langchain.js
    Preparing search index...

    Interface DallEAPIWrapperParams

    An interface for the Dall-E API Wrapper.

    interface DallEAPIWrapperParams {
        apiKey?: string;
        baseUrl?: string;
        dallEResponseFormat?: "url" | "b64_json";
        model?: OpenAIImageModelId;
        modelName?: OpenAIImageModelId;
        n?: number;
        openAIApiKey?: string;
        organization?: string;
        quality?: "standard" | "hd";
        responseFormat?: any;
        size?: "256x256" | "512x512" | "1024x1024" | "1792x1024" | "1024x1792";
        style?: "natural" | "vivid";
        user?: string;
    }

    Hierarchy (View Summary)

    Index

    Properties

    apiKey?: string

    The OpenAI API key

    baseUrl?: string

    The base URL of the OpenAI API.

    dallEResponseFormat?: "url" | "b64_json"

    The format in which the generated images are returned. Must be one of "url" or "b64_json".

    "url"
    

    The model to use.

    "dall-e-2" | "dall-e-3"

    "dall-e-3"
    
    modelName?: OpenAIImageModelId

    The model to use. Alias for model

    "dall-e-2" | "dall-e-3"

    "dall-e-3"
    

    Use model instead.

    n?: number

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

    1
    
    openAIApiKey?: string

    The OpenAI API key Alias for apiKey

    organization?: string

    The organization to use

    quality?: "standard" | "hd"

    The quality of the image that will be generated. ‘hd’ creates images with finer details and greater consistency across the image.

    "standard"
    
    responseFormat?: any

    Use dallEResponseFormat instead for the Dall-E response type.

    size?: "256x256" | "512x512" | "1024x1024" | "1792x1024" | "1024x1792"

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

    "1024x1024"
    
    style?: "natural" | "vivid"

    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.

    "vivid"
    
    user?: string

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