Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

Qwen Image 2.0 Pro API

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name qwen-image-2.0-pro
Type Image generation (text-to-image)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

The professional tier of Alibaba Qwen Image 2.0: stronger in-image text rendering, finer photorealistic detail and better adherence, up to 2048x2048, billed per image.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Pro-grade Chinese text rendering

Plaques, couplets and labels render accurately — the Pro tier speciality, verified in real runs.

promptprompt_extend
Finer photorealism

Skin texture, metal reflections and material detail clearly beat the base tier — built for portraits and product shots.

prompt
Commercial posters

Stronger semantic adherence gets multi-element compositions (subject + text + mood) right in one pass.

promptsize
Flexible sizing

Free width*height between 512x512 and 2048x2048 total pixels, with five recommended presets.

size

Request parameters

model string required

Fixed value qwen-image-2.0-pro.

example qwen-image-2.0-pro
input object required

Business parameters. Put Qwen Image 2.0 Pro-specific configuration here.

prompt string required

Text description of the image. Chinese and English both work well; spell out any text you want rendered.

size enum optional

Output size in width*height. Total pixels between 512x512 and 2048x2048.

default 2048*2048 enum: 2688*15362368*17282048*20481728*23681536*2688
negative_prompt string optional

Describe what to avoid in the generated image.

default ""
prompt_extend boolean optional

Automatically optimize the prompt for better results. Adds slight latency.

default true
watermark boolean optional

Add an AI-generated watermark to the output.

default false
seed integer optional

Random seed for reproducible generation, 0 to 2147483647.

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback
when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Cloud-top teahouse (plaque text)

16:9 scene with calligraphy plaque — text + atmosphere.

Request body
{
  "model": "qwen-image-2.0-pro",
  "input": {
    "prompt": "一座悬浮在云海之上的中式空中茶馆,飞檐翘角挂满暖黄灯笼,木质牌匾上写着「云顶茶居」四个楷书大字,一条木栈道从云中延伸至茶馆,晨光穿透云层,电影感构图,戏剧性定向打光,暖金与云白统一色调,超高细节,商业级质感,细微胶片颗粒",
    "size": "2688*1536",
    "prompt_extend": false
  }
}
Silversmith portrait (photoreal)

3:4 portrait — skin texture and shallow depth of field.

Request body
{
  "model": "qwen-image-2.0-pro",
  "input": {
    "prompt": "A photorealistic portrait of an elderly Miao silversmith, weathered hands chiseling a silver butterfly, silver shavings and tools on the workbench, soft window light on his focused profile, lifelike skin texture and silver reflections, shallow depth of field, cinematic composition, ultra-detailed",
    "size": "1728*2368",
    "prompt_extend": false
  }
}
Agarwood perfume (product shot)

9:16 commercial shot with a bilingual label.

Request body
{
  "model": "qwen-image-2.0-pro",
  "input": {
    "prompt": "A neo-Chinese perfume product shot: an amber glass bottle standing in shallow water, its label clearly printed with 沉香 and AGARWOOD, ink-wash mountains behind, ripple reflections, morning mist, cinematic composition, amber and ink color grade, ultra-detailed, premium commercial finish",
    "size": "1536*2688",
    "prompt_extend": false
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated image from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Pro vs base qwen-image-2.0 — which one?

Pro is stronger at text rendering, photorealism and adherence, at a higher unit price. Iterate on the base tier, deliver on Pro — the parameters are identical, so switching is free.

Does it support 4K?

No. Pro tops out at 2048x2048 total pixels. For native 4K, use wan2.7-image/text-to-image or seedream-5.0-lite.

When should I turn off prompt_extend?

prompt_extend (on by default) rewrites and enriches your prompt. Always set it to false when the image must contain exact text (plaques, couplets, labels) so your wording is preserved; keep it on for pure scene prompts.

How do I get the generated image?

The request returns a taskId immediately. When the task reaches a terminal state, download the image from output[].url. In production, pass callback.url at the top level of the request body instead of polling.

Next steps