Midjourney

供应商: Midjourney

图像

适合艺术插画、视觉概念和风格化创意图

典型耗时: 30-90s
参考输入: 最多 4 个
toolId: midjourney

输入模式

text-to-imageimage-to-image

变体

Imagine

Prompt and image-reference generation on Midjourney v8.2.

text-to-imageimage-to-image

Edit

Text-guided edits for one or more reference images.

image-to-image

Blend

Blend two to four uploaded images into a new composition.

image-to-image

Describe

Generate prompt ideas from one uploaded image.

image-to-image

Upscale

Upscale one image from a completed four-image Midjourney grid.

text-to-image

Variation

Create a variation from a selected image in a completed grid.

text-to-image

Vary Strong

Create a stronger variation from an upscaled image.

text-to-image

Vary Subtle

Create a subtle variation from an upscaled image.

text-to-image

Reroll

Rerun a completed Midjourney task with the same prompt.

text-to-image

Zoom Out

Zoom out from an upscaled Midjourney image.

text-to-image

Pan

Extend an upscaled image left, right, up, or down.

text-to-image

Inpaint

Start an inpaint job and open the mask editing step.

text-to-image

Modal

Submit prompt and mask data for an active inpaint task.

text-to-image

Remix Strong

Remix a selected image with a stronger prompt change.

text-to-image

Remix Subtle

Remix a selected image with a lighter prompt change.

text-to-image

参数

参数	类型	默认值	取值	说明
version	select	8.2	8.2 \| 8.1 \| 8 \| 7 \| 6.1 \| 6 \| 5.2	Model version. Prompt syntax and look differ between versions; older prompts often need rework on newer versions.
aspect_ratio	select	1:1	1:1 \| 16:9 \| 9:16 \| 4:3 \| 3:4 \| 3:2 \| 2:3 \| 21:9	Output frame shape. Keep one ratio across a series.
speed	select	fast	relax \| fast \| turbo	Turbo returns faster results and costs more.
quality	select	1	0.25 \| 0.5 \| 1 \| 2	Render quality/time trade-off. Higher q spends more render time.
stylize	slider	100	0–1000	Controls artistic style intensity.
chaos	slider	0	0–100	Higher values produce more varied results.
weird	slider	0	0–3000	Adds unusual composition and style choices.
raw	toggle	false	—	Reduces default aesthetic styling for more literal results.
tile	toggle	false	—	Creates seamless repeating patterns when supported by the selected version.
niji	toggle	false	—	Uses Niji anime styling. Select v7 or v6 for best compatibility.
seed	text		–20	Optional integer seed for repeatable results.
negative_prompt	text		–1000	Things to avoid in the image.
sref	text		–1000	Optional URL used as a style reference.
cref	text		–1000	Optional URL used as a character reference.
iw	slider	1	0–3	Controls how strongly uploaded image references influence the result.

定价

价格即将公布 —— 联系我们获取抢先体验价格

价格更新于: —

API 示例

POST /v1/generations — midjourney

curl -X POST https://api.mukelabs.com/v1/generations \
  -H "Authorization: Bearer $MUKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "toolId": "midjourney",
    "inputMode": "text-to-image",
    "prompt": "your prompt here",
    "params": { "version": "8.2" },
    "references": [],
    "idempotencyKey": "a-unique-key-per-task",
    "subjectId": "your-user-id"
  }'

常见问题

如何在 Muke Labs 上调用 Midjourney?

提交 POST /v1/generations,toolId 为 "midjourney",选择一种输入模式(text-to-image, image-to-image),然后轮询 GET /v1/generations/{jobId} 获取结果。

Midjourney 的价格是多少?

该模型的公开定价正在敲定 —— 联系我们获取抢先体验价格。所有任务均从预充值美元余额扣费,失败任务自动退款。

任务失败会怎样?

任务返回 "failed" 状态和类型化错误码,费用自动退回余额。

在哪里获取 API key?

在开发者门户(https://portal.muke.name)创建,然后作为 Bearer token 携带在每个请求上。

Midjourney

输入模式

变体

参数

定价

API 示例

常见问题

相关模型

Character Concept Board

Flux 2 Dev

Flux 2 Flex

Flux 2 Pro