When further trying to reproduce the program, the following error occurs

[summeropow]

(textssr) D:\TextSSR-main>accelerate launch --num_processes 1 train_vae.py --config configs/train_vae_cfg.py
01/10/2025 16:15:36 - INFO - main - Distributed environment: NO
Num processes: 1
Process index: 0
Local process index: 0
Device: cpu

Mixed precision type: no

Traceback (most recent call last):
File "D:\TextSSR-main\diffusers\src\diffusers\configuration_utils.py", line 379, in load_config
config_file = hf_hub_download(
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\huggingface_hub\utils_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\huggingface_hub\utils_validators.py", line 154, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './model/stable-diffusion-v2-1\vae'. Use repo_type argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\TextSSR-main\train_vae.py", line 350, in
main()
File "D:\TextSSR-main\train_vae.py", line 132, in main
vae = AutoencoderKL.from_pretrained(os.path.join(cfgs.pretrained_model_name_or_path, "vae"), revision=cfgs.revision
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "D:\TextSSR-main\diffusers\src\diffusers\models\modeling_utils.py", line 607, in from_pretrained
config, unused_kwargs, commit_hash = cls.load_config(
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "D:\TextSSR-main\diffusers\src\diffusers\configuration_utils.py", line 415, in load_config
raise EnvironmentError(
OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like ./model/stable-diffusion-v2-1\vae is not the path to a directory containing a config.json file.
Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.
Traceback (most recent call last):
File "D:\ProgramData\anaconda3\envs\textssr\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "D:\ProgramData\anaconda3\envs\textssr\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "D:\ProgramData\anaconda3\envs\textssr\Scripts\accelerate.exe_main.py", line 7, in
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\accelerate\commands\accelerate_cli.py", line 48, in main
args.func(args)
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\accelerate\commands\launch.py", line 1168, in launch_command
simple_launcher(args)
File "D:\ProgramData\anaconda3\envs\textssr\lib\site-packages\accelerate\commands\launch.py", line 763, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['D:\ProgramData\anaconda3\envs\textssr\python.exe', 'train_vae.py', '--config', 'configs/train_vae_cfg.py']' returned non-zero exit status 1.

[YesianRohn]

Please check if the pre-trained model is placed at ./model/stable-diffusion-v2-1/vae.

[summeropow]

Later, I checked the location where the pretrained files are stored and confirmed that it was correct. However, a new error occurred, indicating that the json_path is missing in the train_vae_cfg.py file. The error message is as follows:

(textssr) kylin@kylin:~/nfs-ubuntu/TextSSR-main$ accelerate launch --num_processes 4 train_vae.py --config configs/train_vae_cfg.py
Traceback (most recent call last):
Traceback (most recent call last):
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 109, in getattr
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 109, in getattr
value = super().getattr(name)value = super().getattr(name)

File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/addict/addict.py", line 67, in getattr
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/addict/addict.py", line 67, in getattr
return self.getitem(item)return self.getitem(item)

File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 138, in getitem
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 138, in getitem
return self.build_lazy(super().getitem(key))return self.build_lazy(super().getitem(key))

File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 105, in missing
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 105, in missing
raise KeyError(name)raise KeyError(name)

KeyErrorKeyErrorTraceback (most recent call last):
: : 'json_path''json_path'

During handling of the above exception, another exception occurred:

File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 109, in getattr
Traceback (most recent call last):

During handling of the above exception, another exception occurred:

File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 354, in
Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 354, in
value = super().getattr(name)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/addict/addict.py", line 67, in getattr
main()main()

File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 71, in main
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 71, in main
return self.getitem(item)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 138, in getitem
cfgs = parse_cfgs()cfgs = parse_cfgs()

File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 50, in parse_cfgs
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 50, in parse_cfgs
return self.build_lazy(super().getitem(key))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 105, in missing
if cfgs.json_path is None:
if cfgs.json_path is None:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 1499, in getattr
raise KeyError(name) File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 1499, in getattr

KeyError: 'json_path'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 354, in
main()
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 71, in main
cfgs = parse_cfgs()
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 50, in parse_cfgs
return getattr(self._cfg_dict, name)return getattr(self._cfg_dict, name)

File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 113, in getattr
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 113, in getattr
if cfgs.json_path is None:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 1499, in getattr
raise AttributeError(f"'{self.class.name}' object has no "
raise AttributeError(f"'{self.class.name}' object has no "AttributeError
: 'ConfigDict' object has no attribute 'json_path'AttributeError: 'ConfigDict' object has no attribute 'json_path'

return getattr(self._cfg_dict, name)

