# 人物照片多風格與動作生成

## 1.更換照片風格

<figure><img src="https://1859296287-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkYEe2LwUkVTEuNZF6NVm%2Fuploads%2FJeWUZqkz7lf0Aj7Uowcp%2Fimage.png?alt=media&#x26;token=c4ccb5f3-72f5-4a65-aaf5-71664a6dc52e" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}

## Prompt

幫我把這張圖改成可愛風格的全身插畫
{% endhint %}

<figure><img src="https://1859296287-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkYEe2LwUkVTEuNZF6NVm%2Fuploads%2F0DGVc59wrBULRmjo4Im5%2Fimage.png?alt=media&#x26;token=4f2cfee4-642b-4fd6-a338-87205b319f40" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}

## Prompt

幫我把插畫圖改成3D風格
{% endhint %}

**其它風格案例，選擇可愛插畫風的成果，然後輸入下方提示詞**

<figure><img src="https://1859296287-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkYEe2LwUkVTEuNZF6NVm%2Fuploads%2FmA60pfyDyeaQXnCuPkhD%2Fimage.png?alt=media&#x26;token=2f964cd8-3ea7-4257-bf7c-92a981491e45" alt=""><figcaption></figcaption></figure>

## 2.更換動作

**改變動作**

<figure><img src="https://1859296287-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkYEe2LwUkVTEuNZF6NVm%2Fuploads%2FXqsOSkOx8NzX3hBTBTXg%2Fimage.png?alt=media&#x26;token=2d31f039-7596-4827-897c-548e9ef92017" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}

## Prompt

幫我把 JELLYCAT 風格娃娃圖片動作改成跑步姿勢
{% endhint %}

**改變動作+增加物件**

<figure><img src="https://1859296287-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkYEe2LwUkVTEuNZF6NVm%2Fuploads%2F7AV0kma2fKUB48YUhUjQ%2Fimage.png?alt=media&#x26;token=23eed66d-d9ea-4a20-9c05-8043e018f26f" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}

## Prompt

幫我把上面 JELLYCAT 風格娃娃改成坐著，然後肩膀上多一隻黃色可愛小鴨
{% endhint %}

## 3.更換背景，但人物盡量保持一致的方法

<figure><img src="https://1859296287-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkYEe2LwUkVTEuNZF6NVm%2Fuploads%2FQaZ05Eyrwv6sRlCq1m2r%2Fimage.png?alt=media&#x26;token=b3fa041a-245e-4453-80b6-30cd4f105b84" alt=""><figcaption></figcaption></figure>

如果你想要針對同張圖片持續修改(變動會比較小)，請點選圖片，會進入編輯模式，最下方可以輸入要更改的提示詞，這樣的效果會比較穩定。


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://creatorhome.gitbook.io/ai-design/chang-yong-ai-she-ji-gong-ju-zhi-nan/chatgpt-tu-pian-sheng-cheng-ying-yong/ip-ying-yong-an-li/ren-wu-zhao-pian-duo-feng-ge-yu-dong-zuo-sheng-cheng.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.