@leonardo-ai/sdk
v4.21.1
Published
<div align="center"> <img src="https://user-images.githubusercontent.com/6267663/230025738-42a4980e-a5ea-4d00-a591-65e8de14de85.png" width="200"> <h1>Leonardo Typescript SDK</h1> <p>The API for creating stunning game assets with AI.</p> <a hre
Readme
Summary
Rest Endpoints: Leonardo.Ai API OpenAPI specification.
Table of Contents
- SDK Installation
- Authentication
- SDK Example Usage
- Available Resources and Operations
- Error Handling
- Custom HTTP Client
- Server Selection
- Authentication
- Requirements
- Standalone functions
- Retries
- Debugging
SDK Installation
The SDK can be installed with either npm, pnpm, bun or yarn package managers.
NPM
npm add @leonardo-ai/sdkPNPM
pnpm add @leonardo-ai/sdkBun
bun add @leonardo-ai/sdkYarn
yarn add @leonardo-ai/sdkAuthentication
To get access to the API and fetch an API key, please sign up for access.
SDK Example Usage
Example
import { Leonardo } from "@leonardo-ai/sdk";
import { SettingName } from "@leonardo-ai/sdk/sdk/models/shared";
const leonardo = new Leonardo({
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await leonardo.blueprints.executeBlueprint({
blueprintVersionId: "550e8400-e29b-41d4-a716-446655440000",
input: {
collectionIds: [],
nodeInputs: [
{
nodeId: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
settingName: SettingName.Text,
value: "A futuristic cityscape at sunset",
},
{
nodeId: "b2c3d4e5-f6a7-8901-bcde-f12345678901",
settingName: SettingName.TextVariables,
value: [
{
name: "characterName",
value: "Luna",
},
{
name: "outfit",
value: "cyberpunk armor",
},
],
},
{
nodeId: "c3d4e5f6-a7b8-9012-cdef-123456789012",
settingName: SettingName.ImageUrl,
value: "https://cdn.leonardo.ai/users/example/image.png",
},
],
public: false,
},
});
console.log(result);
}
run();
Available Resources and Operations
ThreeDModelAssets
- delete3DModelById - Delete 3D Model by ID
- uploadModelAsset - Upload 3D Model
Blueprints
- executeBlueprint - Execute a Blueprint
- getBlueprintById - Get Blueprint by ID
- getBlueprintExecution - Get Blueprint Execution by ID
- getBlueprintExecutionGenerations - Get Blueprint Execution Generations by Execution ID
- getBlueprintVersionsByBlueprintId - Get Blueprint Versions by Blueprint ID
Dataset
- createDataset - Create a Dataset
- deleteDatasetById - Delete a Single Dataset by ID
- getDatasetById - Get a Single Dataset by ID
- uploadDatasetImage - Upload dataset image
- uploadDatasetImageFromGen - Upload a Single Generated Image to a Dataset
Elements
- createElement - Train a Custom Element
- deleteElementById - Delete a Single Custom Element by ID
- getCustomElementsByUserId - Get a list of Custom Elements by User ID
- getElementById - Get a Single Custom Element by ID
- listElements - List Elements
Image
- createGeneration - Create a Generation of Images
- deleteGenerationById - Delete a Single Generation
- getGenerationById - Get a Single Generation
- getGenerationsByUserId - Get generations by user ID
InitImages
- deleteInitImageById - Delete init image
- getInitImageById - Get single init image
- uploadCanvasInitImage - Upload Canvas Editor init and mask image
- uploadInitImage - Upload init image
Models
- createModel - Train a Custom Model
- deleteModelById - Delete a Single Custom Model by ID
- getCustomModelsByUserId - Get a list of Custom Models by User ID
- getModelById - Get a Single Custom Model by ID
- listPlatformModels - List Platform Models
Motion
- createImageToVideoGeneration - Create a video generation from an image
- createSVDMotionGeneration - Create SVD Motion Generation
- createTextToVideoGeneration - Create a video generation from a text prompt
- createVideoUpscale - Upscale a generated video
PricingCalculator
- pricingCalculator - Calculating API Cost
Prompt
- promptImprove - Improve a Prompt
- promptRandom - Generate a Random prompt
RealtimeCanvas
- createLCMGeneration - Create LCM Generation
- performAlchemyUpscaleLCM - Perform Alchemy Upscale on a LCM image
- performInpaintingLCM - Perform inpainting on a LCM image
