v3.2.0

Another pre-release of v3, based on stable-diffusion.cpp.

The release artifacts aren't meant to be downloaded directly (for now). They will be fetched in Easy Diffusion as individual files.

v2.1.1

• Disable outdated and broken LoRA compatibility check

v3.1.0

Another pre-release of v3, based on stable-diffusion.cpp.

The release artifacts aren't meant to be downloaded directly (for now). They will be fetched in Easy Diffusion as individual files.

v3.0.0

First release of v3, based on stable-diffusion.cpp.

The release artifacts aren't meant to be downloaded directly (for now). They will be fetched in Easy Diffusion as individual files.

v2.1.0

Install using python -m pip install sdkit==2.1.0

v2.0.22.6

• Fix a bug where some loras would be numpy arrays
• torchruntime 1.9.4 fixes mps not getting recognized

Install using python -m pip install sdkit==2.0.22.6

v2.0.22.4

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

Install using python -m pip install sdkit==2.0.22.4

v2.0.22.2

• 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

v2.0.22

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

v2.0.21.1

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