Baidu · 8B · ERNIE Image
Run ERNIE Image Turbo on iPad and Mac: Infographics and Comics
ERNIE Image Turbo is for images with words and structure in them: posters, comics, infographics, and multi-panel layouts, plus long prompts that name many objects and how they relate. Baidu's ERNIE-Image team built it, and it runs on a 16 GB iPad or Mac.
- Parameters
- 8B
- License
- Apache License 2.0
- Released
- April 2026
- Download
- 9.66 GB
ERNIE 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.

ERNIE Image Turbo Requirements: Will It Run on My Device?
iPhone
Not available on iPhone
Not offered on iPhone at any memory size.
Try Flux.2 Klein 4B on iPhoneiPad
Needs a 16 GB iPad
iPad Pro (M4 or M5) with 1 TB or 2 TB of storage.
Mac
Needs a Mac with 16 GB or more
Any Apple Silicon Mac configured with 16 GB or more.
ERNIE Image Turbo Specs
Download
- Download Size
- 9.66 GB
Model
- Maker
- Baidu
- Based On
- ERNIE Image
- Parameters
- 8B
- 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
- 8 (fixed)
- Upscaler
- Off · 1.5x · 2x
- Negative Prompt
- No
- Rewrite Prompt
- Yes
- Output Sizes
- S · 512 pxEvery device
- M · 768 pxEvery device
- L · 1024 pxEvery device
- XL · 1536 px24 GB
ERNIE Image Turbo Examples and Prompts
59 of 59 prompts
3d coral library under glassERNIE Image Turbo
Arctic fox listening under snowERNIE Image Turbo
Bridge cables disappearing into fogERNIE Image Turbo
Ceramic submarine in a teacupERNIE Image Turbo
Glass chess knight crossing velvetERNIE Image Turbo
Glass orchard orbiting a crystal moonERNIE Image Turbo
Isometric glasshouse mushroom habitatERNIE Image Turbo
Modular robot garden caretakerERNIE Image Turbo
Monochrome chess table after closingERNIE Image Turbo
Monochrome florist at closing timeERNIE Image Turbo
Monochrome stairwell with one umbrellaERNIE Image Turbo
Mountain observatory during comet watchERNIE Image Turbo
Noir staircase with open umbrellaERNIE Image Turbo
Octopus exploring a tide poolERNIE Image Turbo
Old observatory brass telescopeERNIE Image Turbo
Otter balancing shells at low tideERNIE Image Turbo
Paper lantern city on shelvesERNIE Image Turbo
Rain-dark chess table by the windowERNIE Image Turbo
Rain-soaked stairwell after midnightERNIE Image Turbo
Red fox crossing frozen reedsERNIE Image Turbo
Red panda exploring a bamboo bridgeERNIE Image Turbo
Retro diner pie displayERNIE Image Turbo
Seamstress fitting a velvet stage coatERNIE Image Turbo
Seaside motel pool before checkoutERNIE Image Turbo
Snow macaque beside hot springERNIE Image Turbo
Tailor pins a silent mannequinERNIE Image Turbo
Tree pangolin curling around bambooERNIE Image Turbo
Vintage camper beside a desert telescopeERNIE Image Turbo
Vintage kitchen radio by morning toastERNIE Image Turbo
Vintage orchard ladder at harvestERNIE Image Turbo
Arctic fox crossing blue iceERNIE Image Turbo
Ballerina balancing beside Arctic waterERNIE Image Turbo
Ceramicist shaping a bowl at noonERNIE Image Turbo
Ceramicists preparing a shared kilnERNIE Image Turbo
Chess table after the tournamentERNIE Image Turbo
Copper kettles beside a painted stoveERNIE Image Turbo
Crystal server farm above cloudsERNIE Image Turbo
Desert observatory during a dust stormERNIE Image Turbo
Dusty apothecary jars in afternoon lightERNIE Image Turbo
Floating archive above a neon canalERNIE Image Turbo
Fogbound ferry beneath winter searchlightsERNIE Image Turbo
Glass observatory above a reefERNIE Image Turbo
Glass terrarium orbiting a stone towerERNIE Image Turbo
Gouache study of a copper kettleERNIE Image Turbo
Hands shaping clay in silenceERNIE Image Turbo
Ink wash cranes over winter reedsERNIE Image Turbo
Last ferry leaving the flooded terminalERNIE Image Turbo
Monochrome violin in a quiet roomERNIE Image Turbo
Neon tidepool inside a towerERNIE Image Turbo
Old sewing table by daylightERNIE Image Turbo
Pastel boats drying on river mudERNIE Image Turbo
Potter shaping clay at dawnERNIE Image Turbo
Rainy station platform at midnightERNIE Image Turbo
Red fox crossing a frozen streamERNIE Image Turbo
Red fox crossing snowy reedsERNIE Image Turbo
Seaside diner before the stormERNIE Image Turbo
Tailor measuring cloth in window lightERNIE Image Turbo
Tiny glass tram on a shelfERNIE Image Turbo
Toy repair robot in tiny workshopERNIE Image Turbo
What ERNIE Image Turbo Is Good At
Lettering is where it stands out. Baidu reports that it handles dense, long, and layout-sensitive text, which is what a poster, an infographic, or a mock-up of an app screen needs. Rewrite Prompt is on for this model and expands a short description on the device before generation runs.
Pick It For
- Posters, infographics, and other images with a lot of readable text
- Long, specific prompts with several objects and the relationships between them
- Comics, storyboards, and multi-panel layouts
Know Before You Download
- Not available on iPhone; needs a 16 GB iPad or Mac
- No negative prompt, so say what you want rather than what to avoid
- A 9.66 GB download with its own text encoder
ERNIE Image Turbo in Private Diffusion vs. Draw Things vs. ComfyUI
ERNIE 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 ERNIE Image Turbo on a 16 GB iPad or Mac
- Pre-order Private Diffusion on the App Store; it downloads itself on release day.
- Open Downloads in the app and tap ERNIE Image Turbo. It is a single 9.66 GB download with nothing to configure.
- Pick ERNIE Image Turbo in Studio, describe the picture, and generate. It runs on your own device, so there is no queue.
Questions About ERNIE Image Turbo
No. ERNIE Image Turbo is not offered on iPhone at any memory size. It runs on an iPad Pro with 1 TB or 2 TB of storage, or on any Apple Silicon Mac with 16 GB or more.
9.66 GB. 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 the whole brief in one long paragraph: the camera angle, every element and where it sits, the light direction, the colors, and the style. It is strong on dense text and multi-object layouts, so put any words that should appear in the image in quotes, spelled exactly. Rewrite Prompt is on for this model and expands what you write before generation runs.
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, ERNIE 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 ERNIE 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 ERNIE 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.