- performInstantRefine - Perform instant refine on a LCM image
Texture
- createTextureGeneration - Create Texture Generation
- deleteTextureGenerationById - Delete Texture Generation by ID
User
- getUserSelf - Get user information
Variation
- createUniversalUpscalerJob - Create using Universal Upscaler
- createVariationNoBG - Create no background
- createVariationUnzoom - Create unzoom
- createVariationUpscale - Create upscale
- getMotionVariationById - Get motion variation by ID
- getVariationById - Get variation by ID
Error Handling
LeonardoError is the base class for all HTTP error responses. It has the following properties:
| Property | Type | Description |
| ------------------- | ---------- | ------------------------------------------------------ |
| error.message | string | Error message |
| error.statusCode | number | HTTP response status code eg 404 |
| error.headers | Headers | HTTP response headers |
| error.body | string | HTTP body. Can be empty string if no body is returned. |
| error.rawResponse | Response | Raw HTTP response |
Example
import { Leonardo } from "@leonardo-ai/sdk";
import * as errors from "@leonardo-ai/sdk/sdk/models/errors";
import { SettingName } from "@leonardo-ai/sdk/sdk/models/shared";
const leonardo = new Leonardo({
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
try {
const result = await leonardo.blueprints.executeBlueprint({
blueprintVersionId: "550e8400-e29b-41d4-a716-446655440000",
input: {
collectionIds: [],
nodeInputs: [
{
nodeId: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
settingName: SettingName.Text,
value: "A futuristic cityscape at sunset",
},
{
nodeId: "b2c3d4e5-f6a7-8901-bcde-f12345678901",
settingName: SettingName.TextVariables,
value: [
{
name: "characterName",
value: "Luna",
},
{
name: "outfit",
value: "cyberpunk armor",
},
],
},
{
nodeId: "c3d4e5f6-a7b8-9012-cdef-123456789012",
settingName: SettingName.ImageUrl,
value: "https://cdn.leonardo.ai/users/example/image.png",
},
],
public: false,
},
});
console.log(result);
} catch (error) {
if (error instanceof errors.LeonardoError) {
console.log(error.message);
console.log(error.statusCode);
console.log(error.body);
console.log(error.headers);
}
}
}
run();
Error Classes
Primary error:
LeonardoError: The base class for HTTP error responses.
Network errors:
ConnectionError: HTTP client was unable to make a request to a server.RequestTimeoutError: HTTP request timed out due to an AbortSignal signal.RequestAbortedError: HTTP request was aborted by the client.InvalidRequestError: Any input used to create a request is invalid.UnexpectedClientError: Unrecognised or unexpected error.
Inherit from LeonardoError:
ResponseValidationError: Type mismatch between the data returned from the server and the structure expected by the SDK. Seeerror.rawValuefor the raw value anderror.pretty()for a nicely formatted multi-line string.
Custom HTTP Client
The TypeScript SDK makes API calls using an HTTPClient that wraps the native
Fetch API. This
client is a thin wrapper around fetch and provides the ability to attach hooks
around the request lifecycle that can be used to modify the request or handle
errors and response.
The HTTPClient constructor takes an optional fetcher argument that can be
used to integrate a third-party HTTP client or when writing tests to mock out
the HTTP client and feed in fixtures.
The following example shows how to:
- route requests through a proxy server using undici's ProxyAgent
- use the
"beforeRequest"hook to add a custom header and a timeout to requests - use the
"requestError"hook to log errors
import { Leonardo } from "@leonardo-ai/sdk";
import { ProxyAgent } from "undici";
import { HTTPClient } from "@leonardo-ai/sdk/lib/http";
const dispatcher = new ProxyAgent("http://proxy.example.com:8080");
const httpClient = new HTTPClient({
// 'fetcher' takes a function that has the same signature as native 'fetch'.
fetcher: (input, init) =>
// 'dispatcher' is specific to undici and not part of the standard Fetch API.
