Generate

Creates an image given a prompt

client.images.generate(, ?): ImageGenerateResponse { created, data, background, 4 more } | Stream<ImageGenStreamEvent>

post/images/generations

Creates a high-quality image from a text prompt using GPT-IMAGE-1, the latest image generation model with automatic prompt optimization and enhanced visual capabilities.

ParametersExpand Collapse

ImageGenerateParams = ImageGenerateParamsNonStreaming { stream } | ImageGenerateParamsStreaming { stream }

ImageGenerateParamsBase { prompt, background, model, 9 more }

prompt: string

A text description of the desired image(s). GPT-IMAGE-1 supports up to 32,000 characters and provides automatic prompt optimization for best results.

minLength1

background?: string | null

The background setting for the image generation. GPT-IMAGE-1 supports: transparent, opaque, auto.

model?: string

The model to use for image generation. GPT-IMAGE-1 is the latest model offering the best quality with automatic optimization and enhanced capabilities.

moderation?: string | null

The moderation setting for the image generation. GPT-IMAGE-1 supports: low, auto.

n?: number | null

The number of images to generate. GPT-IMAGE-1 only supports n=1.

minimum1

output_compression?: number | null

The output compression for the image generation. GPT-IMAGE-1 supports: 0-100.

minimum0

output_format?: string | null

The output format for the image generation. GPT-IMAGE-1 supports: png, webp, jpeg.

partial_images?: number | null

The number of partial image chunks to return during streaming generation. This parameter is optional with a default of 0. When stream=true, this must be greater than 0 to receive progressive updates of the image as it's being generated. Higher values provide more frequent updates but may increase response overhead.

minimum0

quality?: string | null

The quality of the image that will be generated. GPT-IMAGE-1 supports: auto (automatically select best quality), high, medium, low.

size?: string | null

The size of the generated images. GPT-IMAGE-1 supports: auto (automatically select best size), 1536x1024 (landscape), 1024x1536 (portrait).

stream?: false | null

If set to true, partial image data will be streamed as the image is being generated. When streaming, the response will be sent as server-sent events with partial image chunks. When stream is true, partial_images must be greater than 0.

Accepts one of the following:

false

user?: string | null

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

maxLength256

ImageGenerateParamsNonStreaming extends ImageGenerateParamsBase { prompt, background, model, 9 more } { stream }

stream?: false | null

Accepts one of the following:

false

ImageGenerateParamsNonStreaming extends ImageGenerateParamsBase { prompt, background, model, 9 more } { stream }

stream?: false | null

Accepts one of the following:

false

ReturnsExpand Collapse

ImageGenerateResponse { created, data, background, 4 more }

The response from the image generation endpoint

created: number

The Unix timestamp (in seconds) of when the images were created

data: Array<Data>

The list of generated images

b64_json: string

The base64-encoded JSON of the generated image. GPT-IMAGE-1 returns images in b64_json format only.

revised_prompt?: string

The optimized prompt that was used to generate the image. GPT-IMAGE-1 automatically optimizes prompts for best results.

background?: string | null

The background setting used for the image generation

output_format?: string | null

The output format of the generated image

quality?: string | null

The quality setting used for the image generation

size?: string | null

The size of the generated image

usage?: Usage | null

Usage statistics for the image generation request

input_tokens: number

Number of tokens in the input prompt

total_tokens: number

Total number of tokens used (input + output)

input_tokens_details?: InputTokensDetails | null

Detailed breakdown of input tokens

text_tokens?: number

Number of text tokens in the input

output_tokens?: number

Number of tokens in the generated output

Creates an image given a prompt

import Gradient from '@digitalocean/gradient';

const client = new Gradient({
  accessToken: 'My Access Token',
});

const response = await client.images.generate({
  prompt: 'A cute baby sea otter floating on its back in calm blue water',
});

console.log(response.created);

{
  "created": 1677649456,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAQAAAAEAAQMAAABmvDolAAAAA1BMVEX...",
      "revised_prompt": "A cute baby sea otter floating on its back in calm blue water, captured with professional photography lighting and composition"
    }
  ],
  "background": "opaque",
  "output_format": "png",
  "quality": "high",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 12,
    "total_tokens": 4172,
    "input_tokens_details": {
      "text_tokens": 12
    },
    "output_tokens": 4160
  }
}

Returns Examples

{
  "created": 1677649456,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAQAAAAEAAQMAAABmvDolAAAAA1BMVEX...",
      "revised_prompt": "A cute baby sea otter floating on its back in calm blue water, captured with professional photography lighting and composition"
    }
  ],
  "background": "opaque",
  "output_format": "png",
  "quality": "high",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 12,
    "total_tokens": 4172,
    "input_tokens_details": {
      "text_tokens": 12
    },
    "output_tokens": 4160
  }
}