Mochi Diffusion 3.1

April 11, 2023

This app uses Apple’s Core ML Stable Diffusion implementation to achieve maximum performance and speed on Apple Silicon based Macs while reducing memory requirements. It also runs on Intel based Macs too.

Features

Extremely fast and memory efficient (~150MB with Neural Engine)
Runs well on all Apple Silicon Macs by fully utilizing Neural Engine
Generate images locally and completely offline
Generate images based on an existing image (commonly known as Image2Image)
Generated images are saved with prompt info inside EXIF metadata (view in Finder’s Get Info window)
Convert generated images to high resolution (using RealESRGAN)
Autosave & restore images
Use custom Stable Diffusion Core ML models
No worries about pickled models
macOS native app using SwiftUI

When using a model for the very first time, it may take up to 2 minutes for the Neural Engine to compile a cached version. Afterwards, subsequent generations will be much faster.

Compute Unit

CPU & Neural Engine provides a good balance between speed and low memory usage
CPU & GPU may be faster on M1 Max, Ultra and later but will use more memory

Depending on the option chosen, you will need to use the correct model version (see Models section for details).
Intel Macs uses CPU & GPU as it doesn’t have Neural Engine.

Models

You will need to convert or download Core ML models in order to use Mochi Diffusion.
A few models have been converted and uploaded here.

Convert or download Core ML models
- split_einsum version is compatible with all compute unit options including Neural Engine
- original version is only compatible with CPU & GPU option
By default, the app’s model folder will be created under the Documents folder. This location can be customized under Settings
In the model folder, create a new folder with the name you’d like displayed in the app then move or extract the converted models here
Your directory should look like this:

Documents/
└── MochiDiffusion/
    └── models/
        ├── stable-diffusion-2-1_split-einsum_compiled/
        │   ├── merges.txt
        │   ├── TextEncoder.mlmodelc
        │   ├── Unet.mlmodelc
        │   ├── VAEDecoder.mlmodelc
        │   ├── VAEEncoder.mlmodelc
        │   └── vocab.json
        ├── ...
        └── ...