Telekinesis Agentic Skill Library

Appearance

Randomizer Nodes ​

Each randomizer node changes one aspect of the scene. A node receives the Context when the tree executes and mutates it in place. Nodes are appended to a Randomizer in the order they should run: instances first, then poses, then appearance, then the camera.

Import ​

python
from telekinesis.illusion.randomizer.randomizer_node import (
    RandomizerNode,
    ObjectInstanceRandomizer,
    ObjectPoseRandomizer,
    MaterialRandomizer,
    BackgroundRandomizer,
    CameraPoseRandomizer,
)

target_objects is matched by prefix throughout, so passing "part_1" selects every instance registered under that name.

Nodes ​

Composition

ObjectInstanceRandomizer

Samples how many instances of each model are visible in the scene, and reveals them.

View →
Pose

ObjectPoseRandomizer

Samples 6-DoF poses for the visible target objects, rejecting poses that collide.

View →
Appearance

MaterialRandomizer

Assigns a random material to each target object, sampled from the requested material types.

View →
Appearance

BackgroundRandomizer

Samples an HDRI background, which also drives the scene lighting.

View →
Camera

CameraPoseRandomizer

Samples one camera pose per view, so a single randomized scene yields several images.

View →
Extend

Custom Nodes

Add any other axis of variation by subclassing RandomizerNode and implementing randomize().

View →

Next Steps ​

Workers

Drive a complete, sharded dataset run from a spec YAML instead of assembling the tree in Python.

Explore →

Flying Things

Build a randomizer tree with one node per axis of variation and render a labeled COCO dataset.

Open tutorial →