Getting custom directories to work using cmd arguments --config --ckpt --ckpt-dir --vae-path --vae-dir --embeddings-dir --lora-dir --hypernetwork-dir

[smasonlawrence]

I am trying to create two different .bat files, one to load only SD15 models, etc, and another to only load SDXL models etc. This is due to having 8000+ models in my files, it bogs down SD and chrome for obvious reasons. However using the custom cmd line arguments dont seem to work, example below and error after that. It seems to cause a CUDA error as well, however running without any of the directory & file arguments SD loads flawlessly without issues. Anybody have any idea how these cmd line arguments are supposed to work, am I doing it right?

Custom BAT file arguments

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--opt-sdp-no-mem-attention --no-half --no-half-vae --opt-channelslast --xformers --config X:\Stable_Diffusion\sd.webui\webui\config.json --ckpt X:\Models\SD15\Checkpoints\Realistic\SFW\realisticVisionV60B1_v51VAE.safetensors --ckpt-dir X:\Models\SD15\Checkpoints --vae-path X:\Models\SD15\VAE\vae-ft-mse-840000.safetensors --vae-dir X:\Models\SD15\VAE --embeddings-dir X:\Models\SD15\Embeddings --lora-dir X:\Models\SD15\Lora --hypernetwork-dir X:\Models\SD15\Hyper_Networks


call git checkout master
call git pull
call webui.bat

Output using BAT with cmd line arguments:

Already on 'master'
M       webui-user.bat
Your branch is up to date with 'origin/master'.
Already up to date.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.9.3
Commit hash: 1c0a0c4c26f78c32095ebc7f8af82f5c04fca8c0
If submitting an issue on github, please provide the full startup log for debugging purposes.

Initializing Dreambooth
Dreambooth revision: 45a12fe5950bf93205b6ef2b7511eb94052a241f
Checking xformers...
Checking bitsandbytes...
Checking bitsandbytes (ALL!)
Checking Dreambooth requirements...
Installed version of bitsandbytes: 0.43.0
[Dreambooth] bitsandbytes v0.43.0 is already installed.
Installed version of accelerate: 0.21.0
[Dreambooth] accelerate v0.21.0 is already installed.
Installed version of dadaptation: 3.2
[Dreambooth] dadaptation v3.2 is already installed.
Installed version of diffusers: 0.27.2
[Dreambooth] diffusers v0.25.0 is already installed.
Installed version of discord-webhook: 1.3.0
[Dreambooth] discord-webhook v1.3.0 is already installed.
Installed version of fastapi: 0.94.0
[Dreambooth] fastapi is already installed.
Installed version of gitpython: 3.1.32
[Dreambooth] gitpython v3.1.40 is not installed.
Successfully installed gitpython-3.1.43

