Get started

Web quickstart

Start a TypeScript project, pose an image, and generate a new view.

Turn a photo into a new viewpoint with Atlas. Run this on your server with Node.js 24 and a Developer API key.

For CLI setup and agent skill installation, see CLI.

Read How To Use Atlas before choosing model inputs or combining tasks. For coordinate calculations, use Cameras and posed images.

To opt out of model training on your inputs, the account owner can open Settings → Account and turn off Use my data to improve models for the relevant account. This setting covers both Studio and Developer API projects in that account.

1. Install

Install the latest tag of the public TypeScript client.

mkdir atlas-demo && cd atlas-demonpm init -ynpm pkg set type=modulenpm install @worldlabsai/client@latest

Create .env with WLT_API_KEY=your_key_here and add .env to .gitignore.

2. Generate a view

Save as generate.ts. The sample photo of a torii gate is by Daniel Erlandson on Pexels.

1import { createClient } from "@worldlabsai/client";23const apiKey = process.env.WLT_API_KEY;4if (!apiKey) throw new Error("Set WLT_API_KEY in .env");5const wl = createClient({ apiKey });6const signal = AbortSignal.timeout(300_000);7const imageUrl =8  "https://images.pexels.com/photos/31252468/pexels-photo-31252468.jpeg?auto=compress&cs=tinysrgb&w=1280";910const posing = await wl.tasks.images2PosedRGBD(11  { frames: [{ imageAsset: { url: imageUrl } }], targetResolution: [1280, 720] },12  { signal },13);14const posed = await wl.operations.wait(posing, { signal });15if (posed.error) throw new Error(posed.error.message ?? "Posing failed");16const context = posed.response?.frames[0];17if (!context) throw new Error("Posing returned no frame");1819const { imageAsset, camera, depth } = context;20const target = structuredClone(camera);21target.extrinsics.position[0] += 0.25;22const generation = await wl.tasks.atlasGenerate(23  {24    contextFrames: [{ imageAsset, camera, depth }],25    targetCameras: [target],26    prompt: "The same scene from a nearby viewpoint",27  },28  { signal },29);30const generated = await wl.operations.wait(generation, { signal });31if (generated.error) throw new Error(generated.error.message ?? "Generation failed");32const outputUrl = generated.response?.frames?.[0]?.imageAsset.url;33if (!outputUrl) throw new Error("Atlas returned no image URL");34console.log(outputUrl);

3. See the result

node --env-file=.env generate.ts

Open the printed URL to see the generated image. The camera moves 0.25 metres along world X in the estimated scene. Metric scale is predicted, so physical distances are approximate.

For a web app, run generation in a backend job and return its status to the browser. Save operation IDs to resume polling and reuse an idempotency key for retries of the same submission. A timeout stops local waiting; it does not cancel the server task. See How To Use Atlas for camera controls and depth output.

For CPU processing of depth with Three.js, apply the EXR row mapping before unprojecting or matching image pixels.