InferX Catalog | Z-Image-Turbo

Z-Image-Turbo

Z-Image-Turbo is a 6-billion parameter text-to-image model released by Alibaba's Tongyi Lab (the team behind Qwen) in late 2025. It was specifically engineered to challenge the dominance of larger models like FLUX.1 by prioritizing extreme inference speed and bilingual text rendering without sacrificing photorealism.

Tongyi-MAI image text2img

Log in to deploy

Metadata

Provider

Tongyi-MAI

Modality

image

API type

text2img

Source

huggingface / Tongyi-MAI/Z-Image-Turbo

Created

2026-04-07 00:43:50 UTC

Updated

2026-04-07 00:43:50 UTC

Catalog version

1

Visibility

Published

Specifications

Parameters

6.00B

MoE

No

Max model length

—

Image

vllm/vllm-omni:v0.14.0

Default Deploy Config

GPU count

1

vRAM

45000 MB

Summary

1xGPU 45000 MB

Recommended Use Cases

—

Model Spec

{
    "image": "vllm/vllm-omni:v0.14.0",
    "commands": [
        "vllm",
        "serve",
        "Tongyi-MAI/Z-Image-Turbo",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.99",
        "--omni"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "vRam": 45000
        }
    },
    "envs": [],
    "sample_query": {
        "body": {
            "model": "Tongyi-MAI/Z-Image-Turbo",
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {
                            "text": "A glass of water",
                            "type": "text"
                        }
                    ]
                }
            ],
            "extra_body": {
                "width": 320,
                "height": 480,
                "num_inference_steps": 12
            }
        },
        "path": "v1/chat/completions",
        "prompt": "A glass of water",
        "apiType": "text2img",
        "dataUrl": "",
        "prompts": [],
        "loadingTimeout": 90
    }
}