Skip to content

Tongyi Lab (Alibaba) · 6B · Z-Image

Run Z-Image-Turbo on iPhone, iPad, and Mac: Photoreal Detail

Z-Image-Turbo makes pictures that look like photographs, with fine detail, true-to-life textures, and legible text in English and Chinese, and it follows prompts closely. Alibaba's Tongyi Lab made it, and it runs on a 12 GB iPhone, an 8 GB iPad, or any Apple Silicon Mac.

Parameters
6B
License
Apache License 2.0
Released
November 2025
Download
6.40 GB

View on Hugging Face

Z-Image-Turbo runs in Private Diffusion, a local AI image generator for iPhone, iPad, and Mac. Every model in the app is trained with quantization aware distillation (QAD) to stay near-lossless at a fraction of its full size. Download it once inside the app.

Pre-order on the App Store
Z-Image-Turbo in Private Diffusion Studio on iPhone, with a finished image

Z-Image-Turbo Requirements: Will It Run on My Device?

  • iPhone

    Needs a 12 GB iPhone

    iPhone 17 Pro and 17 Pro Max, iPhone 18 Pro and 18 Pro Max, iPhone Air, and iPhone Duo.

  • iPad

    Runs on every supported iPad

    Any iPad with an M-series chip.

    Takes its time on an 8 GB iPad.

  • Mac

    Runs on any Apple Silicon Mac

    M1 or later, from 8 GB of memory up.

Check your device

Z-Image-Turbo Specs

Download

Download Size
6.40 GB3.97 GB when the shared text encoder is already installed
Text Encoder Shared With
Flux.2 Klein 4B and Juggernaut Z Fast

Model

Maker
Tongyi Lab (Alibaba)
Based On
Z-Image
Parameters
6B
Quantization
Trained INT4 (QAD)
License
Apache License 2.0Covers the model itself, not the pictures you make with it. Nothing in it asks anything of your images.

Generation

Steps
9 (fixed)
Upscaler
Off · 2x · 4x
Negative Prompt
Yes
Rewrite Prompt
Yes
Output Sizes
  1. S · 512 pxEvery device
  2. M · 768 pxEvery device
  3. L · 1024 px12 GB on iPhone or iPad
  4. XL · 1536 px24 GB

Z-Image-Turbo Examples and Prompts

57 of 57 prompts

Browse Travel prompts

What Z-Image-Turbo Is Good At

Its detail shows most in materials and surfaces, which makes it a good choice for large prints: the 4x upscaler takes a picture to a 4096-pixel long edge on a 16 GB iPad and 6144 on a 24 GB Mac. That upscaler needs 10 GB of memory, and 13 GB once the result passes 4096 pixels.

You will also see it written Z Image Turbo; whichever spelling you searched for, it is the same model. Juggernaut Z Fast, RunDiffusion's photorealistic fine-tune of Z-Image, shares its text encoder, so installing one makes the other a smaller download.

Pick It For

  • Fine detail in textures, foliage, and architecture
  • Signs, labels, and short text in English or Chinese
  • Negative prompts and on-device prompt rewriting, both on

Know Before You Download

  • Needs a 12 GB iPhone: a 17 Pro or 18 Pro model, the Air, or the Duo
  • Runs on an 8 GB iPad, but takes its time there
  • Large output needs 12 GB on iPhone or iPad; extra-large needs 24 GB

Z-Image-Turbo in Private Diffusion vs. Draw Things vs. ComfyUI

Z-Image-Turbo is the same model wherever you run it. The apps differ in how they shrink it to fit, which chips do the work, and who sees your prompts.

Private Diffusion compared with Draw Things and ComfyUI
FeaturePrivate DiffusionDraw ThingsComfyUI
Image QualityNear-lossless: every model is quantization aware distilled (QAD) against the full-size originalShrinks models after training (post-training palettization)Runs the weights you load
SpeedGPU and Neural Engine together, plus Neural Accelerators on M5, M6, A19 Pro, and A20 ProGPU; the Neural Engine only for i8x models on M3 and M4PyTorch MPS, the slowest inference framework on Apple platforms
PrivacyCollects no dataPrivacy label lists Purchases, Identifiers, and User ContentSends telemetry to PostHog and Datadog, checked by default on first launch
SecurityApp Sandbox and Hardened RuntimeApp Sandbox (Mac App Store)Unsandboxed Electron
The AppNative Swift with Liquid Glass, macOS 26.4 or laterMac CatalystElectron

How to Run Z-Image-Turbo on iPhone, iPad, and Mac

  1. Pre-order Private Diffusion on the App Store; it downloads itself on release day.
  2. Open Downloads in the app and tap Z-Image-Turbo. It is a single 6.40 GB download with nothing to configure.
  3. Pick Z-Image-Turbo in Studio, describe the picture, and generate. It runs on your own device, so there is no queue.
Pre-order on the App Store

Questions About Z-Image-Turbo

  • Yes, on an iPhone with 12 GB of memory: the iPhone 17 Pro and 17 Pro Max, the iPhone 18 Pro and 18 Pro Max, the iPhone Air, and the iPhone Duo. Other supported iPhones have 8 GB and cannot hold Z-Image-Turbo.

  • 6.40 GB, or 3.97 GB when the shared text encoder is already installed. It downloads once inside the app from Private Diffusion's own server and picks up where it left off after an interruption. On iPhone and iPad the download keeps going with the app closed; on a Mac, quitting the app stops it, and it resumes at the next launch. You can delete it to reclaim the space and fetch it again later.

  • Write it like a caption, in full sentences, and be specific about materials and surfaces, because that is where its detail shows. Rewrite Prompt is on for this model and does the expanding for you when the prompt is short.

    Build a prompt for Z-Image-Turbo part by part

  • Apache License 2.0: Covers the model itself, not the pictures you make with it. Nothing in it asks anything of your images.

  • Yes. After the one-time download, Z-Image-Turbo works without a connection. It turns your prompt into a finished image on the device, and you never sign in.

  • It is faster, the pictures hold up better, and nothing leaves your device. Private Diffusion ships Z-Image-Turbo quantization aware distilled (QAD), trained against the full-size original, so it stays near-lossless at a fraction of the size. It runs on Apple's own frameworks: the GPU through MLX, including the Neural Accelerators in M5, M6, A19 Pro, and A20 Pro chips, and the Neural Engine through Core ML. ComfyUI runs models through PyTorch's MPS backend, the slowest inference framework on Apple platforms. ComfyUI's desktop app sends usage telemetry to PostHog and error reports to Datadog, with telemetry checked by default on first launch; Private Diffusion collects no data. And Private Diffusion is a sandboxed native Swift app with the hardened runtime on, where ComfyUI's desktop app is an Electron app that is not sandboxed.

  • Private Diffusion ships Z-Image-Turbo quantization aware distilled (QAD), trained against the full-size original, so it stays near-lossless; Draw Things shrinks its models after training. It is faster, using the GPU and the Neural Engine together, plus the Neural Accelerators in M5, M6, A19 Pro, and A20 Pro chips. Private Diffusion collects no data, while Draw Things' App Store privacy label lists Purchases, Identifiers, and User Content. And it is a native Swift app built to Apple's Human Interface Guidelines, with Liquid Glass on macOS 26.4 or later, not a Mac Catalyst port.