Maple-Diffusion

Visit Tool

Maple Diffusion enables Stable Diffusion inference directly on iOS and macOS devices, utilizing the MPSGraph framework for local image generation. It offers fast performance, generating images in minutes on iPhones and under a second per step on macOS.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is maple-diffusion?

Maple Diffusion is an open-source project designed for running Stable Diffusion models locally on Apple devices, specifically iOS and macOS. It leverages Apple's MPSGraph framework, rather than Python, to achieve efficient inference. The tool is optimized for performance on Apple Silicon Macs and recent iPhones, with image generation times as low as <1 second per step on macOS and around 2.3 seconds per step on an iPhone 13 Pro. To overcome iOS memory limitations, Maple Diffusion employs FP16 (NHWC) tensors, operator fusion, and strategic model swapping to device storage. It supports various Stable Diffusion PyTorch model checkpoints and requires Xcode 14 and iOS 16 for building and running. The project also highlights related tools like Core ML Stable Diffusion and Native Diffusion, offering a robust solution for on-device AI image generation.

Best used for

Ideal for developers and AI enthusiasts who need to run Stable Diffusion models directly on their Apple devices, generate images quickly on iOS/macOS, and experiment with on-device AI inference. Especially valuable for those looking for a non-Python-based solution with optimized performance on Apple hardware.

Common actions

generate images

run AI models locally

develop iOS AI apps

"AI Agents"face swappinggithub copilotcollaborationdeepfakeopen-sourceworkflowsautomated workflowlow-code/no-code

Capabilities

Key features

Local Stable Diffusion inference
iOS/macOS native execution
MPSGraph framework
FP16 tensor support
Optimized for Apple Silicon

Target Audience

developersmachine learning engineersios developersresearchers

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What are the device requirements for running Maple Diffusion?

Maple Diffusion runs on any Apple Silicon Mac (M1, M2, etc.) and Intel Macs. For iOS, it requires devices with sufficient RAM (≥6144MB RAM, such as recent iPads or iPhones with the Increased Memory Limit capability enabled). It also expects Xcode 14 and iOS 16.

How does Maple Diffusion achieve good performance on iOS devices?

To achieve usable performance and manage iOS's 4GB memory limit, Maple Diffusion relies on several optimizations. These include using FP16 (NHWC) tensors, leveraging operator fusion from MPSGraph, and strategically swapping models to device storage. This allows for reasonable image generation times on iPhones.

Is Maple Diffusion an alternative to Apple's Core ML Stable Diffusion?

Yes, Maple Diffusion offers an alternative approach to running Stable Diffusion on Apple devices, using MPSGraph instead of Core ML. While Core ML has improved, Maple Diffusion was initially faster and provides a different implementation for developers interested in MPSGraph-based solutions.

Trending

Subcategories trending in Content & Design

AI Writing Assistants Audio & Music Video Generation Photo Editing Graphic Design Video Editing

Trending

Also listed in

This tool also appears in

Coding & Development › Mobile Development

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce