Z-Image Image Local Cloud Image input

Z-Image Turbo

Z-Image Turbo is Tongyi-MAI's official distilled model, delivering photorealistic results with ultra-fast inference in just 8 steps.

$0.005

per image in the cloud

$0

on your own GPU

Run it free Use it in Claude or the API

Z-Image Turbo, AI Image Generator

Z-Image Turbo is the official distilled model from Tongyi-MAI, featuring 6B parameters.

Highlights

Ultra Fast: Sub-second inference, only 8 steps
Photorealistic: Bilingual text rendering and precise instruction following
Foundation Model: Base for many community fine-tunes

Recommended Settings

Steps: 8 | CFG: 1.0 | Scheduler: Euler

Use it

Three ways to run Z-Image Turbo

Download Imference Desktop and open it.
In Local models, pick Z-Image Turbo. It downloads once.
Write a prompt and press Generate. Free, on your GPU.

Get the app

Make an image with Z-Image Turbo ("z-image-turbo"): a lighthouse on a cliff at dusk, cinematic light

curl https://imference.com/generate \
  -H "Authorization: Bearer $IMFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "z-image-turbo",
       "format_code": "square",
       "prompt": "a lighthouse on a cliff at dusk, cinematic light"}'

Claude needs the MCP server. API details in the reference.

Specs