Boogu · 10B · Boogu Image
Run Boogu Image Turbo on iPad and Mac: Posters With Chinese Text
Boogu Image Turbo is for realistic photographs and for pictures with English or Chinese text in them, such as posters and product shots. The Boogu research team built it to make an image in four steps, and it runs on a 16 GB iPad or Mac.
- Parameters
- 10B
- License
- Apache License 2.0
- Released
- June 2026
- Download
- 12.86 GB
Boogu 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.

Boogu 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.
Boogu Image Turbo Specs
Download
- Download Size
- 12.86 GB
Model
- Maker
- Boogu
- Based On
- Boogu Image
- Parameters
- 10B
- 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
- 4 (fixed)
- Upscaler
- Off · 2x · 4x
- Negative Prompt
- No
- Rewrite Prompt
- No
- Output Sizes
- S · 512 pxEvery device
- M · 768 pxEvery device
- L · 1024 pxEvery device
- XL · 1536 px24 GB
Boogu Image Turbo Examples and Prompts
57 of 57 prompts
Accordion player beneath a railway archBoogu Image Turbo
Ballet shoes beside stage dustBoogu Image Turbo
Ballet shoes drying by backstage pipesBoogu Image Turbo
Brass telescope in a dusty studyBoogu Image Turbo
Clockmaker polishing a moonphase dialBoogu Image Turbo
Crystal bakery display in miniatureBoogu Image Turbo
Crystal chess set on velvetBoogu Image Turbo
Empty boxing gym before sunriseBoogu Image Turbo
Fencer practicing alone in an empty hallBoogu Image Turbo
Floating workshop of wooden planetsBoogu Image Turbo
Glass terrarium orbiting a ceramic planetBoogu Image Turbo
Ibex crossing a snowy ridgeBoogu Image Turbo
Laundry courtyard on market morningBoogu Image Turbo
Manta ray gliding over coralBoogu Image Turbo
Mechanical seed vault opening undergroundBoogu Image Turbo
Mountain goat on slate ledgeBoogu Image Turbo
Mountain road through dense fogBoogu Image Turbo
Pangolin curling beneath lantern leavesBoogu Image Turbo
Picnic basket beside a parked canoeBoogu Image Turbo
Porcelain automaton brewing tiny teaBoogu Image Turbo
Porcelain chess set in orbitBoogu Image Turbo
Radio repairman testing glowing tubesBoogu Image Turbo
Red fox resting in beach grassBoogu Image Turbo
Seaside ticket booth in summerBoogu Image Turbo
Snow leopard pausing on granite ridgeBoogu Image Turbo
Snow leopard watching mountain mistBoogu Image Turbo
Steam laundry drying linen indoorsBoogu Image Turbo
Switchboard operator sorting tangled linesBoogu Image Turbo
Tea room prepared for afternoon serviceBoogu Image Turbo
A potter paints the final glazeBoogu Image Turbo
A tortoise crosses the greenhouse tilesBoogu Image Turbo
Arctic fox leaping over meltwaterBoogu Image Turbo
Clockmaker balancing a brass escapementBoogu Image Turbo
Clockmaker inspecting a balance wheelBoogu Image Turbo
Clockwork garden above a data lakeBoogu Image Turbo
Crystal archive opening over desert ruinsBoogu Image Turbo
Floodgate operator at midnightBoogu Image Turbo
Fogbound pier after the tideBoogu Image Turbo
Glass fruit balances on velvet blocksBoogu Image Turbo
Glass terrarium tower with floating roomsBoogu Image Turbo
Gouache heron beside winter reedsBoogu Image Turbo
Linen sheets twist in the windBoogu Image Turbo
Market cooks share the morning steamBoogu Image Turbo
Market rooftops painted in gouacheBoogu Image Turbo
Modular lunar greenhouse during eclipseBoogu Image Turbo
Modular moon habitat under assemblyBoogu Image Turbo
Night ferry crossing the harbor fogBoogu Image Turbo
Night ferry crossing under heavy rainBoogu Image Turbo
Potter trimming clay at sunriseBoogu Image Turbo
Pretzel rafters cross a chocolate canyonBoogu Image Turbo
Rainwater tunnel beneath the cityBoogu Image Turbo
Red fox pausing beside frostBoogu Image Turbo
Roadside observatory in summer duskBoogu Image Turbo
Tea bowl study on raw paperBoogu Image Turbo
The last ferry leaves at duskBoogu Image Turbo
Traveling botanist cataloging pressed flowersBoogu Image Turbo
Vertical archive of floating memory cubesBoogu Image Turbo
What Boogu Image Turbo Is Good At
Photography is its strength: natural light, coherent composition, and a subject and background that hold together even in busy real-world scenes. It also handles stylized work, from miniature 3D scenes to anime portraits.
Pick It For
- Large-model quality without the wait: four steps, fixed
- Posters and signs with readable English or Chinese text
- A 4x latent upscaler, up to 4096 pixels on a 16 GB iPad and 6144 on a 24 GB Mac
- Apache 2.0, which asks nothing of your images
Know Before You Download
- Not available on iPhone; needs a 16 GB iPad or Mac
- No negative prompt and no prompt rewriting
- Less reliable with real brands, landmarks, and famous people; long or dense text can pick up typos, and hands can go wrong in crowded or unusual poses
- A 12.86 GB download with its own text encoder
Boogu Image Turbo in Private Diffusion vs. Draw Things vs. ComfyUI
Boogu 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 Boogu 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 Boogu Image Turbo. It is a single 12.86 GB download with nothing to configure.
- Pick Boogu Image Turbo in Studio, describe the picture, and generate. It runs on your own device, so there is no queue.
Questions About Boogu Image Turbo
No. Boogu 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.
12.86 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 a descriptive paragraph with the subject first, spelling out the details you care about. Keep any on-image text short and large, frame faces large, and avoid crowded or unusual poses where hands are visible. There is no negative prompt and no rewrite step, so be explicit about the medium and the framing.
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, Boogu 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 Boogu 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 Boogu 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.