Midjourney

Mj Imagine

MidjourneyPer Request
Alias:mj_imagine
Create API Key

Compare mj_imagine API pricing, supported endpoints, capabilities and access options on Modelsell.

Midjourney文字与可选参考图创作
Starting price
Per Request
Context
—
Maximum input window
Modalities
→

Pricing by Supplier

标准按次
图片音频视频等多模态按次计费
Price$0.035/ request

Capabilities / Supported modalities

Function callingToolsJSON modeStructured outputVision
Input
Output

Provider & data privacy

Provider
Unknown
Tokenizer
BPE (vendor-specific)
License
Provider-specificUnknown
Data retention51 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Mj Imagine

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About Mj Imagine

把视觉想法变成候选画面

Imagine 是从创作描述开始生成图片的方式。你可以写出一个尚不存在的空间、一组产品陈列或故事中的场景,让 Midjourney 给出可供比较的画面。它尤其适合设计早期的风格探索:先找到构图、配色和氛围,再对满意的结果继续变体、放大或编辑。

描述时优先交代主体及其所处环境,再补充视角、光线、材质和表现形式。简洁、具体的视觉信息通常比大量抽象赞美词更有帮助。宽高比和风格参数可以进一步约束结果,具体语法按所选版本与当前渠道支持的设置提交。

参考图能起什么作用?

图片提示可以影响内容、构图、色彩和风格;风格参考则着重提供视觉语言。准备参考图时,应先决定要借鉴什么,再配合文字描述新的目标场景,而不是期望它逐像素复制。

生成后如何继续?

等待任务完成,比较候选图的主体、轮廓和画面关系,再使用结果实际提供的动作继续创作。已有画面只需小改时,可转向变体或局部编辑;想重新寻找主题方向,则调整提示词再次 Imagine。

Use cases and prompting

从一条清楚的画面描述开始,例如:

山间湖畔的玻璃温室,内部有层叠的绿色植物与小型阅读区,雨后清晨,薄雾笼罩松林,暖光从温室透出,远景环境概念设计,横向宽幅构图。

若使用参考图,按接口要求提交图片或链接,并明确要借鉴的是空间结构、色彩还是绘画风格。设置所需画幅后发起任务,保存返回的任务信息。

完成后挑选最符合目标的一张,先判断构图和主体,再检查局部细节;围绕选定结果继续操作,比每轮同时改变许多条件更容易找到满意方向。

API access

API documentation

mj_imagine

Use the linked documentation for model-specific request parameters and examples.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Rate limits

SupplierRPMTPMRPD
标准按次UnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about mj_imagine

What is mj_imagine?

Compare mj_imagine API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call mj_imagine?

Create an API key with access to mj_imagine, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is mj_imagine priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

How should I evaluate mj_imagine for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.