Installed version of pytorch_optimizer: 2.12.0
[Dreambooth] pytorch_optimizer v2.12.0 is already installed.
Installed version of Pillow: 9.5.0
[Dreambooth] Pillow is already installed.
Installed version of tqdm: 4.66.2
[Dreambooth] tqdm is already installed.
Installed version of tomesd: 0.1.3
[Dreambooth] tomesd v0.1.2 is already installed.
Installed version of tensorboard: 2.13.0
[Dreambooth] tensorboard v2.13.0 is already installed.
[+] torch version 2.1.2+cu121 installed.
[+] torchvision version 0.16.2+cu121 installed.
[+] accelerate version 0.21.0 installed.
[+] diffusers version 0.27.2 installed.
[+] bitsandbytes version 0.43.0 installed.
[+] xformers version 0.0.23.post1 installed.
Launching Web UI with arguments: --opt-sdp-no-mem-attention --no-half --no-half-vae --opt-channelslast --xformers --config X:Stable_Diffusionsd.webuiwebuiconfig.json --ckpt X:ModelsSD15CheckpointsRealisticSFWrealisticVisionV60B1_v51VAE.safetensors --ckpt-dir X:ModelsSD15Checkpoints --vae-path X:ModelsSD15VAEvae-ft-mse-840000.safetensors --vae-dir X:ModelsSD15VAE --embeddings-dir X:ModelsSD15Embeddings --lora-dir X:ModelsSD15Lora --hypernetwork-dir X:ModelsSD15Hyper_Networks
Checkpoint in --ckpt argument not found (Possible it was moved to X:\Stable_Diffusion\sd.webui\webui\models\Stable-diffusion: X:ModelsSD15CheckpointsRealisticSFWrealisticVisionV60B1_v51VAE.safetensors
CHv1.8.7: Get Custom Model Folder
[-] ADetailer initialized. version: 24.4.2, num models: 27
CivitAI Browser+: Aria2 RPC started
[AddNet] Updating model hashes...
0it [00:00, ?it/s]
[AddNet] Updating model hashes...
0it [00:00, ?it/s]
ControlNet preprocessor location: X:\Stable_Diffusion\sd.webui\webui\extensions\sd-webui-controlnet\annotator\downloads
2024-05-23 11:18:07,809 - ControlNet - INFO - ControlNet v1.1.448
Checkpoint Checkpoints\Realistic\SFW\SD15\realisticVisionV60B1_v51VAE.safetensors [ef76aa2332] not found; loading fallback v1-5-pruned-emaonly.safetensors [6ce0161689]
Loading weights [6ce0161689] from X:\Stable_Diffusion\sd.webui\webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
CHv1.8.7: Set Proxy:
2024-05-23 11:18:10,420 - ControlNet - INFO - ControlNet UI callback registered.
Checkpoint in --ckpt argument not found (Possible it was moved to X:\Stable_Diffusion\sd.webui\webui\models\Stable-diffusion: X:ModelsSD15CheckpointsRealisticSFWrealisticVisionV60B1_v51VAE.safetensors
Creating model from config: X:\Stable_Diffusion\sd.webui\webui\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 83.8s (prepare environment: 27.7s, import torch: 5.0s, import gradio: 1.2s, setup paths: 1.6s, initialize shared: 2.5s, other imports: 32.1s, setup gfpgan: 0.4s, list SD models: 0.3s, load scripts: 8.3s, create ui: 4.4s, gradio launch: 0.3s).
loading stable diffusion model: AssertionError
Traceback (most recent call last):
  File "threading.py", line 973, in _bootstrap
  File "threading.py", line 1016, in _bootstrap_inner
  File "threading.py", line 953, in run
  File "X:\Stable_Diffusion\sd.webui\webui\modules\initialize.py", line 149, in load_model
    shared.sd_model  # noqa: B018
  File "X:\Stable_Diffusion\sd.webui\webui\modules\shared_items.py", line 175, in sd_model
    return modules.sd_models.model_data.get_sd_model()
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 620, in get_sd_model
    load_model()
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 748, in load_model
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 474, in load_model_weights
    sd_vae.load_vae(model, vae_file, vae_source)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_vae.py", line 207, in load_vae
    assert os.path.isfile(vae_file), f"VAE {vae_source} doesn't exist: {vae_file}"
AssertionError: VAE from commandline argument doesn't exist: X:ModelsSD15VAEvae-ft-mse-840000.safetensors


Stable diffusion model failed to load
Applying attention optimization: xformers... done.
Advanced elements visible: False
Loading weights [6ce0161689] from X:\Stable_Diffusion\sd.webui\webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
Creating model from config: X:\Stable_Diffusion\sd.webui\webui\configs\v1-inference.yaml
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "threading.py", line 973, in _bootstrap
  File "threading.py", line 1016, in _bootstrap_inner
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\gradio\utils.py", line 707, in wrapper
    response = f(*args, **kwargs)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\ui.py", line 1154, in <lambda>
    update_image_cfg_scale_visibility = lambda: gr.update(visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit")
  File "X:\Stable_Diffusion\sd.webui\webui\modules\shared_items.py", line 175, in sd_model
    return modules.sd_models.model_data.get_sd_model()
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 620, in get_sd_model
    load_model()
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 748, in load_model
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 393, in load_model_weights
    model.load_state_dict(state_dict, strict=False)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 223, in <lambda>
    module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 221, in load_state_dict
    original(module, state_dict, strict=strict)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2138, in load_state_dict
    load(self, state_dict)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
    load(child, child_state_dict, child_prefix)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
    load(child, child_state_dict, child_prefix)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
    load(child, child_state_dict, child_prefix)
  [Previous line repeated 1 more time]
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2120, in load
    module._load_from_state_dict(
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 225, in <lambda>
    linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 191, in load_from_state_dict
    module._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\_meta_registrations.py", line 4516, in zeros_like
    res.fill_(0)
RuntimeError: CUDA error: unknown error
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



Stable diffusion model failed to load
Loading weights [6ce0161689] from X:\Stable_Diffusion\sd.webui\webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
Creating model from config: X:\Stable_Diffusion\sd.webui\webui\configs\v1-inference.yaml
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "threading.py", line 973, in _bootstrap
  File "threading.py", line 1016, in _bootstrap_inner
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\gradio\utils.py", line 707, in wrapper
    response = f(*args, **kwargs)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\ui.py", line 1154, in <lambda>
    update_image_cfg_scale_visibility = lambda: gr.update(visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit")
  File "X:\Stable_Diffusion\sd.webui\webui\modules\shared_items.py", line 175, in sd_model
    return modules.sd_models.model_data.get_sd_model()
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 620, in get_sd_model
    load_model()
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 748, in load_model
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_models.py", line 393, in load_model_weights
    model.load_state_dict(state_dict, strict=False)
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 223, in <lambda>
    module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 221, in load_state_dict
    original(module, state_dict, strict=strict)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2138, in load_state_dict
    load(self, state_dict)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
    load(child, child_state_dict, child_prefix)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
    load(child, child_state_dict, child_prefix)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
    load(child, child_state_dict, child_prefix)
  [Previous line repeated 1 more time]
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\nn\modules\module.py", line 2120, in load
    module._load_from_state_dict(
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 225, in <lambda>
    linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
  File "X:\Stable_Diffusion\sd.webui\webui\modules\sd_disable_initialization.py", line 191, in load_from_state_dict
    module._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
  File "X:\Stable_Diffusion\sd.webui\system\python\lib\site-packages\torch\_meta_registrations.py", line 4516, in zeros_like
    res.fill_(0)
RuntimeError: CUDA error: unknown error
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



