画像生成

This page covers Midjourney image workflows together with OpenAI, Gemini, and Alibaba image generation and editing endpoints.

Apifox のカバー範囲

• Midjourney: intro, Imagine, Action, Blend, Modal, Describe, Shorten, FaceSwap, upload, task query, seed, edit, video, and an OpenAI-compatible imagine endpoint
• OpenAI images: gpt-image-1.5, dall-e-3, edits, web editor, variations, xAI
• Google Gemini: Nano-banana2, Imagen 4, image generation, image editing, native Gemini image generation
• Other vendors: Doubao, Alibaba Qwen, Minimax, flux, flux-kontext-pro, stable-diffusion, ideogram, recraftv3

Midjourney

POST 1. Text to Image (Imagine)

POST /mj/submit/imagine

Executes an Imagine action and submits an image generation task. After submission, obtain the task ID and query its status with the fetch endpoint.

Body Parameters

{
  "mode": "RELAX",
  "prompt": "Cat"
}

Request Parameters

Name	In	Type	Required	Description
body	body	any	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

POST 2. Button Action

POST /mj/submit/action

This endpoint clicks the buttons below an image. The customId can be obtained from the task fetch endpoint.

Body Parameters

{
  "customId": "MJ::JOB::upsample::1::0bc41848-dc7f-42f9-893c-9c33b00ebdf3",
  "taskId": "1734937261701345"
}

Request Parameters

Name	In	Type	Required	Description
body	body	any	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

POST 3. Image Blend

POST /mj/submit/blend

Executes a Blend action and submits an image blending task.

Body Parameters

{
  "mode": "RELAX",
  "base64Array": [
    "data:image/png;base64,xxx1",
    "data:image/png;base64,xxx2"
  ],
  "dimensions": "SQUARE"
}

Request Parameters

Name	In	Type	Required	Description
body	body	any	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

POST 4. Modal Action

POST /mj/submit/modal

When another task returns code 21, call the modal endpoint and provide a new prompt to refine the result.

Body Parameters

{
  "maskBase64": "data:image/png;base64,xxx1",
  "prompt": "Cat",
  "taskId": "1712204995849324"
}

Request Parameters

Name	In	Type	Required	Description
body	body	any	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

POST 6. Shorten Prompt

POST /mj/submit/shorten

Executes a shorten action to identify which words are most important to image generation and which are less important.

Body Parameters

{
  "mode": "RELAX",
  "prompt": "Cat"
}

Request Parameters

Name	In	Type	Required	Description
body	body	any	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

POST 8. Upload

POST /mj/submit/upload-discord-images

Uploads images to Discord for use in image prompting and related workflows

Body Parameters

{
  "mode": "RELAX",
  "base64Array": [
    "data:image/png;base64,xxx1"
  ]
}

Request Parameters

Name	In	Type	Required	Description
body	body	any	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

GET 9. Fetch Task

GET /mj/task/{id}/fetch

Fetches task information by task ID. You can poll this endpoint or rely on callback notifications.

Request Parameters

Name	In	Type	Required	Description
id	path	string	Yes	Task ID
Content-Type	header	string	No	none
Accept	header	string	No	none
Authorization	header	string	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

POST 10. Batch Fetch Tasks

POST /mj/task/list-by-condition

Fetches task information by a list of task IDs. You can poll this endpoint or rely on callback notifications.

Body Parameters

{
  "ids": [
    "1749688282741136"
  ]
}

Request Parameters

Name	In	Type	Required	Description
Content-Type	header	string	No	none
Accept	header	string	No	none
Authorization	header	string	No	none
body	body	any	No	none

Response Example

200 Response

[
  null
]

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
201	Created	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

GET 11. Fetch Image Seed

GET /mj/task/{id}/image-seed

Fetches the image seed value for reuse with the --seed parameter

Request Parameters

Name	In	Type	Required	Description
id	path	string	Yes	Task ID
Content-Type	header	string	No	none
Accept	header	string	No	none
Authorization	header	string	No	none

Response Example

200 Response

null

Responses

Status	Meaning	Description	Model
200	OK	none	Inline
401	Unauthorized	none	Inline
403	Forbidden	none	Inline
404	Not Found	none	Inline

Response Schema

モデル API / 画像生成

POST Flux with Reference Image / OpenAI-Compatible

POST /images/generations

Only some models support reference images For example: seededit flux-kontext

Body Parameters

{
    "prompt": "https://replicate.delivery/pbxt/N55l5TWGh8mSlNzW8usReoaNhGbFwvLeZR3TX1NL4pd2Wtfv/replicate-prediction-f2d25rg6gnrma0cq257vdw2n4c.png Make this a 90s cartoon",
    "n": 1,
    "model": "flux-kontext-pro",
    "size": "1024x1024"
}

Request Parameters

Name	In	Type	Required	Description
Authorization	header	string	No	none
body	body	object	No	none
» prompt	body	string	Yes	Text description of the desired image. Maximum length: 1000 characters.
» n	body	integer	No	Number of images to generate. Must be between 1 and 10.
» size	body	string	No	Size of the generated image. Must be one of 256x256, 512x512, or 1024x1024.

