[bug]: NotImplementedError: Cannot copy out of meta tensor; no data!

[lcsondes]

Is there an existing issue for this problem?

• [X] I have searched the existing issues

Operating system

Windows

GPU vendor

Nvidia (CUDA)

GPU model

RTX 4090

GPU VRAM

24 GB

Version number

v5.0.0

Browser

Backend issue

Python dependencies

{
  "accelerate": "0.30.1",
  "compel": "2.0.2",
  "cuda": "12.1",
  "diffusers": "0.27.2",
  "numpy": "1.26.4",
  "opencv": "4.9.0.80",
  "onnx": "1.15.0",
  "pillow": "10.4.0",
  "python": "3.10.11",
  "torch": "2.2.2+cu121",
  "torchvision": "0.17.2+cu121",
  "transformers": "4.41.1",
  "xformers": "0.0.25.post1"
}

What happened

[2024-09-25 21:32:25,455]::[InvokeAI]::ERROR --> Error while invoking session 45c271cd-85c1-4b5a-a4b5-9599d8a1c961, invocation a322fb69-feaa-4cd7-af05-02e418c5f057 (compel): Cannot copy out of meta tensor; no data!
[2024-09-25 21:32:25,455]::[InvokeAI]::ERROR --> Traceback (most recent call last):
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\app\services\session_processor\session_processor_default.py", line 129, in run_node
    output = invocation.invoke_internal(context=context, services=self._services)
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\app\invocations\baseinvocation.py", line 290, in invoke_internal
    output = self.invoke(context)
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\app\invocations\compel.py", line 81, in invoke
    with (
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\contextlib.py", line 135, in __enter__
    return next(self.gen)
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\backend\model_manager\load\load_base.py", line 77, in model_on_device
    locked_model = self._locker.lock()
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\backend\model_manager\load\model_cache\model_locker.py", line 45, in lock
    self._cache.move_model_to_device(self._cache_entry, self._cache.execution_device)
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\backend\model_manager\load\model_cache\model_cache_default.py", line 308, in move_model_to_device
    raise e
  File "C:\Apps\InvokeAI\.venv\lib\site-packages\invokeai\backend\model_manager\load\model_cache\model_cache_default.py", line 302, in move_model_to_device
    new_dict[k] = v.to(target_device, copy=True)
NotImplementedError: Cannot copy out of meta tensor; no data!

What you expected to happen

No errors

How to reproduce the problem

Attempt to generate anything using this model https://civitai.com/models/3627/protogen-v22-anime-official-release or this one: https://civitai.com/models/3666/protogen-x34-photorealism-official-release

Additional context

These models are SD1.5-based, and they work in AUTOMATIC1111/stable-diffusion-webui.

I can use other SD1.5-based models in InvokeAI.

Discord username

No response