ToAPIs
home

快速结论

  • midjourney supports Text-to-Video, Image-to-Video, R2V, and Video Edit in one workflow.
  • Use this model guide page to validate parameters with minimal request/response examples.
  • Stabilize prompts here first, then move to production API integration.

关键参数

  • model | string | 必填 | midjourney | - | Model identifier. Use the fixed value `midjourney`.
  • prompt | string | 必填 | - | - | Main instruction describing the subject, action, scene, and style.
  • aspect_ratio | string | 可选 | 16:9 | 16:9 | 9:16 | 1:1 | Video aspect ratio. Defaults to `16:9`; supports `16:9 | 9:16 | 1:1`.
  • duration | integer | 可选 | 6 | 5 | 10 | 15 | 20 | Output duration in seconds. Defaults to `6`; supports `5 | 10 | 15 | 20`.
  • resolution | string | 可选 | 720P | 720P | Output resolution. Defaults to `720P`; supports `720P`.

常见错误

  • 400 invalid_request_error: 触发=Request payload misses required fields or has invalid field types.; 修复=Validate model, mode, and input schema before request.; 重试=Retry only after fixing payload; avoid blind retries.
  • 401 authentication_error: 触发=Missing Authorization header or invalid API key.; 修复=Verify Bearer token format and API key scope.; 重试=Retry after auth fix; rotate key if repeated failures continue.
  • 429 rate_limit_exceeded: 触发=Request rate, concurrency, or current quota hits upstream rate limiting.; 修复=Apply exponential backoff first, then review request rate, concurrency, and quota usage.; 重试=Use exponential backoff (e.g., 1s/2s/4s) with jitter; if it persists, reduce submission pressure.
  • 500 internal_error: 触发=Transient upstream error or internal processing failure.; 修复=Capture request id and trigger retry workflow.; 重试=Retry 2-3 times with short delays; escalate if persistent.

midjourney

midjourney is provided by Unknown with Video / Image capabilities. Current pricing reference: 9 積分 /request. This page helps you understand positioning, parameters, and production-ready use cases before integration.

模型類型：
價格： 9 積分 /request
1

描述你的圖片

參考圖

描述你想生成的圖片。44 / 1200

進階選項

範例參數
2

你的生成結果

圖片結果會顯示在這裡

登入後可直接提交生成任務。

查看 API 文件取得 API Key

生成需要一些時間，請稍等您可以離開此頁面，[ 任務日誌 ] 可直接檢查生成的內容

請求預覽

{
  "model": "midjourney",
  "prompt": "使用 midjourney 生成一张高质感产品广告图，主体清晰，光线自然，适合社媒投放。",
  "speed": "relax",
  "version": "v8.2",
  "index": 1,
  "direction": "right",
  "batch_size": 1,
  "_midjourneyAction": "imagine"
}

透明計價

midjourney pricing

Image usage is billed according to the current request and resolution rules. Final billing follows the current account quote.

儲值積分
9 積分 /request

為什麼選擇 ToAPIs

Why call midjourney through ToAPIs?

Keep image generation, API keys, billing, and usage management in one workflow.

Unified multi-mode testing

Switch across Text-to-Video, Image-to-Video, R2V, and Video Edit in one place.

Parameter-first validation

Iterate quickly on prompts, durations, and references before production rollout.

Production-ready handoff

Minimal request/response structure helps you move stable configs into API workflows.

Connect in three steps

Create a key, send an image request, and review the generated result.

  1. 1

    Step 1

    Fill prompt and key parameters.

  2. 2

    Step 2

    Run, inspect output structure, then iterate.

  3. 3

    Step 3

    Move stable settings into production API.

When to use midjourney

Use case 1

When you need fast iteration across multiple generation modes.

Use case 2

When you need to validate parameters and error handling before integration.

常見問題

midjourney FAQ

When should I use midjourney?

Use it to validate video concepts quickly, compare mode behavior, and converge prompts before API rollout.

How do I choose Text-to-Video vs Image-to-Video?

Use Text-to-Video when you only have instructions; use Image-to-Video when you already have key frames or composition.

What is the difference between R2V and Video Edit?

R2V focuses on reference-guided generation, while Video Edit focuses on modifying existing video assets.

图像视频模型报错：invalid apitype: -1

这类错误通常说明接口走错了。图像和视频模型一般不走 chat 接口，而是按对应文档发起 HTTP 任务请求，并通过任务状态接口轮询结果。排查时建议先看用户的实际请求代码、请求地址和请求体。

用户进行生成图片/视频的任务时出现任务失败，但是扣款

先让用户提供任务日志或截图，重点看是否出现了输入或输出 token 统计。如果有这类 token 记录，大概率是用户把图片/视频模型走成了 chat 接口；这不是正确用法。图片和视频模型通常是异步任务接口，需要通过 HTTP 请求先提交任务，再拿到任务 ID 轮询状态，详细以对应文档为准。

midjourney API

Start building with midjourney

Test an image request here, then continue in the dashboard or API documentation.

Start for freeView API Docs

Try midjourney with one ToAPIs key.

Use one account and API surface for image generation workflows.

Sign up to get free credits