Core ML converted model

This model was converted to Core ML for use on Apple Silicon devices by following Apple's instructions here.
Provide the model to an app such as Mochi Diffusion to generate images.

split_einsum versions are compatible with all compute units.
original versions are only compatible with CPU & GPU.

Complex Lineart

Source: Hugging Face

Trained on around 100 images at 768x768 resolution.

Download "ComplexLA Style.ckpt" and add it to your model folder.

Use prompt: ComplexLA style Use resolution near 768x768, lower resolution works but quality will not be as good.