File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 113, in getattr
raise AttributeError(f"'{self.class.name}' object has no "
AttributeError: 'ConfigDict' object has no attribute 'json_path'
Traceback (most recent call last):
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 109, in getattr
value = super().getattr(name)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/addict/addict.py", line 67, in getattr
return self.getitem(item)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 138, in getitem
return self.build_lazy(super().getitem(key))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 105, in missing
raise KeyError(name)
KeyError: 'json_path'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 354, in
main()
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 71, in main
cfgs = parse_cfgs()
File "/home/kylin/nfs-ubuntu/TextSSR-main/train_vae.py", line 50, in parse_cfgs
if cfgs.json_path is None:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 1499, in getattr
return getattr(self._cfg_dict, name)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/mmengine/config/config.py", line 113, in getattr
raise AttributeError(f"'{self.class.name}' object has no "
AttributeError: 'ConfigDict' object has no attribute 'json_path'
[2025-01-15 09:11:13,922] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 3674498 closing signal SIGTERM
[2025-01-15 09:11:13,922] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 3674499 closing signal SIGTERM
[2025-01-15 09:11:13,987] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 0 (pid: 3674496) of binary: /home/kylin/anaconda3/envs/textssr/bin/python
Traceback (most recent call last):
File "/home/kylin/anaconda3/envs/textssr/bin/accelerate", line 8, in
sys.exit(main())
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 48, in main
args.func(args)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/commands/launch.py", line 1159, in launch_command
multi_gpu_launcher(args)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/commands/launch.py", line 793, in multi_gpu_launcher
distrib_run.run(args)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/distributed/run.py", line 797, in run
elastic_launch(
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 134, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

train_vae.py FAILED

Failures:
[1]:
time : 2025-01-15_09:11:13
host : kylin
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 3674497)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

Root Cause (first observed failure):
[0]:
time : 2025-01-15_09:11:13
host : kylin
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 3674496)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

[YesianRohn]

The latest code has already solved this problem. Please update to the latest version.

[summeropow]

I tried the latest code and got a new error：FileNotFoundError: [Errno 2] No such file or directory: 'model/vae_ft/checkpoint-150000/pytorch_model.bin'

(textssr) kylin@kylin:~/nfs-ubuntu/TextSSR$ accelerate launch --num_processes 4 train_vae.py --config configs/train_vae_cfg.py
/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py:453: UserWarning: log_with=tensorboard was passed but no supported trackers are currently installed.
warnings.warn(f"log_with={log_with} was passed but no supported trackers are currently installed.")
/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py:453: UserWarning: log_with=tensorboard was passed but no supported trackers are currently installed.
warnings.warn(f"log_with={log_with} was passed but no supported trackers are currently installed.")
01/15/2025 15:40:37 - INFO - main - Distributed environment: MULTI_GPU Backend: nccl
Num processes: 4
Process index: 0
Local process index: 0
Device: cuda:0

Mixed precision type: no

/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py:453: UserWarning: log_with=tensorboard was passed but no supported trackers are currently installed.
warnings.warn(f"log_with={log_with} was passed but no supported trackers are currently installed.")
01/15/2025 15:40:37 - INFO - main - Distributed environment: MULTI_GPU Backend: nccl
Num processes: 4
Process index: 3
Local process index: 3
Device: cuda:3

Mixed precision type: no

/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py:453: UserWarning: log_with=tensorboard was passed but no supported trackers are currently installed.
warnings.warn(f"log_with={log_with} was passed but no supported trackers are currently installed.")
{'latents_mean', 'use_quant_conv', 'mid_block_add_attention', 'use_post_quant_conv', 'force_upcast', 'scaling_factor', 'latents_std', 'shift_factor'} was not found in config. Values will be initialized to default values.
01/15/2025 15:40:37 - INFO - main - Distributed environment: MULTI_GPU Backend: nccl
Num processes: 4
Process index: 1
Local process index: 1
Device: cuda:1

Mixed precision type: no

01/15/2025 15:40:37 - INFO - main - Distributed environment: MULTI_GPU Backend: nccl
Num processes: 4
Process index: 2
Local process index: 2
Device: cuda:2

Mixed precision type: no

Building Index for Dataset 0: 3430416it [2:39:01, 359.53it/s]

Building Index for Dataset 0: 3430416it [2:39:01, 359.53it/s]
Building Index for Dataset 0: 3430416it [2:39:01, 359.53it/s]
Building Index for Dataset 1: 78395it [05:00, 260.68it/s]

