Z-Image Pro

Z-Image Pro comes from Alibaba's Z-Image family and works differently from most image models in the catalog. There are only two inputs, the prompt and a seed, so the description carries the whole picture: framing, light, lens, mood. Give it one dense paragraph instead of a pile of tags and it pays you back with a coherent scene.

What you can make

• Concept art of characters and locations for a game or a music video.
• A repeatable series built on one fixed seed.
• Photoreal scenes from a single detailed description.
• Clean cover backgrounds where you add the title later in an editor.

Settings that matter

• Inputs: prompt and seed, nothing else. No reference images.
• Prompt style: one English paragraph of roughly 90 to 170 words that covers subject, setting, light, lens and mood.
• Seed: a fixed number reproduces a result; 0, null or no seed means random.
• Testing changes: keep the seed and edit one phrase at a time to see what each word does.
• Output: one image per request.
• Not exposed yet: custom width and height and automatic prompt rewriting, both offered by the vendor.

Starter prompt

An old clockmaker works late in a narrow workshop full of brass gears and half-built clocks. A green desk lamp lights his hands and loupe, the rest of the room fades into warm shadow. 85mm lens, shallow depth of field, dust in the air, quiet focused mood.

Write your own scene in the same order (who, where, light, lens, mood) and extend it toward 120 words for the richest result.

Questions

How much does Z-Image Pro cost?

$0.05 per image. Failed images cost nothing, and your prepaid balance never expires.

Can I choose the output size or shape?

Not in Kadraris yet; only prompt and seed are accepted. If you need a specific ratio, Z-Image Turbo offers five.

Can I upload a photo to edit?

No, Z-Image Pro is text-to-image only.

Z-Image Pro in your code

curl https://kadraris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $KADRARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "z-image-pro",
  "input": {
    "prompt": "Packshot of a white linen sneaker on a concrete block, hard midday sun, crisp shadow, 85mm"
  }
}'

import os, time, requests

API = "https://kadraris.com/v1"
H = {"Authorization": f"Bearer {os.environ['KADRARIS_API_KEY']}"}

task = requests.post(f"{API}/generate", headers=H, json={
    "model": "z-image-pro",
    "input": {
        "prompt": "Packshot of a white linen sneaker on a concrete block, hard midday sun, crisp shadow, 85mm"
    }
}).json()
while task["status"] in ("queued", "running"):
    time.sleep(3)
    task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()

print(task["status"], task["cost"], [o["url"] for o in task["output"]])

const API = "https://kadraris.com/v1";
const headers = { Authorization: `Bearer ${process.env.KADRARIS_API_KEY}`, "Content-Type": "application/json" };

let task = await (await fetch(`${API}/generate`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "z-image-pro",
    "input": {
      "prompt": "Packshot of a white linen sneaker on a concrete block, hard midday sun, crisp shadow, 85mm"
    }
  }),
})).json();

while (task.status === "queued" || task.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));

Input fields

Fetch this list as JSON with GET /v1/models/z-image-pro.