot_download'这个问题，遇到了新的问题，如下：

=============================================== 当前分支(current branch): 71e2c91330a9d866ec05cdd10584bbb962896a99(HEAD) 目标分支(target branch): 71e2c91330a9d866ec05cdd10584bbb962896a99 From https://githubfast.com/kohya-ss/sd-scripts

branch 71e2c91330a9d866ec05cdd10584bbb962896a99 -> FETCH_HEAD
HEAD is now at 71e2c91 Merge pull request #1230 from kohya-ss/dependabot/github_actions/crate-ci/typos-1.19.0
===========================httpd.serve_forever() start=======================================
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.3.0+cu121 with CUDA 1201 (you have 2.1.2+cu121)
Python 3.10.14 (you have 3.10.13)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
/conda/lib/python3.10/site-packages/diffusers/models/transformers/transformer_2d.py:34: FutureWarning: Transformer2DModelOutput is deprecated and will be removed in version 1.0.0. Importing Transformer2DModelOutput from diffusers.models.transformer_2d is deprecated and this will be removed in a future version. Please use from diffusers.models.modeling_outputs import Transformer2DModelOutput, instead.
deprecate("Transformer2DModelOutput", "1.0.0", deprecation_message)
master_port = 47353
Traceback (most recent call last):
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 212, in
func_maptrain_func
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 163, in run_lora_sdxl
LOG({
File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py", line 183, in LOG
raise Exception(f"LOG failed: {resp.text}")
Exception: LOG failed:

<title>ERROR: The requested URL could not be retrieved</title> <style type="text/css"> !!! Exception during processing!!! 训练失败!!! 具体报错信息请查看控制台... Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182551", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '47353', '--other_config_json', '{"sample_prompt": "KiKi\n"}']' returned non-zero exit status 1. Traceback (most recent call last): File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 416, in run_hook_kohya_ss_run_file subprocess.run( File "/conda/lib/python3.10/subprocess.py", line 526, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182551", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '47353', '--other_config_json', '{"sample_prompt": "KiKi\n"}']' returned non-zero exit status 1.
During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/root/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/root/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/root/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/init.py", line 278, in start return mz_train_tools_core.MZ_KohyaSSTrain_call(kwargs) File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 518, in MZ_KohyaSSTrain_call run_hook_kohya_ss_run_file( File "/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/mz_train_tools_core.py", line 426, in run_hook_kohya_ss_run_file raise Exception(f"训练失败!!! 具体报错信息请查看控制台... {e}") Exception: 训练失败!!! 具体报错信息请查看控制台... Command '['/conda/bin/python', '/root/ComfyUI/custom_nodes/ComfyUI-TrainTools-MZ/hook_kohya_ss_run.py', '--sys_path', '/root/ComfyUI/models/minus_zone_models/train_tools/kohya_ss_lora', '--train_config_json', '{"pretrained_model_name_or_path": "/root/ComfyUI/models/checkpoints/sd_xl_base_1.0.safetensors", "max_train_steps": "15", "xformers": true, "sdpa": false, "fp8_base": false, "mixed_precision": "fp16", "cache_latents": true, "cache_latents_to_disk": true, "network_dim": "16", "network_alpha": "8", "network_module": "networks.lora", "network_train_unet_only": true, "learning_rate": "1e-5", "lr_scheduler": "cosine_with_restarts", "optimizer_type": "AdamW", "save_every_n_epochs": "5", "shuffle_caption": true, "lr_warmup_steps": "0", "save_precision": "fp16", "lr_scheduler_num_cycles": "1", "persistent_data_loader_workers": true, "no_metadata": true, "noise_offset": "0.1", "output_dir": "/root/ComfyUI/output/mz_train_workspaces/KiKi/output", "output_name": "KiKi_lora_sdxl_20240626_182551", "no_half_vae": true, "lowram": false, "dataset_config": "/root/ComfyUI/output/mz_train_workspaces/KiKi/dataset.toml", "max_train_epochs": "100"}', '--train_func', 'run_lora_sdxl', '--master_port', '47353', '--other_config_json', '{"sample_prompt": "KiKi\n"}']' returned non-zero exit status 1.

Prompt executed in 18.26 seconds ===========================httpd.serve_forever() end=======================================

看起来像是xformers报错,试一下拉一下高级设置的节点,关掉xformers试试看