Skip to content

Qwen Image 3 Edit

Integrate

Model id alibaba/qwen-image-3/edit
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/alibaba/qwen-image-3/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Change the sign above the door to read \"Open Daily 8-20\" in the same lettering style and color, keep everything else unchanged.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_msc9ak2dbu4cu59zvf0c2ftb/0-RBrxxuL8Z-3AAI916Qh9o_hi2fj8yl.png"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.075 75 API credits Run it on this page

Get API key
Alibaba Image Editing #editing#typography#multi-reference

Edit with one to three reference images, strong at changing or adding text in a picture.

Examples

Input
Output · ~105 s
Change the sign above the door to read "Open Daily 8-20" in the same lettering style and color, keep everything else ...

PromptChange the sign above the door to read "Open Daily 8-20" in the same lettering style and color, keep everything else unchanged.

$0.075 · 75 API credits

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required 127 / 5000

Text describing the edit to make, in Chinese or English, limited to 5000 characters.

•required image_urls
Drop a file, or

Supply 1–3 editing references in JPEG, JPG, PNG (without alpha), or WEBP format, with a maximum of 10MB per file and dimensions of 384–2048px on each axis. Refer to them in the prompt as 'image 1', 'image 2', and 'image 3', according to their supplied order.

image_size

Output image dimensions, constrained by a total pixel count from 512 × 512 to 2048 × 2048. Omitting the size lets the model choose a resolution automatically.

num_images default 1

Image count requested for generation.

Advanced negative_prompt · output_format · seed · enable_prompt_expansion
0 / 500

Content to exclude from the resulting image, limited to 500 characters.

output_format default png

File format for the resulting image.

Random seed enabling reproducible results, ranging from 0 to 2147483647.

POST /run/alibaba/qwen-image-3/edit?wait=20 quote → $0.075
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/alibaba/qwen-image-3/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Change the sign above the door to read \"Open Daily 8-20\" in the same lettering style and color, keep everything else unchanged.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_msc9ak2dbu4cu59zvf0c2ftb/0-RBrxxuL8Z-3AAI916Qh9o_hi2fj8yl.png"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Qwen Image 3 Edit

The editing mode of Qwen Image 3 takes one to three reference images (384 to 2048 px per side) and an instruction that can refer to them as image 1, image 2 and image 3. It is particularly good at replacing or adding lettering. Leave the size empty to let the model choose, or set a preset or custom size up to 2K; up to six results per request.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptrequired
Typestring
≤ 5,000 characters
Text describing the edit to make, in Chinese or English, limited to 5000 characters.
negative_promptoptional
Typestring | null
Default
≤ 500 characters
Content to exclude from the resulting image, limited to 500 characters.
image_sizeoptional
Typeobject
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
Output image dimensions, constrained by a total pixel count from 512 × 512 to 2048 × 2048. Omitting the size lets the model choose a resolution automatically.
enable_prompt_expansionoptional
Typeboolean
Defaulttrue
Controls automatic prompt rewriting by an LLM to improve results.
seedoptional
Typeinteger | null
Random seed enabling reproducible results, ranging from 0 to 2147483647.
num_imagesoptional num_outputs
Typeinteger
Default1
1 – 6
Image count requested for generation.
output_formatoptional
Typeenum
Defaultpng
jpegpngwebp
File format for the resulting image.
image_urlsrequired images
Typeurl[] · image
Supply 1–3 editing references in JPEG, JPG, PNG (without alpha), or WEBP format, with a maximum of 10MB per file and dimensions of 384–2048px on each axis. Refer to them in the prompt as 'image 1', 'image 2', and 'image 3', according to their supplied order.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "alibaba/qwen-image-3/edit",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 75,
    "usd": "0.075",
    "charged": 75,
    "refunded": 0
  },
  "input": {
    "prompt": "Change the text on the sneaker's side to read \"RUN\" in bold letters",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ]
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    ],
    "seed": 42
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
images
array of object {url, content_type, file_name, file_size}Images produced by generation.
seed
integerSeed value applied during generation.

More models: Image Editing

For AI agents: this page as Markdown is at https://doitong.com/developers/models/alibaba/qwen-image-3/edit.md. All models and guides: https://doitong.com/developers/llms.txt