Building Index for Dataset 1: 78395it [05:00, 260.68it/s]
01/15/2025 18:24:56 - INFO - main - ***** Running training *****
01/15/2025 18:24:56 - INFO - main - Num examples = 15057991
01/15/2025 18:24:56 - INFO - main - Num Epochs = 100
01/15/2025 18:24:56 - INFO - main - Instantaneous batch size per device = 8
01/15/2025 18:24:56 - INFO - main - Total train batch size (w. parallel, distributed & accumulation) = 256
01/15/2025 18:24:56 - INFO - main - Gradient Accumulation steps = 8
01/15/2025 18:24:56 - INFO - main - Total optimization steps = 5882100
Resuming from checkpoint checkpoint-150000
01/15/2025 18:24:56 - INFO - accelerate.accelerator - Loading states from ./model/vae_ft/checkpoint-150000
Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 350, in
Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 350, in
Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 350, in
main()
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 284, in main
main()
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 284, in main
accelerator.load_state(os.path.join(cfgs.output_dir, path))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py", line 3238, in load_state
main()
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 284, in main
accelerator.load_state(os.path.join(cfgs.output_dir, path))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py", line 3238, in load_state
accelerator.load_state(os.path.join(cfgs.output_dir, path))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py", line 3238, in load_state
override_attributes = load_accelerator_state(
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/checkpointing.py", line 221, in load_accelerator_state
state_dict = load(input_model_file, map_location=map_location)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/utils/other.py", line 255, in load
override_attributes = load_accelerator_state(
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/checkpointing.py", line 221, in load_accelerator_state
loaded_obj = torch.load(f, map_location=map_location, **kwargs)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 986, in load
state_dict = load(input_model_file, map_location=map_location)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/utils/other.py", line 255, in load
override_attributes = load_accelerator_state(
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/checkpointing.py", line 221, in load_accelerator_state
loaded_obj = torch.load(f, map_location=map_location, **kwargs)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 986, in load
state_dict = load(input_model_file, map_location=map_location)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/utils/other.py", line 255, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 435, in _open_file_like
loaded_obj = torch.load(f, map_location=map_location, **kwargs)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 986, in load
return _open_file(name_or_buffer, mode)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 416, in init
with _open_file_like(f, 'rb') as opened_file:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 435, in _open_file_like
super().init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'model/vae_ft/checkpoint-150000/pytorch_model.bin'
return _open_file(name_or_buffer, mode)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 416, in init
with _open_file_like(f, 'rb') as opened_file:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 435, in _open_file_like
super().init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'model/vae_ft/checkpoint-150000/pytorch_model.bin'
return _open_file(name_or_buffer, mode)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 416, in init
super().init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'model/vae_ft/checkpoint-150000/pytorch_model.bin'
Traceback (most recent call last):
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 350, in
main()
File "/home/kylin/nfs-ubuntu/TextSSR/train_vae.py", line 284, in main
accelerator.load_state(os.path.join(cfgs.output_dir, path))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/accelerator.py", line 3238, in load_state
override_attributes = load_accelerator_state(
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/checkpointing.py", line 221, in load_accelerator_state
state_dict = load(input_model_file, map_location=map_location)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/utils/other.py", line 255, in load
loaded_obj = torch.load(f, map_location=map_location, **kwargs)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 986, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 435, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/serialization.py", line 416, in init
super().init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'model/vae_ft/checkpoint-150000/pytorch_model.bin'
[2025-01-15 18:25:06,637] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 3827275 closing signal SIGTERM
[2025-01-15 18:25:06,639] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 3827276 closing signal SIGTERM
[2025-01-15 18:25:06,639] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 3827278 closing signal SIGTERM
[2025-01-15 18:25:21,368] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 2 (pid: 3827277) of binary: /home/kylin/anaconda3/envs/textssr/bin/python
Traceback (most recent call last):
File "/home/kylin/anaconda3/envs/textssr/bin/accelerate", line 8, in
sys.exit(main())
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 48, in main
args.func(args)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/commands/launch.py", line 1159, in launch_command
multi_gpu_launcher(args)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/accelerate/commands/launch.py", line 793, in multi_gpu_launcher
distrib_run.run(args)
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/distributed/run.py", line 797, in run
elastic_launch(
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 134, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/kylin/anaconda3/envs/textssr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

[YesianRohn]

The VAE code and configuration files I provided do not involve the path 'model/vae_ft/checkpoint-150000'. Have you modified the configuration files and code?

[summeropow]

Thanks for your reply, no changes have been made to your code, the VAE file is downloaded from modelscope. Is the code seeking the diffusion_pytorch_model.bin in the image below?

[YesianRohn]

If you want to retrain the VAE, simply change the output path, for example to "./model/vae_ft_2". If you want to fine-tune it, you can replace the original VAE with the one we provided. The current code requires loading our original training logs, which cannot be provided at present.

[summeropow]

Currently, I am running the command accelerate launch --num_processes 8 train_vae.py --config configs/train_vae_cfg.py using the VAE file you provided in the modelscope VAE folder, but I encountered the following error:
FileNotFoundError: [Errno 2] No such file or directory: 'model/vae_ft/checkpoint-150000/pytorch_model.bin'.

[YesianRohn]

output_dir="./model/vae_ft_2"