Capture & CreateAI-made 3D

Tencent’s WorldClaw Builds an Editable 3D World From One Prompt

AI agents plan the terrain, build separate textured objects, and use Blender to inspect and repair the finished scene.

ShareXFacebookLinkedIn
An isometric WorldClaw scene with mountains, water, buildings, and pink trees beside text describing agentic 3D world generation
WorldClaw turns a written prompt into terrain and separate 3D objects that can be explored and edited.Image: Tencent Hunyuan3D

Tencent’s Hunyuan3D team has introduced WorldClaw (opens in a new tab), a research workflow that builds a large 3D world from one written prompt.

The result is a collection of editable parts. A creator can move one building, replace a tree, or reshape the ground instead of rebuilding the whole scene.

It plans the world before it builds

WorldClaw first turns the prompt into a plan for the regions, terrain, objects, materials, and their positions. That shared plan keeps the later steps working on one connected world.

Next, it draws a color-coded map and turns it into one continuous height field. The height field controls how high or low the ground sits, helping mountains, rivers, and plains meet without visible breaks.

The system spreads rocks, plants, and materials across the land. AI agents then render the scene in Blender, inspect the result, and adjust rough terrain, misplaced objects, textures, and lighting.

Every object stays editable

When a region needs a village, vehicle, or dock, WorldClaw makes a flat reference image over the existing terrain. It cuts each object out and rebuilds it as a separate textured 3D mesh.

Because each object keeps its own shape, position, scale, and texture, a creator can change one part without touching the land around it.

Another inspection checks for objects that float, sink, lean, or arrive at the wrong size. WorldClaw can move the object and reshape the small patch of ground beneath it before checking again.

Tencent shows 11 generated worlds, including a pirate island, river canyon, volcanic lair, and snowy village. Its paper compares rendered views with five other methods, but does not include measured speed, cost, or a user study.

It is a workflow, not a finished game

WorldClaw creates 3D assets for a game workflow. It does not add the navigation, physics, or interactions that make a world playable. Tencent lists game-engine integration as future work.

The research setup is also demanding. Tencent used Blender 5.1.1 on a server with four NVIDIA H20 GPUs, along with several AI models. The paper says each added object and repair round increases the time and cost.

There is no public WorldClaw app yet. Its GitHub repository currently holds the paper and visual assets, not the code needed to run it.

A runnable release and game-engine handoff would show whether one sentence can become a world that creators can keep shaping.

More from Capture & Create.

Browse all stories
The Scenery logo rendered as a luminous Gaussian splat against a blue background

Gaussian splats · 2 min read

Scenery Is Adding Gaussian Splats to Its App Across Apple Platforms

Scenery says the feature will arrive with the public releases of iOS 27, macOS 27, and visionOS 27. Scripts can update hundreds of thousands of splats per frame.

A hand holds a smartphone as a modern room changes from a real scene into a blue Gaussian-splat reconstruction

3D scanning · 2 min read

XGRIDS Turns Your iPhone Into a 3D Spatial Camera

The LCC Scan app builds explorable 3D scenes right on your iPhone, without a cloud upload or server queue.

A performer recorded by multiple cameras for World Labs’ Atlas dynamic 3D capture demonstration

World models · 3 min read

World Labs’ Atlas Combines World Creation, Capture, and Simulation

One model generates camera-controlled video, reconstructs explorable 3D scenes, and reframes motion captured with as few as three cameras.

Preparing the Spatial Insider studio