> ## Documentation Index
> Fetch the complete documentation index at: https://docs.eztokens.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Image2 官方

> 通过对话 API 生成高质量图像，支持文生图和图生图

Image2 官方模型支持文生图和图生图能力，通过标准 Chat Completions 接口调用。

## 文生图

<Tabs>
  <Tab title="cURL">
    ```bash theme={null}
    curl https://api.eztokens.ai/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $EZTOKENS_API_KEY" \
      -d '{
        "model": "image2",
        "messages": [{
          "role": "user",
          "content": "A serene mountain landscape at sunset, oil painting style"
        }],
        "max_tokens": 2000
      }'
    ```
  </Tab>

  <Tab title="Python">
    ```python theme={null}
    from openai import OpenAI

    client = OpenAI(
        api_key="EZTOKENS_API_KEY",
        base_url="https://api.eztokens.ai/v1"
    )

    response = client.chat.completions.create(
        model="image2",
        messages=[{
            "role": "user",
            "content": "A serene mountain landscape at sunset, oil painting style"
        }],
        max_tokens=2000
    )

    print(response.choices[0].message.content)
    ```
  </Tab>

  <Tab title="Node.js">
    ```javascript theme={null}
    import OpenAI from "openai";

    const client = new OpenAI({
      apiKey: "EZTOKENS_API_KEY",
      baseURL: "https://api.eztokens.ai/v1",
    });

    const response = await client.chat.completions.create({
      model: "image2",
      messages: [{
        role: "user",
        content: "A serene mountain landscape at sunset, oil painting style"
      }],
      max_tokens: 2000,
    });

    console.log(response.choices[0].message.content);
    ```
  </Tab>
</Tabs>

## 图生图

通过传入参考图片引导生成过程。支持 URL 和 Base64 两种方式：

```python theme={null}
# 方式一：图片 URL
response = client.chat.completions.create(
    model="image2",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Transform this sketch into a photorealistic oil painting"},
            {"type": "image_url", "image_url": {"url": "https://example.com/sketch.jpg"}}
        ]
    }],
    max_tokens=2000
)
```

```python theme={null}
# 方式二：本地图片 Base64
import base64

with open("photo.jpg", "rb") as f:
    encoded = base64.b64encode(f.read()).decode("utf-8")

response = client.chat.completions.create(
    model="image2",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Enhance this photo with a warm vintage filter"},
            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{encoded}"}}
        ]
    }],
    max_tokens=2000
)
```

## 分辨率与尺寸

Image2 支持以下分辨率规格：

| 分辨率         | 宽高比     | 适用场景         |
| ----------- | ------- | ------------ |
| `1024x1024` | 1:1 正方形 | 头像、图标、社交媒体帖子 |
| `1024x1792` | 9:16 竖版 | 手机壁纸、竖版海报    |
| `1792x1024` | 16:9 横版 | 桌面壁纸、横版横幅    |

通过 `size` 参数指定：

```python theme={null}
response = client.chat.completions.create(
    model="image2",
    messages=[{
        "role": "user",
        "content": "A beautiful sunset over the ocean"
    }],
    max_tokens=2000,
    size="1792x1024"  # 16:9 横版
)
```

## 配置参数

| 参数           | 类型      | 必需 | 说明                                           |
| ------------ | ------- | -- | -------------------------------------------- |
| `model`      | string  | 是  | 模型名称，使用 `image2`                             |
| `messages`   | array   | 是  | 消息数组，文生图传文字描述，图生图传入参考图                       |
| `max_tokens` | integer | 否  | 生成图像的最大 Token 数，默认 2000                      |
| `size`       | string  | 否  | 输出分辨率，可选 `1024x1024`、`1024x1792`、`1792x1024` |
| `quality`    | string  | 否  | 图像质量，可选 `standard`（默认）或 `hd`（高清）             |
| `style`      | string  | 否  | 风格模式，可选 `vivid`（生动）或 `natural`（自然）           |
| `n`          | integer | 否  | 生成图片数量，默认为 1                                 |

<Note>
  图生图模式下，参考图片建议使用清晰、高分辨率的图片以获得更好效果。具体模型 ID 和价格请在控制台模型库中查看。
</Note>