Mochi Diffusion 3.1

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.

1. 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
2. By default, the app’s model folder will be created under the Documents folder. This location can be customized under Settings
3. 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
4. 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
        ├── ...
        └── ...

Compatibility

• Apple Silicon (M1 and later) or Intel Mac (high performance CPU & GPU required)
• macOS Ventura 13.1 and later
• Xcode 14.2 (to build)

What's New

Version 3.1:

• Added option to auto select ML Compute Unit (@vzsg)
• Added support for restoring jpeg files (@vzsg)
• Changed default model & image folder directory to user's home directory
• Changed import behavior to copy images
• Updated translations

Requirements

macOS 13.1 or later.
Apple Silicon or Intel Core processor

Screenshots

Download File

Size: 64.1 MB

Rapidgator Download | NitroFlare Download