Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Z-Image-Turbo

by Tongyi-MAI

Efficient open-weights image generation model built on a single-stream diffusion transformer.

AI image generators Open source

GitHub repoWebsite

2. Commercial use: huggingface.co

“license: apache-2.0”

Apache-2.0 allows commercial use of the model.

huggingface.co

License checked Oct 27, 2026 against 1 official page. Tap a verdict to see its source. How we checked Report an error

Z-Image-Turbo: fast open model for realistic pictures

Z-Image-Turbo is a free image model from Alibaba's Tongyi team that makes pictures from a text description. It is tuned for realistic photos and can write English and Chinese text inside the picture. It runs on your own computer with a gaming-class graphics card, and the Apache-2.0 license allows paid use.

Where you can use it

Realistic photos for a site or app

Make photo-like pictures from a description, such as a cozy cafe interior for a landing page, on your own machine without paying per image.

Posters and banners with lettering

Ask for a picture that includes a short headline or sign text in English or Chinese, for example a poster or a shop sign.

Images on a gaming graphics card

Run it at home or in the office on a graphics card with 16 GB of memory; with memory saving turned on, smaller cards can work too, only slower.

Fast image step in your own service

An app that makes images for its users calls the model on its own server; only 8 model steps per picture keep each request short.

Blog and article cover images Idea

Make a matching cover picture for each new post from its title and a short style line, then pick the best of a few seeds.

Product mockups for a pitch Idea

Show a product idea in a realistic setting, such as a bottle on a kitchen counter, before any real photo shoot.

As reported by Tongyi-MAI: Matches or exceeds leading competitors with only 8 model steps; Ranked 8th overall on the Artificial Analysis text-to-image leaderboard; Runs with as little as 4GB of graphics memory through the community engine stable-diffusion.cpp.

Z-Image-Turbo popularity

35 / 100
Gid Score, same scale as developer tools
12,167
GitHub stars
Z-Image-Turbo: GitHub starsTongyi-MAI/Z-Image 12,167

How the Gid Score is calculated

How to start

Tell your AI assistant

“In a Python venv on our NVIDIA GPU machine, install diffusers with ZImagePipeline, load Tongyi-MAI/Z-Image-Turbo in bfloat16, and write a script that saves a 1024x1024 PNG per prompt with num_inference_steps=9 and guidance_scale=0.0.”

Or install it yourself.

pip install git+https://github.com/huggingface/diffusers
Show codeStep 1 or Step 2

Load the Turbo model in bfloat16 and move it to the graphics card.

pipe = ZImagePipeline.from_pretrained(
    "Tongyi-MAI/Z-Image-Turbo",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=False,
)
pipe.to("cuda")

Mistakes to avoid

Using guidance_scale 3.5 to 7 and 30 to 50 steps as with other image models
num_inference_steps=9 and guidance_scale=0.0 for Turbo

The Turbo model is distilled for 8 steps without guidance.

Loading with StableDiffusionPipeline or an old diffusers release
Use ZImagePipeline from a diffusers version that includes Z-Image support

Z-Image support was added to diffusers recently, so older releases do not have ZImagePipeline.

Calling pipe.to("cuda") on a card with less than 16 GB and getting out-of-memory errors
Call pipe.enable_model_cpu_offload() instead of pipe.to("cuda")

Offloading keeps only the active part of the model on the card.

Using Turbo as the base for LoRA or style training
Train on the base Z-Image model, which the makers mark as easy to fine-tune

The model table lists fine-tunability for Turbo as N/A.

License

Apache-2.0 license. License, so paid use is allowed. If you pass the model files on, include the license and keep the notices; the model card sets no separate rules for the pictures you make.

Commercial use
Yes

“license: apache-2.0” huggingface.co

Credit
Not stated
Inside your app or game
Can ship inside your app

“license: apache-2.0” huggingface.co

Pass the files on to your users
With conditions

Passing on the weights or code needs a copy of the Apache-2.0 license, change notices and kept attribution notices.

“You must give any other recipients of the Work or Derivative Works a copy of this License” LICENSE on GitHub

AI training
Not stated
Bots and bulk downloads
Not stated

AllowedWith conditionsNot allowedNot stated or not checked yet

Is Z-Image-Turbo free for commercial use? The full answer Not legal advice. Check the license page before you ship.

For your agent

License rules tell your agent what it may do with Z-Image-Turbo. Paste them into your prompt or AGENTS.md.

License rules
- Z-Image-Turbo (AI image generators). Efficient open-weights image generation model built on a single-stream diffusion transformer. Price: free; commercial use OK.
  Connect: download from https://huggingface.co/Tongyi-MAI/Z-Image-Turbo (no API).
  Rule: Keep the Apache-2.0 license and notices when you redistribute the weights.
  Rule: The model card does not add a separate output license; check the repo before shipping.
  License: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md (checked 2026-10-27; details: https://agentgid.com/assets/z-image-turbo/)
Can an agent use it by itself?
No.
API, key or account
Not needed. Everything runs on your side.
MCP server
None found
This card for machines

Alternatives

Z-Image-Turbo This page

Free Commercial OK Download

Stable Diffusion XL base 1.0

Pick Stable Diffusion XL for an older, widely supported open model with a separate refiner and many community add-ons.

Free With conditions Download

FLUX.1 [dev]

Pick FLUX.1 [dev] only for non-commercial work; commercial use of its weights needs a paid license.

Free Non-commercial Download

OpenAI GPT Image

Pick OpenAI GPT Image when you want a paid hosted service with image editing and no own graphics card.

Paid Commercial OK API, npm, PyPI

InvokeAI

Free open-source, self-hosted AI image generation app with a layer-based canvas and node-based workflows.

Free Commercial OK Download

HunyuanDiT

Tencent's diffusion-transformer text-to-image model with fine-grained Chinese and English prompt understanding.

Free With conditions Download

All ai image generators

Questions

Can I use the pictures in a paid product?

The model is under Apache-2.0, which allows commercial use, and the model card adds no separate rules for outputs.

Can I try it before installing?

Yes, the makers link an online demo on Hugging Face Spaces and on ModelScope.

Why is guidance set to 0?

The Turbo model is distilled to work without guidance; the official example says guidance should be 0 for it.

Can it edit an existing picture?

Not this model. Editing is the job of a separate Z-Image-Edit model, which the model table lists as not yet released.