gemini-3-pro-image-preview 生图 API

curl --request POST \
  --url https://www.geeknow.top/v1beta/models/{model}:generateContent \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "contents": [
    {}
  ],
  "contents[].role": "<string>",
  "contents[].parts": [
    {}
  ],
  "contents[].parts[].text": "<string>",
  "contents[].parts[].inlineData": {},
  "contents[].parts[].inlineData.mimeType": "<string>",
  "contents[].parts[].inlineData.data": "<string>",
  "generationConfig": {},
  "generationConfig.responseModalities": [
    "<string>"
  ],
  "generationConfig.imageConfig": {},
  "generationConfig.imageConfig.aspectRatio": "<string>",
  "generationConfig.imageConfig.imageSize": "<string>",
  "safetySettings": [
    {}
  ]
}
'

import requests

url = "https://www.geeknow.top/v1beta/models/{model}:generateContent"

payload = {
    "contents": [{}],
    "contents[].role": "<string>",
    "contents[].parts": [{}],
    "contents[].parts[].text": "<string>",
    "contents[].parts[].inlineData": {},
    "contents[].parts[].inlineData.mimeType": "<string>",
    "contents[].parts[].inlineData.data": "<string>",
    "generationConfig": {},
    "generationConfig.responseModalities": ["<string>"],
    "generationConfig.imageConfig": {},
    "generationConfig.imageConfig.aspectRatio": "<string>",
    "generationConfig.imageConfig.imageSize": "<string>",
    "safetySettings": [{}]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    contents: [{}],
    'contents[].role': '<string>',
    'contents[].parts': [{}],
    'contents[].parts[].text': '<string>',
    'contents[].parts[].inlineData': {},
    'contents[].parts[].inlineData.mimeType': '<string>',
    'contents[].parts[].inlineData.data': '<string>',
    generationConfig: {},
    'generationConfig.responseModalities': ['<string>'],
    'generationConfig.imageConfig': {},
    'generationConfig.imageConfig.aspectRatio': '<string>',
    'generationConfig.imageConfig.imageSize': '<string>',
    safetySettings: [{}]
  })
};

fetch('https://www.geeknow.top/v1beta/models/{model}:generateContent', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://www.geeknow.top/v1beta/models/{model}:generateContent",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'contents' => [
        [
                
        ]
    ],
    'contents[].role' => '<string>',
    'contents[].parts' => [
        [
                
        ]
    ],
    'contents[].parts[].text' => '<string>',
    'contents[].parts[].inlineData' => [
        
    ],
    'contents[].parts[].inlineData.mimeType' => '<string>',
    'contents[].parts[].inlineData.data' => '<string>',
    'generationConfig' => [
        
    ],
    'generationConfig.responseModalities' => [
        '<string>'
    ],
    'generationConfig.imageConfig' => [
        
    ],
    'generationConfig.imageConfig.aspectRatio' => '<string>',
    'generationConfig.imageConfig.imageSize' => '<string>',
    'safetySettings' => [
        [
                
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.geeknow.top/v1beta/models/{model}:generateContent"

	payload := strings.NewReader("{\n  \"contents\": [\n    {}\n  ],\n  \"contents[].role\": \"<string>\",\n  \"contents[].parts\": [\n    {}\n  ],\n  \"contents[].parts[].text\": \"<string>\",\n  \"contents[].parts[].inlineData\": {},\n  \"contents[].parts[].inlineData.mimeType\": \"<string>\",\n  \"contents[].parts[].inlineData.data\": \"<string>\",\n  \"generationConfig\": {},\n  \"generationConfig.responseModalities\": [\n    \"<string>\"\n  ],\n  \"generationConfig.imageConfig\": {},\n  \"generationConfig.imageConfig.aspectRatio\": \"<string>\",\n  \"generationConfig.imageConfig.imageSize\": \"<string>\",\n  \"safetySettings\": [\n    {}\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.geeknow.top/v1beta/models/{model}:generateContent")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"contents\": [\n    {}\n  ],\n  \"contents[].role\": \"<string>\",\n  \"contents[].parts\": [\n    {}\n  ],\n  \"contents[].parts[].text\": \"<string>\",\n  \"contents[].parts[].inlineData\": {},\n  \"contents[].parts[].inlineData.mimeType\": \"<string>\",\n  \"contents[].parts[].inlineData.data\": \"<string>\",\n  \"generationConfig\": {},\n  \"generationConfig.responseModalities\": [\n    \"<string>\"\n  ],\n  \"generationConfig.imageConfig\": {},\n  \"generationConfig.imageConfig.aspectRatio\": \"<string>\",\n  \"generationConfig.imageConfig.imageSize\": \"<string>\",\n  \"safetySettings\": [\n    {}\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://www.geeknow.top/v1beta/models/{model}:generateContent")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"contents\": [\n    {}\n  ],\n  \"contents[].role\": \"<string>\",\n  \"contents[].parts\": [\n    {}\n  ],\n  \"contents[].parts[].text\": \"<string>\",\n  \"contents[].parts[].inlineData\": {},\n  \"contents[].parts[].inlineData.mimeType\": \"<string>\",\n  \"contents[].parts[].inlineData.data\": \"<string>\",\n  \"generationConfig\": {},\n  \"generationConfig.responseModalities\": [\n    \"<string>\"\n  ],\n  \"generationConfig.imageConfig\": {},\n  \"generationConfig.imageConfig.aspectRatio\": \"<string>\",\n  \"generationConfig.imageConfig.imageSize\": \"<string>\",\n  \"safetySettings\": [\n    {}\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "BASE64_OR_URL"
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 456,
    "totalTokenCount": 579,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 23
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 456
      }
    ]
  },
  "modelVersion": "gemini-3-pro-image-preview",
  "createTime": "2026-05-21T00:00:00Z"
}

