space-gemini-image

Gemini Image Generation

Use this Skill when the user expresses an intent to draw (such as "draw a...", "generate an image...", "help me create...").

Invocation Steps

1. Read Configuration

• Read config/secrets.md to get the API Key

2. Construct the prompt

Mode	prompt format	Example
Text-to-image	描述文字	一只可爱的橘猫
Image-to-image	图片URL 描述文字	https://xxx.jpg 画类似风格
Multi-image reference	URL1 URL2 描述文字	https://a.jpg https://b.jpg 融合两张图

Image-to-image requires uploading an image first; refer to tips/image-upload.md。

3. Call the API

curl -s -X POST "https://api.apicore.ai/v1/images/generations" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "模型名称",
    "prompt": "提示词",
    "size": "尺寸比例",
    "n": 1
  }'

4. Return the result

Extract from the response data[0].url and return it to the user.

Reference Documents

• tips/image-upload.md - Image upload method
• tips/chinese-text.md - Chinese text processing techniques