World models for creators: 3D scene asset vs interactive experience — when to use RTFM vs when to use Genie 3

3 sources

World Labs RTFM and DeepMind Genie 3 are two world model surfaces that map to two different creator use cases. RTFM produces a 3D scene asset from a single image — the asset can be exported into a 3D pipeline (Blender / Unity / Unreal), used as a still scene, or embedded into a video. Genie 3 produces an interactive experience — the user navigates the generated environment in real time, with the experience living in the Genie runtime rather than as an exportable asset. Creators pick between them based on the use case: exportable 3D asset → RTFM, interactive experience → Genie 3.

Why now

Both shipped in the same week — creators can now pick between an exportable 3D asset (RTFM) and an interactive experience (Genie 3) for their world model needs.

Why it is worth publishing

Demo potential: same scene as RTFM-exported asset vs Genie 3 interactive experience, comparing export vs interaction.

Evidence basis

Two independent vendor primary sources + The Decoder weekly roundup

“World Labs RTFM and DeepMind Genie 3 both shipped this week — and they map to two different creator use cases: exportable 3D asset (RTFM) vs interactive experience (Genie 3).”

Angle

Frame the two as 'exportable 3D asset vs interactive experience' — pick based on whether the creator needs an exportable asset (RTFM) or a runtime experience (Genie 3).

Format

Short talking-head video

Demo idea

Record a 6-minute explainer: 2 min intro on 'exportable vs interactive' framing, 2 min on RTFM (exportable 3D asset), 2 min on Genie 3 (interactive experience).

Platform notes

Specific asset export format and Genie 3 interaction model details beyond the captured summary are not extracted; confirm specific surface details against the underlying vendor docs before stating them on the record.

Usable claims

World Labs shipped RTFM — real-time feed-forward 3D world model that generates 3D scenes from a single image without per-scene optimization.
Google DeepMind shipped Genie 3 GA — interactive world model that lets a user navigate and interact with a generated environment in real time.

Evidence pipeline

From the news

Breakdown

RTFM produces an exportable 3D scene asset; Genie 3 produces an interactive experience. This explainer uses the asset-vs-experience framing as the lens for picking a world model, rather than treating 'world model' as a single category.

Sources

Risks

Use The Decoder and IT之家 as media-type corroboration, but read the underlying vendor docs for any specific capability or benchmark claim before stating it on the record. Verify specific capability claim against the underlying vendor docs and the actual license / pricing matrix before stating it on the record; do not paraphrase per-platform pricing or license terms into specific dollar figures or commercial-use clauses.
Vendor docs confirm real-time / interactive capability but specific latency targets beyond the captured summary are not in this pass. Verify specific capability claim against the underlying vendor docs and the actual license / pricing matrix before stating it on the record; do not paraphrase per-platform pricing or license terms into specific dollar figures or commercial-use clauses.

Demo ideas

Side-by-side: same scene as RTFM-exported 3D asset vs Genie 3 interactive experience.
Workflow decision: 'which world model for which creator use case' (exportable asset → RTFM, interactive experience → Genie 3).
Pipeline integration: 'RTFM-generated 3D scene imported into Blender + Genie 3 interactive runtime', measure workflow delta.