POST

https://www.geeknow.top

v1beta

models

{model}

:generateContent

gemini-3-pro-image-preview 生图 API

curl --request POST \
  --url https://www.geeknow.top/v1beta/models/{model}:generateContent \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "contents": [
    {}
  ],
  "contents[].role": "<string>",
  "contents[].parts": [
    {}
  ],
  "contents[].parts[].text": "<string>",
  "contents[].parts[].inlineData": {},
  "contents[].parts[].inlineData.mimeType": "<string>",
  "contents[].parts[].inlineData.data": "<string>",
  "generationConfig": {},
  "generationConfig.responseModalities": [
    "<string>"
  ],
  "generationConfig.imageConfig": {},
  "generationConfig.imageConfig.aspectRatio": "<string>",
  "generationConfig.imageConfig.imageSize": "<string>",
  "safetySettings": [
    {}
  ]
}
'

import requests

url = "https://www.geeknow.top/v1beta/models/{model}:generateContent"

payload = {
    "contents": [{}],
    "contents[].role": "<string>",
    "contents[].parts": [{}],
    "contents[].parts[].text": "<string>",
    "contents[].parts[].inlineData": {},
    "contents[].parts[].inlineData.mimeType": "<string>",
    "contents[].parts[].inlineData.data": "<string>",
    "generationConfig": {},
    "generationConfig.responseModalities": ["<string>"],
    "generationConfig.imageConfig": {},
    "generationConfig.imageConfig.aspectRatio": "<string>",
    "generationConfig.imageConfig.imageSize": "<string>",
    "safetySettings": [{}]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    contents: [{}],
    'contents[].role': '<string>',
    'contents[].parts': [{}],
    'contents[].parts[].text': '<string>',
    'contents[].parts[].inlineData': {},
    'contents[].parts[].inlineData.mimeType': '<string>',
    'contents[].parts[].inlineData.data': '<string>',
    generationConfig: {},
    'generationConfig.responseModalities': ['<string>'],
    'generationConfig.imageConfig': {},
    'generationConfig.imageConfig.aspectRatio': '<string>',
    'generationConfig.imageConfig.imageSize': '<string>',
    safetySettings: [{}]
  })
};

fetch('https://www.geeknow.top/v1beta/models/{model}:generateContent', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://www.geeknow.top/v1beta/models/{model}:generateContent",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'contents' => [
        [
                
        ]
    ],
    'contents[].role' => '<string>',
    'contents[].parts' => [
        [
                
        ]
    ],
    'contents[].parts[].text' => '<string>',
    'contents[].parts[].inlineData' => [
        
    ],
    'contents[].parts[].inlineData.mimeType' => '<string>',
    'contents[].parts[].inlineData.data' => '<string>',
    'generationConfig' => [
        
    ],
    'generationConfig.responseModalities' => [
        '<string>'
    ],
    'generationConfig.imageConfig' => [
        
    ],
    'generationConfig.imageConfig.aspectRatio' => '<string>',
    'generationConfig.imageConfig.imageSize' => '<string>',
    'safetySettings' => [
        [
                
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.geeknow.top/v1beta/models/{model}:generateContent"

