README.md

---
title: Core ML Models
emoji: 🐱
pinned: false
tags:
  - coreml
  - stable-diffusion
---

# Core ML Models Repository

↓↓↓ **Scroll down to see models** ↓↓↓

Thanks to Apple engineers, we can now run Stable Diffusion on Apple Silicon using Core ML!<br>
However its hard to find compatible models and converting models isn't the easiest thing to do.<br>
By organizing Core ML models in one place, hopefully it will be easier to find them and for everyone to benefit.

## Conversion flags

The models were converted using the following flags:<br>
`--convert-unet --convert-text-encoder --convert-vae-decoder --bundle-resources-for-swift-cli --attention-implementation {SPLIT_EINSUM or ORIGINAL}`

## `split_einsum` vs `original` Models

Depending on what compute unit you select, you will need to use the correct model version.<br>
Some model versions may also generate other image sizes and are named as such.

`split_einsum` version is compatible with all compute unit options including Neural Engine.<br>
`original` version is only compatible with CPU & GPU option.

## Contributing

Do you have a model that was converted and wish to upload? Join our community or create a Pull Request to get started!<br>

### Repo Name

Repos are named with the original diffusers Hugging Face repo name prefixed by `coreml-`. So for example, `coreml-stable-diffusion-2-1`.

### Repo README Contents

You can copy the beginning template for the README from one of the repo models that already exists here.<br>
Then copy the original model's README as the body.

### Repo Directory Structure

```
coreml-stable-diffusion-2-1
├── README.md
├── original
│   ├── stable-diffusion-2-1_original_compiled.zip
│   ├── stable-diffusion-2-1_512x768_original_compiled.zip
│   └── ...
└── split_einsum
    └── stable-diffusion-2-1_split-einsum_compiled.zip
```