Blaizzy
Featured
nativ
Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It showcases practical on-device AI image generation with careful memory optimization, detailed performance benchmarks, and a strong privacy focus—all under an MIT license.
Who it is for
- iOS developers interested in on-device machine learning
- privacy-conscious users who want local image generation
- AI hobbyists with compatible iPhones (15 Pro/16 series or newer)
- developers learning MLX Swift for mobile inference
Use cases
- Generating images offline without sending data to a cloud server
- Prototyping and testing on-device diffusion models for personal projects
- Educational exploration of memory tuning and model quantization on mobile
- Creating custom images for personal use, such as wallpapers or concept art
Strengths
- Fully on-device inference—no cloud, no accounts, images never leave the phone
- Measured and validated memory usage (peaks ~4.25 GiB for SDXL-Turbo) on 8 GB devices
- Supports two models (SDXL-Turbo and SD-Turbo) with adjustable steps and cancellation
- Open source (MIT) with clear installation instructions via Xcode and free Apple ID
Considerations
- Requires an iPhone with at least 8 GB RAM (iPhone 15 Pro, 16 series, or newer); older models are blocked
- Installation is manual from source; no App Store build, and free Apple ID certificates expire every 7 days
- First launch requires downloading several GB of model weights over Wi-Fi, and the app must stay active to avoid interruption
README quick start
Alis Studio Mobile
On-device, native image generation for iPhone — a SwiftUI app that runs text-to-image diffusion models entirely on the device with MLX Swift. No cloud, no accounts; your images never leave the phone.
The mobile sibling of Alis Studio (the Mac desktop app), sharing its design language — clay accent, cream surfaces, the pine mark, light + dark.
| Generate | Gallery |
|---|---|
Real images generated on an iPhone 16 Pro Max — SDXL-Turbo, 512², 4 steps.
Requirements
[!IMPORTANT] An 8 GB-class iPhone is required. The app runs a multi-gigabyte diffusion model fully in memory; on devices with less than 8 GB of RAM it shows an "unsupported device" screen and will not generate (the OS would otherwise kill it mid-generation). This is enforced at runtime.
| Minimum | |
|---|---|
| Device RAM | 8 GB — iPhone 15 Pro, 15 Pro Max, 16, 16 Plus, 16 Pro, 16 Pro Max, or newer. Not supported: iPhone 15 / 15 Plus (6 GB), SE, and all older models. |
| iOS | 17.0 or later |
| Free storage | ~8 GB for SDXL-Turbo (≈7 GB weights + ≈0.3 GB fp16-fix VAE), or ~2.5 GB for SD-Turbo. Downloaded once, then cached. |
| Network | Required on first run to download model weights from Hugging Face. Keep the screen on — the download is several GB and the app is killed if it's suspended mid-download. |
| Hardware | A physical iPhone. MLX has no Metal backend in the iOS Simulator, so generation only runs on a real device. |
Models & on-device memory (validated on iPhone 16 Pro Max, 8 GB)
| Model | Config | Peak resident | Latency (512²) | Quality |
|---|---|---|---|---|
| SDXL-Turbo | 4-bit UNet · sdxl-vae-fp16-fix · 2–4 steps | ~4.25 GiB | ~10–13 s/img | highest (photorealistic) |
| SD-Turbo | 4-bit UNet · fp16 VAE · 4 steps | ~3.4 GiB | ~6 s/img | good, fastest |
Both stay well under the 8 GB device's jetsam limit at 512². The memory tuning came from on-device measurement: the VAE decode activation is the memory peak, so SDXL loads the fp16-stable VAE (the stock SDXL VAE NaNs in fp16); the UNet is 4-bit; and the MLX cache is cleared between generations to stop it accumulating.
Features
- Prompt → 512² image, fully on-device (MLX Metal)
- Model picker
Description
On-device image generation for iPhone (MLX Swift) — the mobile sibling of Alis Studio
Related repositories
Similar projects matched by category, topics, and programming language.
uzairansaruzi
Featured
hermex
Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.
simonw
Featured
speech-analyzer-cli
A macOS command-line tool that uses Apple's on-device speech APIs to transcribe prerecorded audio into plain text, JSON, JSONL, SRT, or WebVTT.