fetch(input, { ...init, dispatcher } as RequestInit),
});
httpClient.addHook("beforeRequest", (request) => {
const nextRequest = new Request(request, {
signal: request.signal || AbortSignal.timeout(5000)
});
nextRequest.headers.set("x-custom-header", "custom value");
return nextRequest;
});
httpClient.addHook("requestError", (error, request) => {
console.group("Request Error");
console.log("Reason:", `${error}`);
console.log("Endpoint:", `${request.method} ${request.url}`);
console.groupEnd();
});
const sdk = new Leonardo({ httpClient: httpClient });Server Selection
Override Server URL Per-Client
The default server can be overridden globally by passing a URL to the serverURL: string optional parameter when initializing the SDK client instance. For example:
import { Leonardo } from "@leonardo-ai/sdk";
import { SettingName } from "@leonardo-ai/sdk/sdk/models/shared";
const leonardo = new Leonardo({
serverURL: "https://cloud.leonardo.ai/api/rest/v1",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await leonardo.blueprints.executeBlueprint({
blueprintVersionId: "550e8400-e29b-41d4-a716-446655440000",
input: {
collectionIds: [],
nodeInputs: [
{
nodeId: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
settingName: SettingName.Text,
value: "A futuristic cityscape at sunset",
},
{
nodeId: "b2c3d4e5-f6a7-8901-bcde-f12345678901",
settingName: SettingName.TextVariables,
value: [
{
name: "characterName",
value: "Luna",
},
{
name: "outfit",
value: "cyberpunk armor",
},
],
},
{
nodeId: "c3d4e5f6-a7b8-9012-cdef-123456789012",
settingName: SettingName.ImageUrl,
value: "https://cdn.leonardo.ai/users/example/image.png",
},
],
public: false,
},
});
console.log(result);
}
run();
Authentication
Per-Client Security Schemes
This SDK supports the following security scheme globally:
| Name | Type | Scheme |
| ------------ | ---- | ----------- |
| bearerAuth | http | HTTP Bearer |
To authenticate with the API the bearerAuth parameter must be set when initializing the SDK client instance. For example:
import { Leonardo } from "@leonardo-ai/sdk";
import { SettingName } from "@leonardo-ai/sdk/sdk/models/shared";
const leonardo = new Leonardo({
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await leonardo.blueprints.executeBlueprint({
blueprintVersionId: "550e8400-e29b-41d4-a716-446655440000",
input: {
collectionIds: [],
nodeInputs: [
{
nodeId: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
settingName: SettingName.Text,
value: "A futuristic cityscape at sunset",
},
{
nodeId: "b2c3d4e5-f6a7-8901-bcde-f12345678901",
settingName: SettingName.TextVariables,
value: [
{
name: "characterName",
value: "Luna",
},
{
name: "outfit",
value: "cyberpunk armor",
},
],
},
{
nodeId: "c3d4e5f6-a7b8-9012-cdef-123456789012",
settingName: SettingName.ImageUrl,
value: "https://cdn.leonardo.ai/users/example/image.png",
},
],
public: false,
},
});
console.log(result);
}
run();
Requirements
For supported JavaScript runtimes, please consult RUNTIMES.md.
Standalone functions
All the methods listed above are available as standalone functions. These functions are ideal for use in applications running in the browser, serverless runtimes or other environments where application bundle size is a primary concern. When using a bundler to build your application, all unused functionality will be either excluded from the final bundle or tree-shaken away.
To read more about standalone functions, check FUNCTIONS.md.
blueprintsExecuteBlueprint- Execute a BlueprintblueprintsGetBlueprintById- Get Blueprint by IDblueprintsGetBlueprintExecution- Get Blueprint Execution by IDblueprintsGetBlueprintExecutionGenerations- Get Blueprint Execution Generations by Execution IDblueprintsGetBlueprintVersionsByBlueprintId- Get Blueprint Versions by Blueprint IDdatasetCreateDataset- Create a DatasetdatasetDeleteDatasetById- Delete a Single Dataset by IDdatasetGetDatasetById- Get a Single Dataset by IDdatasetUploadDatasetImage- Upload dataset imagedatasetUploadDatasetImageFromGen- Upload a Single Generated Image to a DatasetelementsCreateElement- Train a Custom ElementelementsDeleteElementById- Delete a Single Custom Element by IDelementsGetCustomElementsByUserId- Get a list of Custom Elements by User IDelementsGetElementById- Get a Single Custom Element by IDelementsListElements- List ElementsimageCreateGeneration- Create a Generation of ImagesimageDeleteGenerationById- Delete a Single GenerationimageGetGenerationById- Get a Single GenerationimageGetGenerationsByUserId- Get generations by user