	payload := strings.NewReader("{\n  \"contents\": [\n    {}\n  ],\n  \"contents[].role\": \"<string>\",\n  \"contents[].parts\": [\n    {}\n  ],\n  \"contents[].parts[].text\": \"<string>\",\n  \"contents[].parts[].inlineData\": {},\n  \"contents[].parts[].inlineData.mimeType\": \"<string>\",\n  \"contents[].parts[].inlineData.data\": \"<string>\",\n  \"generationConfig\": {},\n  \"generationConfig.responseModalities\": [\n    \"<string>\"\n  ],\n  \"generationConfig.imageConfig\": {},\n  \"generationConfig.imageConfig.aspectRatio\": \"<string>\",\n  \"generationConfig.imageConfig.imageSize\": \"<string>\",\n  \"safetySettings\": [\n    {}\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.geeknow.top/v1beta/models/{model}:generateContent")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"contents\": [\n    {}\n  ],\n  \"contents[].role\": \"<string>\",\n  \"contents[].parts\": [\n    {}\n  ],\n  \"contents[].parts[].text\": \"<string>\",\n  \"contents[].parts[].inlineData\": {},\n  \"contents[].parts[].inlineData.mimeType\": \"<string>\",\n  \"contents[].parts[].inlineData.data\": \"<string>\",\n  \"generationConfig\": {},\n  \"generationConfig.responseModalities\": [\n    \"<string>\"\n  ],\n  \"generationConfig.imageConfig\": {},\n  \"generationConfig.imageConfig.aspectRatio\": \"<string>\",\n  \"generationConfig.imageConfig.imageSize\": \"<string>\",\n  \"safetySettings\": [\n    {}\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://www.geeknow.top/v1beta/models/{model}:generateContent")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"contents\": [\n    {}\n  ],\n  \"contents[].role\": \"<string>\",\n  \"contents[].parts\": [\n    {}\n  ],\n  \"contents[].parts[].text\": \"<string>\",\n  \"contents[].parts[].inlineData\": {},\n  \"contents[].parts[].inlineData.mimeType\": \"<string>\",\n  \"contents[].parts[].inlineData.data\": \"<string>\",\n  \"generationConfig\": {},\n  \"generationConfig.responseModalities\": [\n    \"<string>\"\n  ],\n  \"generationConfig.imageConfig\": {},\n  \"generationConfig.imageConfig.aspectRatio\": \"<string>\",\n  \"generationConfig.imageConfig.imageSize\": \"<string>\",\n  \"safetySettings\": [\n    {}\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "BASE64_OR_URL"
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 456,
    "totalTokenCount": 579,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 23
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 456
      }
    ]
  },
  "modelVersion": "gemini-3-pro-image-preview",
  "createTime": "2026-05-21T00:00:00Z"
}

gemini-3-pro-image-preview 生图 API

这个模型使用 Gemini 官方 generateContent 格式生图，适合直接复用 contents / parts 结构，并且支持 2K 尺寸档位。

路径为 POST /v1beta/models/{model}:generateContent。
model 固定传 gemini-3-pro-image-preview。
文生图和图生图都走同一套 contents[].parts[] 结构。
generationConfig.responseModalities 建议同时请求 IMAGE 和 TEXT。
返回里既可能直接给 inlineData.data Base64，也可能给图片 URL。

先看懂图生图

Gemini 这里的图生图，本质上就是：

把文字提示词放进 parts[].text
把参考图按顺序继续塞进同一个 parts[]
让模型在同一次 generateContent 里同时看到“文字要求 + 图片参考”

最关键的区别只有一处：

文生图：parts[] 里只有 text
图生图：parts[] 里除了 text，还会追加一个或多个 inlineData

也就是说，Gemini 不是单独再开一个“edit”接口；它是直接在 generateContent 里，把图片当作输入的一部分传进去。

文生图 vs 图生图

场景	`parts[]` 内容	说明
文生图	只有 `text`	纯提示词生成
图生图	`text` + 一个或多个 `inlineData`	让模型参考已有图片风格、主体或构图

图生图怎么传

你只需要记住一个规则：

第一类内容是提示词：{ "text": "..." }
第二类内容是参考图：{ "inlineData": { "mimeType": "...", "data": "BASE64..." } }

构造请求时通常先放文本提示词，再把每一张参考图转成 Base64，按顺序追加到同一个 parts[]。

图生图最小示例

{
  "contents": [
    {
      "role": "user",
      "parts": [
        { "text": "保留参考图的主体氛围，重做成更高级的海报" },
        {
          "inlineData": {
            "mimeType": "image/jpeg",
            "data": "BASE64_IMAGE"
          }
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": ["TEXT", "IMAGE"],
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "2K"
    }
  }
}

方法与路径

POST /v1beta/models/gemini-3-pro-image-preview:generateContent

请求示例

curl -X POST https://www.geeknow.top/v1beta/models/gemini-3-pro-image-preview:generateContent \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Accept: application/json" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          { "text": "一张未来感 AI 工作台场景，冷色氛围，电影级布光" }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "temperature": 1.0,
      "topP": 0.95,
      "maxOutputTokens": 8192,
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'

import requests

resp = requests.post(
    "https://www.geeknow.top/v1beta/models/gemini-3-pro-image-preview:generateContent",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Accept": "application/json",
        "Content-Type": "application/json",
    },
    json={
        "contents": [
            {
                "role": "user",
                "parts": [
                    {"text": "一张未来感 AI 工作台场景，冷色氛围，电影级布光"}
                ],
            }
        ],
        "generationConfig": {
            "responseModalities": ["TEXT", "IMAGE"],
            "temperature": 1.0,
            "topP": 0.95,
            "maxOutputTokens": 8192,
            "imageConfig": {
                "aspectRatio": "16:9",
                "imageSize": "2K",
            },
        },
    },
    timeout=60,
)
print(resp.json())

