From the source
From the source
Hugging Face and
Apple released Core ML versions of Stable Diffusion XL for Mac, including a mixed-bit palettization technique that compresses the model from 4.8 GB to 1.4 GB (71% reduction) while maintaining quality.
The release includes ported base models, updated conversion and inference tools, and a demo app.
From the source
For Stable Diffusion XL we’ve done a few things: Ported the base model to Core ML so you can use it in your native Swift apps. Updated Apple’s conversion and inference repo so you can convert the models yourself, including any fine-tunes you’re interested in. Updated Hugging Face’s demo app to show how to use the new Core ML Stable Diffusion XL models downloaded from the Hub. Explored mixed-bit palettization, an advanced compression technique that achieves important size reductions while minimizing and controlling the quality loss you incur.
