创建图像

创建图像

POST /images/generations

使用所选的提供者和模型生成图像

Create Image

post

Authorizations

Portkey-Key & Virtual-KeyPortkey-Key & Provider-Auth & Provider-NamePortkey-Key & ConfigPortkey-Key & Provider-Auth & Provider-Name & Custom-Host

x-portkey-api-keystringRequired

x-portkey-virtual-keystringRequired

Body

application/json

promptstringRequired

A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2 and 4000 characters for dall-e-3.

Example: A cute baby sea otter

modelany of | nullableOptional

The model to use for image generation.

Default: dall-e-2Example: dall-e-3

stringOptional

or

string · enumOptionalPossible values:

ninteger | nullableOptional

The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.

Default: 1Example: 1

qualitystring · enumOptional

The quality of the image that will be generated. hd creates images with finer details and greater consistency across the image. This param is only supported for dall-e-3.

Default: standardExample: standardPossible values:

response_formatstring · enum | nullableOptional

The format in which the generated images are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated.

Default: urlExample: urlPossible values:

sizestring · enum | nullableOptional

The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.

Default: 1024x1024Example: 1024x1024Possible values:

stylestring · enum | nullableOptional

The style of the generated images. Must be one of vivid or natural. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for dall-e-3.

Default: vividExample: vividPossible values:

userstringOptional

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example: user-1234

Responses

200

OK

application/json

post

/images/generations

DefaultDefaultDefaultSelf-HostedSelf-HostedSelf-Hosted

curl https://api.portkey.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "size": "1024x1024"
  }'

200

OK

{
  "created": 1,
  "data": [
    {
      "b64_json": "text",
      "url": "text",
      "revised_prompt": "text"
    }
  ]
}

将请求的配置参数作为头部传递，如这里所定义。

Portkey会根据图像模型接受的参数自动转换参数。

SDK 使用

images.create 方法在 Portkey 或 OpenAI SDK 中允许您使用各种图像模型生成图像。此方法提供了一个简单的接口来请求图像生成。

方法签名

OpenAI NodeJS

client.images.create(requestParams[configParams]);

OpenAI Python

参数

1. requestParams (对象): 完成请求的参数。这些参数应包括提示和模型，并由 Portkey 自动转换为图像模型。

2. configParams (对象): 请求的附加配置选项。这是一个可选参数，可以包括此特定请求的自定义配置选项。这些选项将覆盖在 Portkey 客户端中设置的配置。

示例用法

REST API 示例

在 REST 调用中，x-portkey-api-key 是一个必需的头部，它可以与以下选项配对以发送提供者详细信息：

1. x-portkey-provider 和 Authorization（或类似的身份验证头部）

2. x-portkey-virtual-key

3. x-portkey-config

使用提供者 + 身份验证的示例请求：

curl "https://api.portkey.ai/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-provider: openai" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "prompt": "A cute baby sea otter",
    "model": "dall-e-3",
    "n": 1
  }'

使用虚拟密钥的示例请求：

curl "https://api.portkey.ai/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: openai-virtual-key" \
  -d '{
    "prompt": "A cute baby sea otter",
    "model": "dall-e-3",
    "n": 1
  }'

使用配置的示例请求：

curl "https://api.portkey.ai/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-config: config-key" \
  -d '{
    "prompt": "A cute baby sea otter",
    "model": "dall-e-3",
    "n": 1
  }'

您可以在 Portkey 请求中发送 3 个其他头部

• x-portkey-trace-id: 发送追踪 ID

• x-portkey-metadata: 发送自定义元数据

• x-portkey-cache-force-refresh: 强制刷新此请求的缓存

使用这 3 个的示例请求：

curl "https://api.portkey.ai/v1/images/generations" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-config: config-key" \
  -H "x-portkey-trace-id: $UNIQUE_TRACE_ID" \
  -H "x-portkey-metadata: {\"_user\":\"john\"}" \
  -H "x-portkey-cache-force-refresh: True" \
  -d '{
    "prompt": "A cute baby sea otter",
    "model": "dall-e-3",
    "n": 1
  }'

响应格式

响应将符合 Portkey API 的图像生成对象架构，通常包括基于提示和所选模型生成的图像。

---

参考：

使用 OpenAI 进行图像生成