图像（Images）原生Gemini格式
Gemini原生格式
Gemini 图片生成
Path Parameters
model*string
模型名，如 gemini-3-pro-image-preview
Request Body
application/json
contents*
对话内容数组。文生图只放文本；图生图把参考图作为 inlineData 与文本混排在同一条 parts 里
generationConfig?
生成参数。生图必须在 responseModalities 里包含 IMAGE
safetySettings?
安全过滤设置，按有害类别分别指定拦截阈值
systemInstruction?
系统指令，用于统一约束画风或输出要求
Response Body
application/json
curl -X POST "https://jiniu.ai/v1beta/models/string:generateContent" \ -H "Content-Type: application/json" \ -d '{ "contents": [ { "role": "user", "parts": [ { "text": "一只戴宇航头盔的柴犬，等距视角" } ] } ], "generationConfig": { "responseModalities": [ "TEXT", "IMAGE" ], "imageConfig": { "aspectRatio": "16:9", "imageSize": "2K" } } }'{
"candidates": [
{
"content": {
"role": "string",
"parts": [
{}
]
},
"finishReason": "string",
"safetyRatings": [
{}
]
}
],
"usageMetadata": {
"promptTokenCount": 0,
"candidatesTokenCount": 0,
"totalTokenCount": 0
}
}