andrei-zgirvaci/coreml-stable-diffusion-2-1-split-einsum-v2-txt2img

Core ML Converted Model

This model was converted to Core ML for use on Apple Silicon devices using the following Python script, following Apple's instructions here:

python -m python_coreml_stable_diffusion.torch2coreml \
  --model-version stabilityai/stable-diffusion-2-1-base \
  --convert-unet \
  --convert-text-encoder \
  --convert-vae-decoder \
  --convert-safety-checker \
  --chunk-unet \
  --attention-implementation SPLIT_EINSUM_V2 \
  --compute-unit CPU_AND_NE \
  --bundle-resources-for-swift-cli \
  -o models/stable-diffusion-2-1/split_einsum_v2/compiled

Read more about the conversion process at: Convert Your Own Model.

This model it's intended for testing purposes within the expo-stable-diffusion module.