gemini-image

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Gemini Image Generation

Gemini 图像生成

Use this skill when user expresses intent to generate images (e.g., "draw a...", "generate an image...", "create a picture...").

当用户表达出生成图像的意图时使用此技能（例如：“画一只……”、“生成一张图像……”、“创建一幅画……”）。

Steps

步骤

1. Read Configuration

1. 读取配置

Read
```
config/secrets.md
```
to get API Key

读取
```
config/secrets.md
```
获取API Key

2. Construct Prompt

2. 构建提示词

Mode	Prompt Format	Example
Text-to-Image	`description text`	`a cute orange cat`
Image-to-Image	`image_URL description`	`https://xxx.jpg draw similar style`
Multi-Image Reference	`URL1 URL2 description`	`https://a.jpg https://b.jpg merge these two`

For image-to-image, upload local images first. See

tips/image-upload.md

模式	提示词格式	示例
文本转图像	`描述文本`	`一只可爱的橘猫`
图像转图像	`图片URL 描述`	`https://xxx.jpg 绘制相似风格`
多图像参考	`URL1 URL2 描述`	`https://a.jpg https://b.jpg 融合这两张图片`

对于图像转图像模式，请先上传本地图片。详见

tips/image-upload.md

。

3. Call API

3. 调用API

bash

curl -s -X POST "https://api.apicore.ai/v1/images/generations" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "model_name",
    "prompt": "prompt_text",
    "size": "aspect_ratio",
    "n": 1
  }'

bash

curl -s -X POST "https://api.apicore.ai/v1/images/generations" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "model_name",
    "prompt": "prompt_text",
    "size": "aspect_ratio",
    "n": 1
  }'

4. Return Result

4. 返回结果

Extract

data[0].url

from response and return to user.

从响应中提取

data[0].url

并返回给用户。

Reference Docs

参考文档

```
tips/image-upload.md
```
- Image upload methods
```
tips/chinese-text.md
```
- Chinese text handling tips

```
tips/image-upload.md
```
- 图片上传方法
```
tips/chinese-text.md
```
- 中文文本处理技巧