Diffusion Bee runs Stable Diffusion locally on Mac and offers a one click installer without extra dependencies.
Open source
24 alternativesMochi Diffusion
The Mochi Diffusion project runs Stable Diffusion natively on Mac computers.
About Mochi Diffusion
Mochi Diffusion is a native macOS app for generating images locally with Stable Diffusion and FLUX.2 Klein models. Stable Diffusion models run through Apple's Core ML implementation, and FLUX.2 Klein models run through the Iris pipeline with Metal GPU acceleration. The app is built with SwiftUI and is open source.
Users must supply Core ML Stable Diffusion or FLUX.2 Klein models. Core ML models are converted to a fixed image size during conversion, so each one produces images at only that size. The first use of a Core ML model can take up to 2 minutes while the Neural Engine compiles a cached version. Later generations are faster.
Key features
- Generates images locally on Mac, described as working completely offline
- Supports Core ML Stable Diffusion and FLUX.2 Klein models
- Image-to-image generation and ControlNet with Stable Diffusion models
- Choice between CPU with Neural Engine or CPU with GPU compute units
- Saves PNG files with generation settings readable by compatible tools
- Built-in gallery with import, save, and sync support
Best for: Mac users who want to generate images locally with Stable Diffusion or FLUX.2 Klein models.
Good for
- Core ML models are described as fast and memory efficient on Apple Silicon Macs with Neural Engine
- Open source, with the repository available on GitHub
- Generation settings are stored in saved PNG files and can be read by AUTOMATIC1111-compatible tools
Watch out for
- Each Core ML model generates images at a fixed size set during conversion
- The CPU and GPU option may be faster on M1 Max, Ultra, and later but uses more memory
- The first use of a Core ML model can take up to 2 minutes
Mochi Diffusion at a glance
- Category
- AI & Machine Learning › AI Image Generators
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Mochi Diffusion alternatives
Tools and sites you could use instead, ranked by how closely they match.
A custom AUTOMATIC1111 script adds a small template language for generating random Stable Diffusion prompts.
Open source
24 alternatives
This repository provides Stable Diffusion Web UI notebooks for running through Google Colab.
Open source
24 alternatives
A Python library to remove unwanted pseudo-text from images generated by your favorite generative AI models (Stable Diffusion, Midjourney, DALL·E).
Open source
24 alternatives
Create videos with Stable Diffusion by exploring the latent space and morphing between text prompts.
Open source
24 alternatives
ComfyUI-Zluda adapts a Stable Diffusion interface and backend with ZLUDA enhancements for AMD GPU performance.
Open source
24 alternativesPopular in AI Image Generators
Well-known listings from the same topic.
FigureLabsfigurelabs.aiImagePromptGuruimagepromptguru.netAI SVGaisvg.artCGDreamcgdream.aiFlux.1 AIflux1.aiHairstyle AIhairstyleai.com
Mochi Diffusion FAQ
What models do I need to use Mochi Diffusion?
You need Core ML Stable Diffusion models or FLUX.2 Klein models. Core ML models must be converted or downloaded and placed in the model folder. FLUX.2 Klein models do not require conversion.
Where are models stored?
By default, the model folder is created under your home directory in MochiDiffusion/models. The location can be changed under Settings.
Why is the first generation slow?
When a Core ML model is used for the first time, the Neural Engine may take up to 2 minutes to compile a cached version. Subsequent generations are much faster.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.