---
title: "Lyra"
description: "Lyra from NVIDIA: open generative 3D and 4D world models; Verified; 2 variants."
modelId: "lyra"
pageSource: authored
---

Lyra is NVIDIA's generative world model family for exploration: from an image or video (Lyra-1) or from actions (Lyra-2) it produces an explorable world video. In this catalog both variants run through in-tree pipelines backed by vendored runtime adapters, the default runner targets Lyra-2, and runner status is Verified.

<ModelPaperFigures modelId="lyra" locale="en" />

Project page: [research.nvidia.com/labs/sil/projects/lyra2](https://research.nvidia.com/labs/sil/projects/lyra2/). Code: [nv-tlabs/lyra](https://github.com/nv-tlabs/lyra).

The paper is [Paper](https://openreview.net/forum?id=tIVCfVnIHo). Project page: [research.nvidia.com/labs/sil/projects/lyra2](https://research.nvidia.com/labs/sil/projects/lyra2). Code: [nv-tlabs/lyra](https://github.com/nv-tlabs/lyra).

<ModelCommandBuilder modelId="lyra" locale="en" />

## What it is for

Use `lyra-1` for catalog world-model inference. Choose it when you need action-conditioned future frames rather than a standalone clip generator.

The catalog records two generations: Lyra-1 for image-or-video-to-world-video and Lyra-2 for action-conditioned world video (paper on OpenReview; project page at NVIDIA Research). Runtime execution requires local Lyra checkpoints, text-encoder assets, DA3 (Depth Anything 3) assets, and CUDA dependencies; internals beyond the recorded structure are not stored in this repository.

Catalog tasks include open generative 3D and 4D world models. Catalog aliases include `Project Lyra`, `Lyra 1.0`, and `Lyra 2.0`. Also recorded: `lyra-2`.

Recorded evaluation entry points include [WorldScore](/docs/evaluation/benchmark-hub/worldscore) (Standard scoring for explorable generated worlds), [CameraBench](/docs/evaluation/benchmark-hub/camerabench) (Evaluates camera/viewpoint control quality during exploration).

## Runtime contract

Optional `image`, `prompt`, `mode`, `trajectory`, and `camera_rotation`; artifacts `generated_world`, `generated_3d_asset`, and `lyra-1.mp4`.

CLI task profiles: `official-static-sdg` and `official-zoomgs`. WorldFoundry binds `LyraPipeline`.

Start on `lyra-1`. The family registers 2 catalog variants (cards above): `lyra-1` (`image-or-video-to-world-video`) — Runner parity pending; `lyra-2` (`action-conditioned-world-video`) — Runner parity pending. Family status: **Verified**.

Recorded `official-zoomgs` defaults: fps=16, seed=1.

Pick the variant by input: lyra-1 when you start from an image or video, lyra-2 when you drive the world with actions. The default catalog runner resolves to Lyra-2.

## Running in WorldFoundry

Launch `worldfoundry-eval run lyra-1 --pipeline.task-profile official-static-sdg` to step the world. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

Recorded weight repositories include `depth-anything/DA3NESTED-GIANT-LARGE-1.1`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh lyra-1`. Add `--download` to fetch missing public checkpoints.

Status: **Verified**.

<ModelRelatedRecipes modelId="lyra" locale="en" />