Stable Diffusion XL on Mac with Advanced Core ML Quantization

What changed

The downside is that the model is much bigger, and therefore slower and more difficult to run on consumer hardware. Using the latest release of the Hugging Face diffusers library, you can run Stable Diffusion XL on CUDA hardware in 16 GB of GPU RAM, making it possible to use it on Colab’s free tier. This is an example of the latter using the new Stable Diffusion XL pipeline: As with previous Stable Diffusion releases, we expect the community to come up with novel fine-tuned versions for different domains, and many of them will be converted to Core ML.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• 🧨 Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e
• Using LoRA for Efficient Stable Diffusion Fine-Tuning
• Accelerating Stable Diffusion Inference on Intel CPUs

• 🧨 Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e similarity 0.35
• Using LoRA for Efficient Stable Diffusion Fine-Tuning similarity 0.28
• Accelerating Stable Diffusion Inference on Intel CPUs similarity 0.27