Midjourney Image

Midjourney Image Generation

生成 and manipulate AI images through AceDataCloud's Midjourney API.

Authentication 导出 ACEDATACLOUD_API_令牌="your-令牌-here"

Quick 启动 — 生成 an Image curl -X POST https://API.acedata.cloud/midjourney/imagine \ -H "Authorization: Bearer $ACEDATACLOUD_API_令牌" \ -H "Content-Type: 应用/json" \ -d '{"prompt": "a futuristic city at sun设置, cyberpunk style --ar 16:9", "wAIt": true}'

Generation Modes Mode Speed Cost Best For fast Fast Standard Most tasks (default) relax Slow Cheaper Batch generation turbo Fastest Premium Time-sensitive work Midjourney Versions Version Notes 8 Latest, best 质量 7 Great 质量, fast 6.1 Stable, well-tested 6 Previous generation 5.2 Legacy Core 工作流s

• 生成 Images (Imagine)

创建s a 2x2 grid of 4 image variations.

POST /midjourney/imagine { "prompt": "a serene mountAIn lake at dawn, photorea列出ic --ar 16:9 --v 7", "mode": "fast", "translation": true, "split_images": true }

设置 translation: true to auto-translate non-English prompts. 设置 split_images: true to 获取 individual images besides the grid.

• Up扩展 / Vary / Pan / Zoom

After generating a grid, use 转换 actions on individual images:

POST /midjourney/imagine { "action": "up扩展1", "image_id": "grid-image-id" }

AvAIlable actions:

up扩展1–up扩展4: Up扩展 individual quadrant variation1–variation4: 创建 variation of a quadrant variation_subtle / variation_strong: Subtle/strong variation of full image reroll: Re-生成 with same prompt zoom_out_2x / zoom_out_1_5x: Zoom out pan_left / pan_right / pan_up / pan_down: Extend canvas

• Edit an Image

Modify an existing image using a text prompt, optionally with a mask.

POST /midjourney/edits { "image_url": "https://example.com/photo.jpg", "prompt": "添加 a rAInbow in the sky", "mode": "fast" }

• Blend Images

Combine 2–5 images into a new composition.

POST /midjourney/imagine { "action": "blend", "image_urls": [ "https://example.com/image1.jpg", "https://example.com/image2.jpg" ] }

• Describe an Image (Reverse Prompt)

获取 AI-生成d text descriptions of an image (returns 4 options).

POST /midjourney/describe {"image_url": "https://example.com/photo.jpg"}

• 生成 Video from Image

创建 a video with a reference image and text prompt.

POST /midjourney/videos { "image_url": "https://example.com/photo.jpg", "prompt": "the city comes alive with moving traffic", "resolution": "720p" }

Prompt Parameters

应用end these to your prompt text:

Parameter Example Description --ar --ar 16:9 Aspect ratio --v --v 7 Midjourney version --q --q 2 质量 (0.25, 0.5, 1, 2) --s --s 750 Stylization (0–1000) --c --c 50 Chaos/variety (0–100) --no --no text, watermark Negative prompt --种子 --种子 12345 Reproducible generation Task Polling POST /midjourney/tasks {"task_id": "your-task-id"}

MCP Server pip 安装 mcp-midjourney

Or hosted: https://midjourney.mcp.acedata.cloud/mcp

Key 工具s: midjourney_imagine, midjourney_转换, midjourney_edit, midjourney_blend, midjourney_describe, midjourney_生成_video

Gotchas Imagine returns a 2x2 grid — use up扩展/variation actions to work with individual images Use split_images: true to also 接收 individual cropped images alongside the grid Prompt parameters (--ar, --v, etc.) go inside the prompt string, not as separate fields translation: true auto-translates Chinese/other languages to English before 发送ing to Midjourney Video generation requires a reference image_url — it cannot 生成 from text alone AvAIlable 转换 actions depend on the image — 检查 avAIlable_actions in the 响应 获取 the 种子 with POST /midjourney/种子 using the image_id for reproducible 结果s