IDinitImagesDeleteInitImageById- Delete init imageinitImagesGetInitImageById- Get single init imageinitImagesUploadCanvasInitImage- Upload Canvas Editor init and mask imageinitImagesUploadInitImage- Upload init imagemodelsCreateModel- Train a Custom ModelmodelsDeleteModelById- Delete a Single Custom Model by IDmodelsGetCustomModelsByUserId- Get a list of Custom Models by User IDmodelsGetModelById- Get a Single Custom Model by IDmodelsListPlatformModels- List Platform ModelsmotionCreateImageToVideoGeneration- Create a video generation from an imagemotionCreateSVDMotionGeneration- Create SVD Motion GenerationmotionCreateTextToVideoGeneration- Create a video generation from a text promptmotionCreateVideoUpscale- Upscale a generated videopricingCalculatorPricingCalculator- Calculating API CostpromptPromptImprove- Improve a PromptpromptPromptRandom- Generate a Random promptrealtimeCanvasCreateLCMGeneration- Create LCM GenerationrealtimeCanvasPerformAlchemyUpscaleLCM- Perform Alchemy Upscale on a LCM imagerealtimeCanvasPerformInpaintingLCM- Perform inpainting on a LCM imagerealtimeCanvasPerformInstantRefine- Perform instant refine on a LCM imagetextureCreateTextureGeneration- Create Texture GenerationtextureDeleteTextureGenerationById- Delete Texture Generation by IDthreeDModelAssetsDelete3DModelById- Delete 3D Model by IDthreeDModelAssetsUploadModelAsset- Upload 3D ModeluserGetUserSelf- Get user informationvariationCreateUniversalUpscalerJob- Create using Universal UpscalervariationCreateVariationNoBG- Create no backgroundvariationCreateVariationUnzoom- Create unzoomvariationCreateVariationUpscale- Create upscalevariationGetMotionVariationById- Get motion variation by IDvariationGetVariationById- Get variation by ID
Retries
Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.
To change the default retry strategy for a single API call, simply provide a retryConfig object to the call:
import { Leonardo } from "@leonardo-ai/sdk";
import { SettingName } from "@leonardo-ai/sdk/sdk/models/shared";
const leonardo = new Leonardo({
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await leonardo.blueprints.executeBlueprint({
blueprintVersionId: "550e8400-e29b-41d4-a716-446655440000",
input: {
collectionIds: [],
nodeInputs: [
{
nodeId: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
settingName: SettingName.Text,
value: "A futuristic cityscape at sunset",
},
{
nodeId: "b2c3d4e5-f6a7-8901-bcde-f12345678901",
settingName: SettingName.TextVariables,
value: [
{
name: "characterName",
value: "Luna",
},
{
name: "outfit",
value: "cyberpunk armor",
},
],
},
{
nodeId: "c3d4e5f6-a7b8-9012-cdef-123456789012",
settingName: SettingName.ImageUrl,
value: "https://cdn.leonardo.ai/users/example/image.png",
},
],
public: false,
},
}, {
retries: {
strategy: "backoff",
backoff: {
initialInterval: 1,
maxInterval: 50,
exponent: 1.1,
maxElapsedTime: 100,
},
retryConnectionErrors: false,
},
});
console.log(result);
}
run();
If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:
import { Leonardo } from "@leonardo-ai/sdk";
import { SettingName } from "@leonardo-ai/sdk/sdk/models/shared";
const leonardo = new Leonardo({
retryConfig: {
strategy: "backoff",
backoff: {
initialInterval: 1,
maxInterval: 50,
exponent: 1.1,
maxElapsedTime: 100,
},
retryConnectionErrors: false,
},
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await leonardo.blueprints.executeBlueprint({
blueprintVersionId: "550e8400-e29b-41d4-a716-446655440000",
input: {
collectionIds: [],
nodeInputs: [
{
nodeId: "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
settingName: SettingName.Text,
value: "A futuristic cityscape at sunset",
},
{
nodeId: "b2c3d4e5-f6a7-8901-bcde-f12345678901",
settingName: SettingName.TextVariables,
value: [
{
name: "characterName",
value: "Luna",
},
{
name: "outfit",
value: "cyberpunk armor",
},
],
},
{
nodeId: "c3d4e5f6-a7b8-9012-cdef-123456789012",
settingName: SettingName.ImageUrl,
value: "https://cdn.leonardo.ai/users/example/image.png",
},
],
public: false,
},
});
console.log(result);
}
run();
Debugging
You can setup your SDK to emit debug logs for SDK requests and responses.
You can pass a logger that matches console's interface as an SDK option.
[!WARNING] Beware that debug logging will reveal secrets, like API tokens in headers, in log messages printed to a console or files. It's recommended to use this feature only during local development and not in production.
import { Leonardo } from "@leonardo-ai/sdk";
const sdk = new Leonardo({ debugLogger: console });