Image-to-image (以图生图)

基于输入图像生成相似或变体图像的API接口，基于先进的AI模型，能够根据输入的参考图像生成风格相似或内容变体的新图像，适合创意设计和图像迭代需求

📋 基本信息

属性	值
接口地址	`POST /v1/chat/completions`
模型名称	`gemini-2.5-flash-image`

📝 请求参数

路径	参数	类型	必填	说明	默认
-	`model`	string	✅	模型名称，固定为 `gemini-2.5-flash-image`	-
-	`messages`	array	✅	消息数组，包含用户输入的文本和图片	-
`messages[]`	`role`	string	✅	消息角色，固定为 `user`	-
`messages[]`	`content`	array	✅	内容数组，包含文本和图片元素	-
`content[]`	`type`	string	✅	内容类型：`text` 或 `image_url`	-
`content[]`	`text`	string	❌	当 type 为 `text` 时的文本内容	-
`content[]`	`image_url`	object	❌	当 type 为 `image_url` 时的图片对象	-
`image_url`	`url`	string	✅	图片的URL地址（当type为image_url时必填）	-

注意：

image-to-image 模型需要一个参考图片和可选的文本描述来生成变体图片。
默认会保持输出图片与输入图片尺寸一致；若未提供输入图片，则生成 1:1 的方图。
若需指定宽高比，可通过 extra_body.google.image_config.aspect_ratio 选择以下预设值。

宽高比	分辨率
1:1	1024x1024
2:3	832x1248
3:2	1248x832
3:4	864x1184
4:3	1184x864
4:5	896x1152
5:4	1152x896
9:16	768x1344
16:9	1344x768
21:9	1536x672

📝 请求示例

curl https://api.xty.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxx" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "基于这张图片生成一个卡通风格的变体，保持主要元素但改变艺术风格"},
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/reference-image.jpg"
            }
          }
        ]
      }
    ],
    "extra_body": {
      "google": {
        "image_config": {
          "aspect_ratio": "16:9"
        }
      }
    }
  }'

import requests
import json

url = "https://api.xty.app/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-xxxxx"
}
data = {
    "model": "gemini-2.5-flash-image",
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "基于这张图片生成一个卡通风格的变体，保持主要元素但改变艺术风格"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/reference-image.jpg"
                    }
                }
            ]
        }
    ],
    "extra_body": {
        "google": {
            "image_config": {
                "aspect_ratio": "16:9"
            }
        }
    }
}

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json())

from openai import OpenAI
import httpx

client = OpenAI(
    base_url="https://api.xty.app/v1",
    api_key="sk-xxxxx",
    http_client=httpx.Client(
        base_url="https://api.xty.app/v1",
        follow_redirects=True,
    ),
)

response = client.chat.completions.create(
    model="gemini-2.5-flash-image",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "基于这张图片生成一个卡通风格的变体，保持主要元素但改变艺术风格"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/reference-image.jpg"
                    }
                }
            ]
        }
    ],
    extra_body={
        "extra_body": {
            "google": {
                "image_config": {
                    "aspect_ratio": "16:9"
                }
            }
        }
    }
)

print(response)

fetch('https://api.xty.app/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-xxxxx'
  },
  body: JSON.stringify({
    model: "gemini-2.5-flash-image",
    messages: [
      {
        role: "user",
        content: [
          {type: "text", text: "基于这张图片生成一个卡通风格的变体，保持主要元素但改变艺术风格"},
          {
            type: "image_url",
            image_url: {
              url: "https://example.com/reference-image.jpg"
            }
          }
        ]
      }
    ],
    extra_body: {
      google: {
        image_config: {
          aspect_ratio: "16:9"
        }
      }
    }
  })
})
.then(response => response.json())
.then(data => console.log(data));

📤 响应示例

成功响应

{
  "id": "gemini-1704067200000",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "gemini-2.5-flash-image",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "这是修改后的图片:![image](data:image/png;base64,XXX)"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

错误响应

{
  "error": {
    "message": "请求失败",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

🖼️ 效果展示

输入示例

输入文字(中文版)：使用提供的图片来制作插画角色的 1/7 比例商业化手办，并以写实的风格与环境呈现。将手办放置在一张电脑桌上，使用无文字的圆形透明亚克力底座。在电脑屏幕上，显示该手办在 ZBrush 中的建模过程。在电脑屏幕旁边，放置一个 BANDAI 风格的玩具包装盒，包装盒上印有原始插画。

输入文字(英文版)：Use the provided images to create a 1/7-scale commercial figure of the character from the illustration, presented in a realistic style and environment. Place the figure on a computer desk, using a circular transparent acrylic base with no text. On the computer screen, display the figure’s modeling process in ZBrush. Beside the computer screen, place a BANDAI-style toy packaging box printed with the original illustration.

输入图片：输入图片 - 原始照片