one dataset · paper, tables, graph, wiki
simgrammar the grammar of simulation

mechanism

An image or video diffusion model generates views of a scene (a 360-degree panorama in HunyuanWorld, multi-view images in Marble) from the prompt; the views are lifted to an explicit 3D representation (3D Gaussian splats, or a semantically layered mesh) that can be walked through and re-rendered without regeneration. Marble also emits triangle meshes and coarse collider meshes for physics, can expand or merge worlds, and in Chisel mode takes a blockout of boxes and planes as structure and a text prompt as style. A parallel line renders frames directly instead of building geometry: RTFM keeps generated frames with camera poses as spatial memory and retrieves nearby frames as context. Atlas (2026) is a multimodal model that outputs video, point clouds, and splats.

limitations

  • Scenes are static: no dynamic objects, agents, or rules are generated, and RTFM lists dynamics and interaction as future work.
  • Single-image or text prompts force the model to invent unseen regions; Marble notes artifacts and less crisp far regions that expansion may fix.
  • Splat output bakes lighting into colors, so day-night cycles and relighting need conversion to meshes or other methods.
  • Collider meshes are coarse and need manual work for gameplay-critical collision.
  • Corporate change (World Labs joining AMD in 2026) leaves the hosted product's future terms uncertain.

relations

5 stored edges
affects

Procedural build assist

Chisel turns a coarse blockout into a detailed styled scene, the same rough-input to detailed-output contract as Townscaper-style build assist but with a learned generator; today it is an editor mode, not a runtime player tool.

Enables new form
affects

Procedural terrain

Maps come from a prompt, photo, or video rather than a seed and noise pipeline, and unlike frame-based world models the result is baked geometry that persists, can be saved, and can be expanded region by region.

Enables new form
affects

Rigid-body physics

Exported collider meshes give generated scenes collision geometry automatically; Marble describes them as coarse, so precise physics still needs cleanup.

Cuts authoring cost
affects

Scenario objectives

Bespoke scenario maps can be produced from a reference image or description and exported with collider meshes, reducing hand modeling per scenario; objectives and rules still need authoring.

Cuts authoring cost

claims

4 with sources
c01high

Marble became generally available on 2025-11-12, taking text, images, video, or coarse 3D layouts and exporting Gaussian splats, triangle meshes including collider meshes for coarse physics, and rendered video; Chisel separates blocked-out structure from prompted style.

src-worldlabs-2025-marble

c02high

HunyuanWorld 1.0 (Tencent, July 2025) generates explorable worlds from text or images via panoramic proxies converted to a semantically layered 3D mesh exportable to standard graphics pipelines, listing game development as an application.

src-tencent-2025-hunyuanworld-1

c03high

RTFM (October 2025) renders generated or real scenes from a single image at interactive frame rates on one H100, using posed frames as spatial memory; it models static scenes only.

src-worldlabs-2025-rtfm

c04medium

World Labs launched a public World API in January 2026, released Atlas to early-access partners in September 2026, and announced it is joining AMD on 2026-09-28.

src-worldlabs-2026-blog, src-worldlabs-2026-atlas

sources

5

provenance

runs in log/runs
2026-10-24
created2026-10-24-techniques-world-modelstechnique