算力路由器算力路由器
AI Model InterfaceImagesNative OpenAI format

Generate Images

Create images given a prompt. Learn more.

Quick Start

This generic interface is used for OpenAI image models; GPT Image 2, Universal Sync Image, and Imagen within the project also reuse /v1/images/generations, selecting model extension parameters according to the corresponding model page.

TypeModel
OpenAIdall-e-2, dall-e-3, gpt-image-1, gpt-image-1-mini, gpt-image-1.5, chatgpt-image-latest
GPT Image 2gpt-image-2, gpt-image-2-vip, gpt-image-2-1k, gpt-image-2-2k, gpt-image-2-4k
Universal Sync Imagez-image, z-image-turbo, qwen-image, wan2.6, wan2.7-image, wan2.7-image-pro
Imagenimagen-4.0-generate-001, imagen-4.0-ultra-generate-001, imagen-4.0-fast-generate-001
Gemini Image Chatgemini-2.0-flash-exp-image-generation, gemini-2.0-flash-exp, gemini-2.5-flash-image, gemini-3-pro-image-preview, gemini-3.1-flash-image-preview
curl "$BASE_URL/v1/images/generations" \
  -H "Authorization: Bearer $NODEKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A product poster of a red mountain bike, white background, clear studio shot",
    "size": "1024x1024",
    "quality": "medium",
    "n": 1,
    "response_format": "url"
  }'
from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://nodekey.xinghanyun.cn/v1")
image = client.images.generate(
    model="gpt-image-2",
    prompt="A product poster of a red mountain bike, white background, clear studio shot",
    size="1024x1024",
    quality="medium",
    n=1,
)
print(image.data[0].url)

Image editing goes through /v1/images/edits; the Universal editing models include qwen-image-edit, qwen-image-edit-max, qwen-image-edit-plus and their dated versions. The Gemini image chat model goes through /v1/chat/completions or Gemini native generateContent.

POST
/v1/images/generations/
AuthorizationBearer <token>

In: header

Request Body

application/json

model?string

用于图像生成的模型。dall-e-2dall-e-3gpt-image-1 之一。默认为 dall-e-2,除非使用特定于 gpt-image-1 的参数。

prompt*string

所需图像的文本描述。gpt-image-1 的最大长度为 32000 个字符,dall-e-2 的最大长度为 1000 个字符,dall-e-3 的最大长度为 4000 个字符。

n?integer

要生成的图像数量。必须介于 1 到 10 之间。对于 dall-e-3,仅支持 n=1

size?string

生成的图像的大小。对于 gpt-image-1,必须是 1024x10241536x1024(横向)、1024x1536(纵向)或自动(默认值)之一,对于 dall-e-2,必须是 256x256、``512x5121024x1024 之一,对于 dall-e-3,必须是 1024x10241792x10241024x1792 之一。

background?string

允许为生成的图像的背景设置透明度。此参数仅支持 gpt-image-1。必须是以下之一 透明不透明自动(默认值)。使用自动时,模型将自动确定图像的最佳背景。

如果是透明的,则输出格式需要支持透明度,因此应将其设置为 png(默认值)或 webp

moderation?string

控制 gpt-image-1 生成的图像的内容审核级别。必须为低, 以进行限制较少的筛选或自动(默认值)。

quality?string

将生成的图像的质量。

stream?string
style?string
user?string

Response Body

application/json

curl -X POST "https://nodekey.xinghanyun.cn/v1/images/generations/" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-4o",    "prompt": "把图片中的自行车改成红色,保持背景和构图不变",    "n": 1  }'
{
  "created": 0,
  "data": [
    {
      "b64_json": "string",
      "url": "string"
    }
  ],
  "usage": {
    "total_tokens": 0,
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": {
      "text_tokens": 0,
      "image_tokens": 0
    }
  }
}

Last updated on