image-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Image Generation

图像生成

Use When

使用场景

The desired final asset is an image or image batch.
The request may include text prompts, uploaded images, previous outputs, product URLs, research handoffs, product images, persona images, banners, thumbnails, storyboard panels, or batch variants.
The next decision is task class, model/reference policy, and runner handoff.

所需最终资产为单张图像或批量图像。
请求可能包含文本提示词、上传的图像、之前的输出、产品URL、研究资料移交、产品图、人物形象图、横幅、缩略图、分镜面板或批量变体。
下一步需要确定任务类别、模型/参考策略，并转交给执行器。

Do Not Use When

不适用场景

The final asset is video, audio, subtitles, transcripts, or an edit plan.
The image request is already normalized and ready to execute. Use
```
image-batch-runner
```
.
The user needs hook decoding or reference boundaries first. Use
```
reference-decode
```
or
```
reference-contract-builder
```
.

最终资产为视频、音频、字幕、转录稿或编辑方案。
图像请求已标准化并可直接执行。此时应使用
```
image-batch-runner
```
。
用户需要先进行钩子解码或确定参考边界。此时应使用
```
reference-decode
```
或
```
reference-contract-builder
```
。

Core Boundary

核心边界

This is the image generation controller. It does not submit jobs.

It must:

identify the input type,
classify the image task,
select model and reference rules,
create the handoff for
```
image-batch-runner
```
.

这是图像生成控制器，不提交任务。

它必须：

识别输入类型，
对图像任务进行分类，
选择模型和参考规则，
创建转交给
```
image-batch-runner
```
的移交信息。

Task Classes

任务类别

Task class	Typical input	Handoff
`text_to_image`	prompt only	write normalized image brief for `image-batch-runner`
`image_edit`	uploaded image plus change request	bind edit image and preserve/alter rules
`reference_image`	benchmark frame or style board	use `reference-contract-builder` before runner
`product_image`	product photo, URL, or product facts	bind product identity and forbid invented claims
`banner_thumbnail`	offer, hook, platform	require aspect ratio and text/UI policy
`storyboard_image`	panel plan or board spec	hand storyboard panels to `image-batch-runner`
`batch_variant`	many variants or personas	preserve shared rules and vary only declared fields

任务类别	典型输入	移交操作
`text_to_image`	仅提示词	为 `image-batch-runner` 编写标准化的图像需求说明
`image_edit`	上传的图像加修改请求	绑定待编辑图像并设置保留/修改规则
`reference_image`	基准帧或风格板	在交给执行器前先使用 `reference-contract-builder`
`product_image`	产品照片、URL或产品信息	绑定产品身份并禁止虚构声明
`banner_thumbnail`	促销信息、钩子、平台	要求指定宽高比和文字/UI策略
`storyboard_image`	分镜面板方案或规格	将分镜面板转交给 `image-batch-runner`
`batch_variant`	多种变体或人物形象	保留通用规则，仅修改指定字段

Model And Reference Rules

模型与参考规则

Text-only drafts may use a text-to-image endpoint.
Edits require a bound source image and an edit-capable endpoint.
Persona, product, and brand identity are
```
binding
```
references unless the user explicitly marks them inspiration-only.
Benchmark clips, mood boards, and competitor references are inspiration-only unless the contract says otherwise.
Excluded references must not enter the runner request.

纯文本草稿可使用文本转图像接口。
编辑任务需要绑定源图像和支持编辑的接口。
人物形象、产品和品牌标识属于
```
binding
```
（绑定型）参考，除非用户明确标记为仅作灵感参考。
基准片段、情绪板和竞品参考默认仅作灵感参考，除非合同另有规定。
被排除的参考不得纳入执行器的请求中。

Routing Table

路由表

If not image-generation	Send to
Needs media understanding first	`media-router`
Needs reference meaning decoded	`reference-decode`
Needs binding/inspiration/excluded contract	`reference-contract-builder`
Needs storyboard panels	`storyboard-grid-writer`
Needs execution with normalized request	`image-batch-runner`
Final output is video	`video-generation`
Final output is audio	`audio-generation`

若不属于图像生成场景	转交至
需要先进行媒体理解	`media-router`
需要解码参考内容含义	`reference-decode`
需要制定绑定/灵感/排除参考的规则	`reference-contract-builder`
需要生成分镜面板	`storyboard-grid-writer`
需要使用标准化请求执行	`image-batch-runner`
最终输出为视频	`video-generation`
最终输出为音频	`audio-generation`

Output Shape

输出格式

Return:

```
taskClass
```
```
inputType
```
```
modelRule
```
```
referencePolicy
```
```
requiredRunnerInputs
```
```
handoffSkill
```
```
mustNotDo
```

返回以下内容：

```
taskClass
```
```
inputType
```
```
modelRule
```
```
referencePolicy
```
```
requiredRunnerInputs
```
```
handoffSkill
```
```
mustNotDo
```

Fail Fast

快速失败规则

Stop if source images, edit targets, product identity, aspect ratio, text/UI policy, or reference ownership is missing and would change the output.
Do not submit, poll, upload, or choose private provider routes.
Do not let
```
image-batch-runner
```
make creative classification decisions.

若缺失源图像、编辑目标、产品身份、宽高比、文字/UI策略或参考所有权，且这些信息会影响输出结果，则停止操作。
不得提交、轮询、上传或选择私有提供商路由。
不得让
```
image-batch-runner
```
做出创意分类决策。

Public Command Boundary

公共命令边界

Check readiness first:

postplus doctor --skill image-generation

This public skill is instruction-driven. Produce the controller handoff artifact directly from the available evidence.
Do not call private provider/runtime paths or unpublished local tools.
If the CLI returns a quote-confirmation challenge, run
```
postplus quote confirm --json --challenge-file <challenge.json>
```
and retry with the returned token.

先检查就绪状态：

postplus doctor --skill image-generation

。

此公共技能由指令驱动，直接根据现有证据生成控制器移交文件。
不得调用私有提供商/运行时路径或未发布的本地工具。
若CLI返回报价确认挑战，运行
```
postplus quote confirm --json --challenge-file <challenge.json>
```
并使用返回的令牌重试。