Sdkit

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`

- **ControlNet** - Full support for ControlNet, including custom ControlNets. Set them using `context.model_paths['controlnet'] = '/path/to/controlnet.safetensors'; load_model(context, 'controlnet')`.
- **SDXL** - Full support for SDXL. No configuration necessary, just load the SDXL model like any stable diffusion model.
- **Multiple LoRAs** - Use multiple LoRAs, including SDXL and SD2-compatible LoRAs. Set them using `context.model_paths['lora'] = '/path/to/lora.safetensors'; load_model(context, 'lora')`.
- **Embeddings** - Use textual inversion embeddings easily. Set them using `context.model_paths['embeddings'] = '/path/to/embedding.pt'; load_model(context, 'embeddings')`. Thanks JeLuf.
- **Seamless Tiling** - Generate repeating textures that can be useful for games and other art projects. Works best in 512x512 resolution. Thanks JeLuf.
- **Inpainting Models** - Full support for inpainting models, including custom inpainting models. No configuration (or yaml files) necessary.
- **Faster than v2.5** - Nearly 40% faster than sdkit v1.0, and can be even faster if you enable xFormers.
- **Even less VRAM usage** - Less than 2 GB for 512x512 images on 'low' VRAM usage setting (SD 1.5). Can generate large images with SDXL.
- **WebP images** - Supports saving images in the lossless webp format.
- **Three new samplers, and latent upscaler** - Added `DEIS`, `DDPM` and `DPM++ 2m SDE` as additional samplers. Thanks ogmaresca and rbertus2000.
- **Major rewrite of the code** - We've switched to using diffusers under-the-hood, which allows us to release new features faster.