Stable diffusion model failed to load

Output using BAT without cmd line arguments:

Already on 'master'
M       webui-user.bat
Your branch is up to date with 'origin/master'.
Already up to date.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.9.3
Commit hash: 1c0a0c4c26f78c32095ebc7f8af82f5c04fca8c0
Installing requirements
If submitting an issue on github, please provide the full startup log for debugging purposes.

Initializing Dreambooth
Dreambooth revision: 45a12fe5950bf93205b6ef2b7511eb94052a241f
Checking xformers...
Checking bitsandbytes...
Checking bitsandbytes (ALL!)
Checking Dreambooth requirements...
Installed version of bitsandbytes: 0.43.0
[Dreambooth] bitsandbytes v0.43.0 is already installed.
Installed version of accelerate: 0.21.0
[Dreambooth] accelerate v0.21.0 is already installed.
Installed version of dadaptation: 3.2
[Dreambooth] dadaptation v3.2 is already installed.
Installed version of diffusers: 0.27.2
[Dreambooth] diffusers v0.25.0 is already installed.
Installed version of discord-webhook: 1.3.0
[Dreambooth] discord-webhook v1.3.0 is already installed.
Installed version of fastapi: 0.94.0
[Dreambooth] fastapi is already installed.
Installed version of gitpython: 3.1.32
[Dreambooth] gitpython v3.1.40 is not installed.
Successfully installed gitpython-3.1.43

Installed version of pytorch_optimizer: 2.12.0
[Dreambooth] pytorch_optimizer v2.12.0 is already installed.
Installed version of Pillow: 9.5.0
[Dreambooth] Pillow is already installed.
Installed version of tqdm: 4.66.2
[Dreambooth] tqdm is already installed.
Installed version of tomesd: 0.1.3
[Dreambooth] tomesd v0.1.2 is already installed.
Installed version of tensorboard: 2.13.0
[Dreambooth] tensorboard v2.13.0 is already installed.
[+] torch version 2.1.2+cu121 installed.
[+] torchvision version 0.16.2+cu121 installed.
[+] accelerate version 0.21.0 installed.
[+] diffusers version 0.27.2 installed.
[+] bitsandbytes version 0.43.0 installed.
[+] xformers version 0.0.23.post1 installed.
Launching Web UI with arguments: --opt-sdp-no-mem-attention --no-half --no-half-vae --opt-channelslast --xformers
CHv1.8.7: Get Custom Model Folder
[-] ADetailer initialized. version: 24.4.2, num models: 27
CivitAI Browser+: Aria2 RPC started
[AddNet] Updating model hashes...
0it [00:00, ?it/s]
[AddNet] Updating model hashes...
0it [00:00, ?it/s]
ControlNet preprocessor location: X:\Stable_Diffusion\sd.webui\webui\extensions\sd-webui-controlnet\annotator\downloads
2024-05-23 11:37:08,511 - ControlNet - INFO - ControlNet v1.1.448
Checkpoint Checkpoints\Realistic\SFW\SD15\realisticVisionV60B1_v51VAE.safetensors [ef76aa2332] not found; loading fallback v1-5-pruned-emaonly.safetensors [6ce0161689]
Loading weights [6ce0161689] from X:\Stable_Diffusion\sd.webui\webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
CHv1.8.7: Set Proxy:
2024-05-23 11:37:09,772 - ControlNet - INFO - ControlNet UI callback registered.
Creating model from config: X:\Stable_Diffusion\sd.webui\webui\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 39.0s (prepare environment: 24.4s, import torch: 4.4s, import gradio: 1.0s, setup paths: 1.3s, initialize shared: 0.2s, other imports: 0.7s, load scripts: 3.3s, create ui: 3.3s, gradio launch: 0.3s).
Applying attention optimization: xformers... done.
Model loaded in 5.5s (load weights from disk: 2.6s, create model: 0.8s, apply weights to model: 1.8s, calculate empty prompt: 0.1s).

[smasonlawrence]

Ok figured it out, i guess you have to use a forward slash instead of a backslash.
Leaving this for others incase anybody makes the same dumb mistake I did lol