[Bug]: AssertionError: Torch not compiled with CUDA enabled

[vararth]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits

Bug Description

Unable to run and install Kandinsky

Step-by-step instructions to reproduce the issue.

Simple Install button, unable to launch

Expected Behavior

Should install everything and launch correctly

Current Behavior

Not launching and giving the error as mentioned

Version or Commit where the problem happens

0.1.4.8

What platforms do you use SEAIT ?

Windows

What Python version are you running on ?

3.11.8

What proccecor do you running on SEAIT ?

No response

What GPU are you running SEAIT on?

RTX 3050

How much GPU VRAM are you running SEAIT on?

N.A.

On what Project the issue are you facing?

Kandinsky

Console logs

launching Kandinsky-2 at C:\Users\Admin\seait\Kandinsky-2
C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
  torch.utils._pytree._register_pytree_node(
C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\huggingface_hub\file_download.py:678: FutureWarning: 'cached_download' is the legacy way to download files from the HF hub, please consider upgrading to 'hf_hub_download'
  warnings.warn(
Traceback (most recent call last):
  File "C:\Users\Admin\seait\Kandinsky-2\app.py", line 13, in <module>
    model = get_kandinsky2(
            ^^^^^^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\kandinsky2\__init__.py", line 180, in get_kandinsky2
    model = get_kandinsky2_1(
            ^^^^^^^^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\kandinsky2\__init__.py", line 160, in get_kandinsky2_1
    model = Kandinsky2_1(config, cache_model_name, cache_prior_name, device, task_type=task_type)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\kandinsky2\kandinsky2_1_model.py", line 64, in __init__
    self.clip_model, self.preprocess = clip.load(
                                       ^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\clip\clip.py", line 139, in load
    model = build_model(state_dict or model.state_dict()).to(device)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\torch\nn\modules\module.py", line 1152, in to
    return self._apply(convert)
           ^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\torch\nn\modules\module.py", line 802, in _apply
    module._apply(fn)
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\torch\nn\modules\module.py", line 802, in _apply
    module._apply(fn)
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\torch\nn\modules\module.py", line 825, in _apply
    param_applied = fn(param)
                    ^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\torch\nn\modules\module.py", line 1150, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Admin\seait\Kandinsky-2\venv\Lib\site-packages\torch\cuda\__init__.py", line 293, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

Additional information

Looking for support - and hopefully an extension to inference with Kandinsky 2.2 :)