Sdkit

- [Fix a bug where some loras would be numpy arrays](https://github.com/easydiffusion/sdkit/commit/4d110af684acbfcf5754ca6171ee3b23a62335f8)
- [torchruntime 1.9.4 fixes mps not getting recognized](https://github.com/easydiffusion/sdkit/commit/1e34d289a59c7ecd763bf92416ea11b2e63dfe1a)

Install using `python -m pip install sdkit==2.0.22.6`

Allow a string device ID argument in `sdkit.utils.is_cpu_device()`

Install using `python -m pip install sdkit==2.0.22.4`

* Convenient command to test image generation from the command line, without writing python code: `python -m sdkit -p 'Astronaut riding a horse' -m 'path/to/sd-model.safetensors'`
* Minor refactor - move torch-device utilities to `torchruntime`
* Minor bugfix (remove a missed hardcoding of cuda)

Install using `python -m pip install sdkit==2.0.22.2`

Adds support for DirectML (AMD and Integrated GPUs on Windows), Intel XPU (Arc) and MTIA.

Install using `python -m pip install sdkit==2.0.22`

Workaround for a bug in basicsr with newer versions of `torchvision`, also fixes codeformer.

Install using `python -m pip install sdkit==2.0.21.1`

Workaround for a bug in basicsr with newer versions of `torchvision`.

Install using `python -m pip install sdkit==2.0.21`