MiniMax Image 01 Subject Reference
Usage-based pricing
ae_minimax_image_01_subject_reference
Create new images from a text prompt while keeping the person or character in a reference image visually consistent.
Usage-based pricing
Pricing
The charge per call is (max(12 × successfully generated images, 0)) AE credits. All applicable conditions are combined to calculate the total.
Charges are based on the actual number of successfully generated images, not merely the requested count. The same per-image rate applies across aspect ratios and the prompt-optimization option.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.prompt | string | Yes | Text prompt for image generation (max 1500 characters) | — |
request_body.image_url | string | Yes | URL of the subject reference image to use for consistent character appearance | — |
request_body.num_images | integer | No | Number of images to generate (1-9) | 1 |
request_body.aspect_ratio | enum (1:1 | 16:9 | 4:3 | 3:2 | 2:3 | 3:4 | 9:16 | 21:9) | No | Aspect ratio of the generated image | 1:1 |
request_body.prompt_optimizer | boolean | No | Whether to enable automatic prompt optimization | false |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeySubmit first, then query with the returned task_id until the task completes.
Request coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_minimax_image_01_subject_reference' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"aspect_ratio": "9:16",
"image_url": "https://agentearth.ai/fileserver/file/ad10a9a7-815f-4435-b5b3-9b160ee77016.jpg",
"num_images": 3,
"prompt": "参考图中这位女生的本人照片。必须完全保留她的长相:圆润柔和的鹅蛋脸、脸颊带一点肉感、大眼睛、深棕色瞳孔、自然的深色平眉、小巧的鼻子、饱满的嘴唇带温柔浅笑;长直黑发加空气刘海。肤色极度白皙透亮、白得发光。她现在笔直站立,正面朝向镜头,从头到脚全身入镜,双脚赤足站在浅米色影棚地面上,自然微笑看着镜头。她穿着一件青绿到白色的渐变汉服:宽大飘逸的半透明纱袖,袖子和裙摆上绣粉色桃花,腰间系青绿色宽腰带并垂一根金色流苏,裙摆外层为菱形网格薄纱。版型贴身收腰,勾勒纤细腰肢与凹凸有致的女性曲线,方领抹胸设计露出白皙的锁骨和肩颈,身姿优雅妩媚、很有女人味。高级时尚人像摄影,柔和影棚光,8K高清,无文字无水印。",
"prompt_optimizer": false
}
}
}'Response exampleresponse.json
{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "695c5761-f60a-4e07-aa47-f67c03aa7e65"
}This example shows part of the response. Copied content is valid JSON.
Guides using this tool
See how this tool fits into real workflows
Reference-Based E-Commerce Main Images with AI AgentsLock a product's shape with a reference image and let an AI agent swap backgrounds and scenes in bulk — produce main images from one prompt, no reshoot, with the product staying consistent across every variation.Character-Consistent Image Generation with AI AgentsLock a character's look with a reference image and have an AI agent keep the same person consistent across scenes and poses — batch out IP, picture-book, comic and mascot image sets from one instruction.
Product & Person Replacement in Images with AI AgentsUse an AI agent to swap the product or person in a scene photo for the subject in a reference image while keeping the background intact — reuse one scene across many SKUs, skip reshoots, and batch the output.



