Alibaba

Qwen Image 2.0

qwen-image-2.0

Alibaba's unified architecture model for image generation and editing, skilled at long-form Chinese text rendering, supporting instructions up to 1000 tokens and 2K output

qwen-image-2.0 qwen-image-2.0-pro

Try qwen-image-2.0

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

qwen-image-2.0 per image

Unit Price	$0.0422

Positioning Overview

Qwen-Image-2.0 is an image generation model released by Alibaba, available on HiAPI.ai through a text-to-image API. It is designed for developers who need high-resolution image output and Chinese text rendering. It supports positive and negative prompts of up to 800 characters, can output 2K-level images with a choice of landscape or portrait orientation, and also offers intelligent prompt rewriting and seed reproducibility. It is suitable for batch image generation workflows in poster, presentation, and long-form visual content production that require stable Chinese text presentation and composition control.

Key Highlights

Chinese text rendering is the main differentiator — it can stably render multiple fonts and longer Chinese copy, making it suitable for generating visual materials that include headlines and body text.
2K-level resolution and multiple aspect ratios — output sizes cover five tiers from 1536×2688 to 2688×1536, accommodating both portrait posters and landscape banners.
Prompt rewriting and random seed — intelligent prompt rewriting is enabled by default to complete descriptions, and combined with the seed parameter it can reproduce the same result as closely as possible.

Capability Description

Positive and negative prompt control: positive prompts can be up to 800 characters and negative prompts up to 500 characters, allowing you to exclude unwanted elements while describing the image content and reducing repeated trial and error.

Five output size tiers: specify the output ratio as WIDTH*HEIGHT, defaulting to 2048*2048, with four additional portrait and landscape sizes so that a single call can directly match the placement slot.

Intelligent prompt rewriting: prompt_extend is enabled by default, with the model completing shorter descriptions; when strict adherence to the original description is required, it can be explicitly disabled.

Reproducible generation results: fix the random seed via seed to reproduce the same image as closely as possible under identical parameters, facilitating version comparison and batch debugging.

Optional watermark switch: the watermark parameter controls whether the Qwen-Image watermark is added, so the final image can carry or omit the mark depending on the publishing channel.

Applicable Scenarios

Marketing teams producing Chinese posters in batches — input prompts containing the main headline and selling points to produce finished images in the specified portrait size, ready for use on campaign pages and social media placements.
Content teams creating long-form graphics and comic panels — use longer prompts to describe multi-panel compositions and dialogue text, obtaining matching illustrations for long-form WeChat articles or serialized content.
Draft exploration in design workflows — start with short prompts and intelligent rewriting for batch image generation, use fixed seeds to filter directions, and then use the results as reference drafts for formal design.

Limitations and Model Selection Advice

The maximum output is 2K level; if higher resolution or fine local editing is required, other models supporting higher resolution and editing capabilities should be evaluated. Its capability boundary is centered on text-to-image and text rendering, and it is not suitable for knowledge-driven tasks such as retrieval augmentation or multi-step reasoning. The API accepts only text prompts and has no image input channel, so it cannot modify based on existing images. When images must strictly follow the original description, it is recommended to disable prompt rewriting and fix the seed to control variables.

What's new

View changelog →

New model qwen-image-2.0-pro is now live: supports text-to-image, standard price $0.107/image Oct 31, 2026

Frequently asked questions

View all FAQs →

What is Qwen Image 2.0 best for?

A cost-efficient Chinese-friendly model with negative prompts, prompt extension, optional seed, and five 2K pixel-size presets.
Does Qwen Image 2.0 accept reference images?

No. This route is text-to-image only.
Which output settings are supported?

The page exposes 2688×1536, 2368×1728, 2048×2048, 1728×2368, 1536×2688 and ; use the Playground contract for the final available set.
How is Qwen Image 2.0 billed?

Billing is per successful generated image. Resolution or quality differences, when present, are reflected by the live page price.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: qwen-image-2.0

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for qwen-image-2.0 and route default — see the parameter table below.

seedintegerOptionalmin 0max 2147483647

Random seed, used to reproduce the same result as closely as possible under the same parameters. Pass an integer; if not provided, it is randomly generated by the server.

sizestringOptionalDefault: "2048*2048"

Output image size, given as a string in width*height format. Default is 2048*2048.

Options:2688*15362368*17282048*20481728*23681536*2688

promptstringRequiredmaxLength 800

Positive prompt, describing the content, style, and composition of the image you want to generate.

watermarkbooleanOptionalDefault: false

Whether to add a Qwen-Image watermark to the output image. Default is false.

prompt_extendbooleanOptionalDefault: true

Whether to enable intelligent prompt rewriting, which automatically expands and optimizes the input prompt. Default is true.

negative_promptstringOptionalDefault: ""maxLength 500

Negative prompt, describing content you do not want to appear in the generated result. Default is an empty string.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-image-2.0",
  "input": {
    "size": "2048*2048",
    "prompt": "…",
    "watermark": false,
    "prompt_extend": true,
    "negative_prompt": ""
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen-image-2.0",
    input: {
      "size": "2048*2048",
      "prompt": "…",
      "watermark": false,
      "prompt_extend": true,
      "negative_prompt": ""
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "qwen-image-2.0",
        "input": {
          "size": "2048*2048",
          "prompt": "…",
          "watermark": False,
          "prompt_extend": True,
          "negative_prompt": ""
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}