Neither CUDA_VISIBLE_DEVICES nor --cuda-device seems to be respected

Trying to run:

`CUDA_VISIBLE_DEVICES=1 python main.py`

and

```
export CUDA_VISIBLE_DEVICES=1
python main.py
```

Gets ignored entirely, but checking with:
`python main.py --help`

I see the flag _--cuda-devices_ yet this also does not seem to behave as expected:

```
$ python main.py --cuda-device 1
**Set cuda device to: 1**
Total VRAM 11009 MB, total RAM 128484 MB
xformers version: 0.0.23.post1
Set vram state to: NORMAL_VRAM
**Device: cuda:0** NVIDIA GeForce RTX 2080 Ti : cudaMallocAsync
VAE dtype: torch.float32
Using xformers cross attention
Starting server

To see the GUI go to: http://127.0.0.1:8188/
```

So even though I set it to use device 1 it is actually using device 0. This leads to OOM errors since device 0 is busy as illustrated by nvidia-smi and is why I am trying to get this to run on device 1.

$ nvidia-smiWed Dec 27 19:22:28 2023      
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.147.05   Driver Version: 525.147.05   CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  Off  | 00000000:17:00.0 Off |                  N/A |
| 41%   50C    P2    68W / 260W |   1928MiB / 11264MiB |      8%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   1  NVIDIA GeForce ...  Off  | 00000000:65:00.0 Off |                  N/A |
| 41%   46C    P8    27W / 260W |     18MiB / 11264MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A      1594      G   /usr/lib/xorg/Xorg                  4MiB |
|    0   N/A  N/A   1256382      C   python                           1920MiB |
|    1   N/A  N/A      1594      G   /usr/lib/xorg/Xorg                  9MiB |
|    1   N/A  N/A      1691      G   /usr/bin/gnome-shell                4MiB |
+-----------------------------------------------------------------------------+

$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description: Ubuntu 22.04.3 LTS
Release: 22.04
Codename: jammy

I setup the environment in Anaconda using:
```
conda create -n sdcomfy python=3.10
conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
conda install -c xformers xformers
conda install -c conda-forge transformers
conda install jupyter scikit-learn
```

I hit the error when trying to execute the SVD example. The SD image prompting works despite the constrained memory on device 0.