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
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.

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.
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
- S · 512 pxEvery device
- M · 768 pxEvery device
- L · 1024 px12 GB on iPhone or iPad
- XL · 1536 px24 GB
Z-Image-Turbo Examples and Prompts
57 of 57 prompts
Autonomous ferry leaving dawn harborZ-Image-Turbo
Canal cargo barge at dawnZ-Image-Turbo
Cantilevered library above forest ravineZ-Image-Turbo
Compact pottery studio after glazingZ-Image-Turbo
Copper watch gears in alignmentZ-Image-Turbo
Courtyard library with brick archesZ-Image-Turbo
Desert archive tower with shaded stairsZ-Image-Turbo
Dew on a watch springZ-Image-Turbo
Fern spores beneath curled frondZ-Image-Turbo
Ferry deck approaching island harborZ-Image-Turbo
Frost crystals on blue mussel shellZ-Image-Turbo
Glacier stream under volcanic cliffsZ-Image-Turbo
Glass laundry room after rainfallZ-Image-Turbo
Limestone river terraces at dawnZ-Image-Turbo
Mountain ferry dock in clear weatherZ-Image-Turbo
Narrow laundry room with skylightZ-Image-Turbo
Rainy canal landing at twilightZ-Image-Turbo
Rescue hovercraft on frozen reedsZ-Image-Turbo
Salt crystals on citrus peelZ-Image-Turbo
Salt grains on dried kelpZ-Image-Turbo
Snow groomer climbing moonlit pisteZ-Image-Turbo
Snow groomer on ridge trailZ-Image-Turbo
Soap bubble on rough slateZ-Image-Turbo
Solar trike crossing salt flatsZ-Image-Turbo
Stone footpath through terraced teaZ-Image-Turbo
Tide pool under basalt ledgesZ-Image-Turbo
Vintage snow groomer beside alpine shedsZ-Image-Turbo
Watch gears beside a ruby bearingZ-Image-Turbo
Wind-carved dunes around dry shrubsZ-Image-Turbo
Basalt tide pools after rainZ-Image-Turbo
Basalt tide pools under cloud breaksZ-Image-Turbo
Breakfast nook with tiled alcoveZ-Image-Turbo
Canyon footbridge near hot springsZ-Image-Turbo
Ceramic studio with drying shelvesZ-Image-Turbo
Cliffside observatory above basalt terracesZ-Image-Turbo
Concrete bathhouse beside winter reedsZ-Image-Turbo
Concrete library atrium with roof gardenZ-Image-Turbo
Concrete library with stepped roof gardensZ-Image-Turbo
Desert rest stop after sunriseZ-Image-Turbo
Dew on a fern spiralZ-Image-Turbo
Electric ferry crossing a quiet inletZ-Image-Turbo
Frost rings on fallen reed stemsZ-Image-Turbo
Frosted circuit traces under magnificationZ-Image-Turbo
Heavy snowplow clearing a mountain passZ-Image-Turbo
Mountain tea house above terracesZ-Image-Turbo
Rooftop hammam above blue courtyardsZ-Image-Turbo
Salt crystals on a dried figZ-Image-Turbo
Salt crystals on dark slateZ-Image-Turbo
Salt crystals on dried lemon peelZ-Image-Turbo
Salt flats camp at sunriseZ-Image-Turbo
Sandstone canyon after sudden rainZ-Image-Turbo
Skyborne pirate ship over misted hillsZ-Image-Turbo
Solar ferry crossing a calm harborZ-Image-Turbo
Sunken conversation pit with tile hearthZ-Image-Turbo
Sunken listening room with walnut wallsZ-Image-Turbo
Sunken lounge with tiled hearthZ-Image-Turbo
Timber chapel in a rain gardenZ-Image-Turbo
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.
| Feature | Private Diffusion | Draw Things | ComfyUI |
|---|---|---|---|
| Image Quality | Near-lossless: every model is quantization aware distilled (QAD) against the full-size original | Shrinks models after training (post-training palettization) | Runs the weights you load |
| Speed | GPU and Neural Engine together, plus Neural Accelerators on M5, M6, A19 Pro, and A20 Pro | GPU; the Neural Engine only for i8x models on M3 and M4 | PyTorch MPS, the slowest inference framework on Apple platforms |
| Privacy | Collects no data | Privacy label lists Purchases, Identifiers, and User Content | Sends telemetry to PostHog and Datadog, checked by default on first launch |
| Security | App Sandbox and Hardened Runtime | App Sandbox (Mac App Store) | Unsandboxed Electron |
| The App | Native Swift with Liquid Glass, macOS 26.4 or later | Mac Catalyst | Electron |
How to Run Z-Image-Turbo on iPhone, iPad, and Mac
- Pre-order Private Diffusion on the App Store; it downloads itself on release day.
- Open Downloads in the app and tap Z-Image-Turbo. It is a single 6.40 GB download with nothing to configure.
- Pick Z-Image-Turbo in Studio, describe the picture, and generate. It runs on your own device, so there is no queue.
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.
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.