图生图示例

{
  "contents": [
    {
      "role": "user",
      "parts": [
        { "text": "融合参考图风格，输出一张高清横版海报" },
        {
          "inlineData": {
            "mimeType": "image/jpeg",
            "data": "BASE64_IMAGE_1"
          }
        },
        {
          "inlineData": {
            "mimeType": "image/jpeg",
            "data": "BASE64_IMAGE_2"
          }
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": ["TEXT", "IMAGE"],
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "2K"
    }
  }
}

图生图字段解释

字段	图生图里的作用
`parts[].text`	告诉模型“你要怎么改、保留什么、输出成什么风格”
`parts[].inlineData.mimeType`	声明参考图格式
`parts[].inlineData.data`	参考图的 Base64 内容
`imageConfig.aspectRatio`	约束最终出图比例
`imageConfig.imageSize`	约束最终出图清晰度

能传几张参考图

多参考图可以按顺序追加多个 inlineData：

支持 1 张参考图
也支持多张参考图
多张时就是连续放多个 inlineData

返回后怎么看结果

Gemini 生图返回的图片通常在：

candidates[0].content.parts[].inlineData.data

这个字段可能有两种情况：

直接是 Base64 图片数据
直接是图片 URL

因此文档示例中用 BASE64_OR_URL 表示这两种可能的返回形式。

Body

contents

array<object>

required

输入内容列表。每项通常包含 role 和 parts。

contents[].role

string

角色字段，常用值为 user。

contents[].parts

array<object>

required

内容片段数组。提示词和参考图都在这里构造。

contents[].parts[].text

string

文本提示词。

contents[].parts[].inlineData

object

参考图输入。包含 mimeType 和 data 两个字段。

contents[].parts[].inlineData.mimeType

string

图片 MIME 类型，常见值为 image/jpeg、image/png、image/webp。

contents[].parts[].inlineData.data

string

Base64 编码的图片内容。

generationConfig

object

required

生成配置对象。

generationConfig.responseModalities

array<string>

返回模态列表。建议使用 ["IMAGE", "TEXT"]。

generationConfig.imageConfig

object

required

图像配置对象。

generationConfig.imageConfig.aspectRatio

string

图片比例。常见值包括 1:1、16:9、9:16、4:3、3:4、3:2、2:3、21:9。

generationConfig.imageConfig.imageSize

string

图片清晰度。这个模型支持 1K 和 2K。

safetySettings

array<object>

安全设置。可不传。

响应示例

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "BASE64_OR_URL"
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 456,
    "totalTokenCount": 579,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 23
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 456
      }
    ]
  },
  "modelVersion": "gemini-3-pro-image-preview",
  "createTime": "2026-05-21T00:00:00Z"
}

Response

candidates[].content.parts[].inlineData.mimeType

string

返回图片 MIME 类型。

candidates[].content.parts[].inlineData.data

string

图片数据。可能是 Base64，也可能直接是图片 URL。

usageMetadata

object

Token 统计信息。

gemini-3-pro-image-preview 会按请求里的 imageSize 下发，2K 会保留，不会被强制回落到 1K。

异步调用

gemini-3-pro-image-preview 也支持通过统一图像异步入口提交任务：

POST /v1/images/generations/async

异步入口使用 OpenAI Images 兼容 JSON。提交成功后读取返回的 id / task_id，再通过 GET /v1/images/generations/async/{taskId} 查询状态和结果。

概览

文本系列

图像系列

视频系列

上传管理

任务管理

账户管理

gemini-3-pro-image-preview 生图 API

gemini-3-pro-image-preview 生图 API

先看懂图生图

文生图 vs 图生图

图生图怎么传

图生图最小示例

方法与路径

请求示例

图生图示例

图生图字段解释

能传几张参考图

返回后怎么看结果

Body

响应示例

Response

异步调用

相关接口

​gemini-3-pro-image-preview 生图 API

​先看懂图生图

​文生图 vs 图生图

​图生图怎么传

​图生图最小示例

​方法与路径

​请求示例

​图生图示例

​图生图字段解释

​能传几张参考图

​返回后怎么看结果

​Body

​响应示例

​Response

​异步调用

​相关接口

gemini-3-pro-image-preview 生图 API

先看懂图生图

文生图 vs 图生图

图生图怎么传

图生图最小示例

方法与路径

请求示例

图生图示例

图生图字段解释

能传几张参考图

返回后怎么看结果

Body

响应示例

Response

异步调用

相关接口