Text to Image

qwen-image-3.0

Image generation and editing with standard instruction following and text rendering.

POST /v1/images/generationsAsync generation

Quick start

Submit a request with this public model ID. The API immediately returns a normalized job; poll GET /v1/jobs/{jobId} while its status is queued or running.

curl -X POST "https://api.artany.ai/v1/images/generations" \
  -H "Authorization: Bearer $ARTANY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: unique-request-id" \
  -d '{"model":"qwen-image-3.0","prompt":"A cafe poster with the title Autumn Limited, warm tones, refined layout","resolution":"1K","size":"16:9","n":1,"prompt_extend":false}'

Request

Headers

Header	Required	Description
Authorization	Yes	Bearer token for an Artany API key.
Content-Type	Yes	Must be application/json.
Idempotency-Key	Recommended	8–128 characters. Reusing it with an identical request prevents duplicate jobs and charges.

Body

{
  "model": "qwen-image-3.0",
  "prompt": "A cafe poster with the title Autumn Limited, warm tones, refined layout",
  "resolution": "1K",
  "size": "16:9",
  "n": 1,
  "prompt_extend": false
}

Request Parameters

Only fields in this model’s public request contract are shown. Defaults are applied before validation and quoting.

Note:Text-to-image and image-to-image generation. Use the Pro variant for dense text, layouts, menus, storyboards, and other content-heavy compositions.

modelstringrequireddefault: "qwen-image-3.0"

Stable public model ID for this request.

promptstringrequired

Text description for image generation, up to approximately 4.5k tokens.

Length: 1–18000

image_urlsarray<string>

Reference image URL array for image-to-image generation or editing.

Items: 1–3

Use 1–3 public http(s) URLs or complete Base64 Data URIs.
Supported formats: JPG, JPEG, PNG, BMP, TIFF, WEBP, and GIF.

Note:Each reference image must be at most 10MB. Suggested dimensions are 384–2048 px.

resolutionstringdefault: "1K"

Output resolution tier.

Allowed: 1K, 2K, 1k, 2k

Field description

1K: Default output tier.
2K: Higher-resolution output tier. The Pro model has a separate 2K price.

1K2K1k2k

Lowercase 1k and 2k are accepted.

Note:When using custom pixel dimensions, output above 2.25 megapixels is billed as the 2K tier.

sizestringdefault: "1:1"

Output aspect ratio.

Allowed: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3

Field description

1:1: Square.
4:3 / 3:4: Landscape or portrait.
16:9 / 9:16: Widescreen or vertical.
3:2 / 2:3: Photo aspect ratios.

1:14:33:416:99:163:22:3

nintegerdefault: 1

Number of images to generate in this request.

Range: 1–6

Note:Use a JSON integer from 1 to 6. Higher values are limited to 6 by the upstream API.

negative_promptstring

Visual content, styles, or defects to avoid in the generated image.

Length: 0–18000

prompt_extendbooleandefault: false

Whether to enable intelligent prompt rewriting.

It is disabled by default for predictable results.

prompt_extend_modestring

Prompt-rewrite mode used when prompt_extend is true.

Allowed: direct, agent

Field description

direct: Works for text-to-image and image-to-image.
agent: More aggressive rewriting for text-to-image only.

directagent

Note:Do not use agent when image_urls is supplied.

Response and task status

A successful asynchronous submission returns HTTP 202 with a supplier-neutral job.

{
  "id": "job_…",
  "object": "generation.job",
  "model": "qwen-image-3.0",
  "status": "queued",
  "progress": 0,
  "output": null,
  "error": null,
  "billing": {
    "estimated_credits": "…",
    "frozen_credits": "…",
    "charged_credits": "0",
    "state": "frozen",
    "price_version": "2026-07-18.picverse-parity"
  },
  "created_at": "2026-07-21T00:00:00.000Z",
  "completed_at": null
}

queued / running: continue polling.
succeeded: retrieve media URLs from output; billing has settled.
failed / canceled: inspect error; frozen Credits are released.