Interface EditImageConfig

Configuration for editing an image.

interface EditImageConfig {
    abortSignal?: AbortSignal;
    addWatermark?: boolean;
    aspectRatio?: string;
    baseSteps?: number;
    editMode?: EditMode;
    guidanceScale?: number;
    httpOptions?: HttpOptions;
    includeRaiReason?: boolean;
    includeSafetyAttributes?: boolean;
    labels?: Record<string, string>;
    language?: ImagePromptLanguage;
    negativePrompt?: string;
    numberOfImages?: number;
    outputCompressionQuality?: number;
    outputGcsUri?: string;
    outputMimeType?: string;
    personGeneration?: PersonGeneration;
    safetyFilterLevel?: SafetyFilterLevel;
    seed?: number;
}

Properties

abortSignal? addWatermark? aspectRatio? baseSteps? editMode? guidanceScale? httpOptions? includeRaiReason? includeSafetyAttributes? labels? language? negativePrompt? numberOfImages? outputCompressionQuality? outputGcsUri? outputMimeType? personGeneration? safetyFilterLevel? seed?

Properties

OptionalabortSignal

abortSignal?: AbortSignal

Abort signal which can be used to cancel the request.

NOTE: AbortSignal is a client-only operation. Using it to cancel an operation will not cancel the request in the service. You will still be charged usage for any applicable operations.

OptionaladdWatermark

addWatermark?: boolean

Whether to add a watermark to the generated images.

OptionalaspectRatio

aspectRatio?: string

Aspect ratio of the generated images. Supported values are "1:1", "3:4", "4:3", "9:16", and "16:9".

OptionalbaseSteps

baseSteps?: number

The number of sampling steps. A higher value has better image quality, while a lower value has better latency.

OptionaleditMode

editMode?: EditMode

Describes the editing mode for the request.

OptionalguidanceScale

guidanceScale?: number

Controls how much the model adheres to the text prompt. Large values increase output and prompt alignment, but may compromise image quality.

OptionalhttpOptions

httpOptions?: HttpOptions

Used to override HTTP request options.

OptionalincludeRaiReason

includeRaiReason?: boolean

Whether to include the Responsible AI filter reason if the image is filtered out of the response.

OptionalincludeSafetyAttributes

includeSafetyAttributes?: boolean

Whether to report the safety scores of each generated image and the positive prompt in the response.

Optionallabels

labels?: Record<string, string>

User specified labels to track billing usage.

Optionallanguage

language?: ImagePromptLanguage

Language of the text in the prompt.

OptionalnegativePrompt

negativePrompt?: string

Description of what to discourage in the generated images.

OptionalnumberOfImages

numberOfImages?: number

Number of images to generate.

OptionaloutputCompressionQuality

outputCompressionQuality?: number

Compression quality of the generated image (for image/jpeg only).

OptionaloutputGcsUri

outputGcsUri?: string

Cloud Storage URI used to store the generated images.

OptionaloutputMimeType

outputMimeType?: string

MIME type of the generated image.

OptionalpersonGeneration

personGeneration?: PersonGeneration

Allows generation of people by the model.

OptionalsafetyFilterLevel

safetyFilterLevel?: SafetyFilterLevel

Filter level for safety filtering.

Optionalseed

seed?: number

Random seed for image generation. This is not available when add_watermark is set to true.

Settings

On This Page

Properties