Response Example

200 Response

{
  "created": 0,
  "data": [
    {
      "url": "string"
    }
  ]
}

Responses

Status	Meaning	Description	Model
200	OK	none	Inline

Response Schema

Status 200

Name	Type	Required	Constraints	Chinese Name	Description
» created	integer	true	none		none
» data	[object]	true	none		none
»» url	string	true	none		none

モデル API / 画像生成 / OpenAI 形式

POST Create Image Variation

POST /images/variations

Creates variations of the supplied image.

Official documentation：https://platform.openai.com/docs/api-reference/images/createVariation

Body Parameters

image: ""
n: "2"
size: 1024x1024

Request Parameters

Name	In	Type	Required	Description
Authorization	header	string	No	none
body	body	object	No	none
» image	body	string(binary)	Yes	Base image used to create the variation. Must be a valid square PNG smaller than 4 MB.
» n	body	string	No	1024x1024
» size	body	string	No	Generated image size. For dall-e-2, allowed values are 256x256, 512x512, or 1024x1024. For dall-e-3, allowed values are 1024x1024, 1792x1024, or 1024x1792.

Response Example

200 Response

{
  "created": 0,
  "data": [
    {
      "url": "string"
    }
  ]
}

Responses

Status	Meaning	Description	Model
200	OK	none	Inline

Response Schema

Status 200

Name	Type	Required	Constraints	Chinese Name	Description
» created	integer	true	none		none
» data	[object]	true	none		none
»» url	string	true	none		none

モデル API / 画像生成 / Google Gemini / ネイティブ Gemini 形式

POST Generate Image

POST /v1beta/models/{model}:generateContent/

Body Parameters

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "draw a cat"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "TEXT",
      "IMAGE"
    ],
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "4K"
    }
  }
}

Request Parameters

Name	In	Type	Required	Description
model	path	string	Yes	Model Name
key	query	string	Yes	none
Content-Type	header	string	Yes	none
body	body	object	No	none
» contents	body	[object]	Yes	none
»» parts	body	[object]	No	none
»»» text	body	string	No	none

Response Example

200 Response

{
  "id": "string",
  "object": "string",
  "created": 0,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "string",
        "content": "string"
      },
      "finish_reason": "string"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

Responses

Status	Meaning	Description	Model
200	OK	none	Inline

Response Schema

Status 200

Name	Type	Required	Constraints	Chinese Name	Description
» id	string	true	none		none
» object	string	true	none		none
» created	integer	true	none		none
» choices	[object]	true	none		none
»» index	integer	false	none		none
»» message	object	false	none		none
»»» role	string	true	none		none
»»» content	string	true	none		none
»» finish_reason	string	false	none		none
» usage	object	true	none		none
»» prompt_tokens	integer	true	none		none
»» completion_tokens	integer	true	none		none
»» total_tokens	integer	true	none		none

モデル API / 画像生成 / Alibaba Qwen

POST General Image Edit 2.5

POST /images/edits

Official documentation：https://help.aliyun.com/zh/model-studio/wan2-5-image-edit-api-reference?spm=a2c4g.11186623.help-menu-2400256.d_2_2_7.36fa95e52PaUYv&scm=20140722.H_2982258._.OR_help-T_cn~zh-V_1

Body Parameters

image: ""
prompt: 转个圈
model: wan2.5-i2i-preview

Request Parameters

Name	In	Type	Required	Description
Authorization	header	string	No	none
body	body	object	No	none
» image	body	string(binary)	Yes	none
» prompt	body	string	Yes	Text description of the image you want to generate.
» model	body	string	No	Model used for image generation.

Response Example

200 Response

{
  "created": 0,
  "data": [
    {
      "url": "string"
    }
  ]
}

Responses

Status	Meaning	Description	Model
200	OK	none	Inline

Response Schema

Status 200

Name	Type	Required	Constraints	Chinese Name	Description
» created	integer	true	none		none
» data	[object]	true	none		none
»» url	string	true	none		none