Z-Image Turbo z-image-turbo

Efficient text-to-image diffusion model that produces quality images in as few as 8 steps.

From the live catalog

Image

$0.02 / megapixel

region ATL quantization bf16 Hugging Face Tongyi-MAI/Z-Image-Turbo

Inputs

Input	Accepts
`text`

Parameters

Streams with stream: true.

Parameter	Type	Values	Default
`size`	any
`aspect_ratio`	string	1:1, 9:7, 7:9, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 9:21	`1:1`
`resolution`	string	512, 768, 1K, 1.5K, 2K
`n`	integer	1–10	`1`
`response_format`	string	url, b64_json	`url`
`seed`	integer
`steps`	integer	1–50	`8`
`output_format`	string	png, jpeg, webp	`png`
`output_compression`	integer	0–100
`background`	string	auto, opaque	`auto`

Endpoints

POST/v1/images/generations Create Image POST/v1/images Generate Image (OpenRouter) POST/v1/images/edits Edit Image

A request

curl https://api.vultrinference.com/v1/images/generations \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-image-turbo",
    "prompt": "Studio photograph of a red ceramic teapot beside a blue cup on a wooden table.",
    "n": 1,
    "size": "1024x1024",
    "response_format": "b64_json"
  }'

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/images/generations",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    json={
        "model": "z-image-turbo",
        "prompt": "Studio photograph of a red ceramic teapot beside a blue cup on a wooden table.",
        "n": 1,
        "size": "1024x1024",
        "response_format": "b64_json",
    },
)
print(response.json())

const response = await fetch("https://api.vultrinference.com/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "z-image-turbo",
    "prompt": "Studio photograph of a red ceramic teapot beside a blue cup on a wooden table.",
    "n": 1,
    "size": "1024x1024",
    "response_format": "b64_json"
  }),
});
console.log(await response.json());