Skip to content

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

View on Hugging Face

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.

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

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 iPhone
  • iPad

    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.

Check your device

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
  1. S · 512 pxEvery device
  2. M · 768 pxEvery device
  3. L · 1024 pxEvery device
  4. XL · 1536 px24 GB

ERNIE Image Turbo Examples and Prompts

59 of 59 prompts

Browse Nature prompts

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.

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 ERNIE Image Turbo on a 16 GB iPad or Mac

  1. Pre-order Private Diffusion on the App Store; it downloads itself on release day.
  2. Open Downloads in the app and tap ERNIE Image Turbo. It is a single 9.66 GB download with nothing to configure.
  3. Pick ERNIE 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 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.

    Build a prompt for ERNIE 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, 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.