Wan 27 Image Pro Edit
Edit 1–4 reference images with a text prompt, including multi-image edits that refer to images by order. Choose the output size and create up to 4 edited images.
Pricing
The charge per call is (max(90 × Generated output images (images), 0)) AE credits. All applicable conditions are combined to calculate the total.
Billing is based on the number of output images actually generated; input reference images are excluded from the billable count. The same per-image rate applies across supported output sizes and prompt expansion and safety checker settings.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.seed | integer | unknown | No | Random seed for reproducibility (0-2147483647). | — |
request_body.prompt | string | Yes | Text prompt describing the desired image edit. Supports Chinese and English. | — |
request_body.image_size | object | string | No | Output image size. Uses fal image size presets or explicit dimensions and is converted to DashScope size format. | square_hd |
request_body.image_size.width | integer | No | The width of the generated image. | 512 |
request_body.image_size.height | integer | No | The height of the generated image. | 512 |
request_body.image_urls | array | Yes | Reference images for editing (1-4 images required). Order matters: reference them as image 1, image 2, image 3, image 4 in the prompt. | — |
request_body.num_images | integer | No | Number of images to generate (1-4). | 1 |
request_body.negative_prompt | string | unknown | No | Content to avoid in the generated image. Max 500 characters. | "" |
request_body.enable_safety_checker | boolean | No | Enable content moderation for input and output. | true |
request_body.enable_prompt_expansion | boolean | No | Enable DashScope prompt expansion. Supported only for image edit mode. | true |
Invocation example
Copy the request and explore its response example.
/agent-api/v1/tool/executeX-Api-KeySubmit first, then query with the returned task_id until the task completes.
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_wan_27_image_pro_edit' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"image_urls": [
"https://agentearth.ai/fileserver/file/8856e1d8-7b41-4bd2-9262-a52b9039d07d.jpg",
"https://agentearth.ai/fileserver/file/c0d357bb-6178-4d71-b230-7440e81b95c8.jpg"
],
"num_images": 1,
"output_format": "jpeg",
"prompt": "图1是已经完成换装的照片,只需修正左下方那只米白色立体兔子头口袋的朝向:现在它是歪斜的。图2是这件睡衣的原始参考图。\n\n保持图1的一切不变(构图、俯拍视角、左手抓衣领、贝壳纽扣门襟、黑色皮质沙发、深色木地板、光线、3:4 竖版、珊瑚绒质感、粉灰小碎花),只改兔子。\n\n把左下方的兔子头修正端正:整体不旋转不歪斜不倒置;两只长耳朵朝画面正上方竖起、对称;两只黑色圆眼睛水平并排对称;X 形小嘴居中位于双眼正下方;圆脸立体绒毛质感;自然贴合衣料表面。\n\n不要新增物体,不要文字,不要改动手型和纽扣。"
}
}
}'{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "90a568cc-d89c-41e8-bdf4-6866dfa69dc5"
}Guides using this tool
See how this tool fits into real workflows





