MotionDiffusionModel<T>

Models & Types · AiDotNet.Diffusion.MotionGeneration

Motion Diffusion Model (MDM) for text-to-motion generation of human body movements.

Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → MotionDiffusionModel<T>

For Beginners

MDM generates 3D human body animations from text. Describe a motion like “a person doing a jumping jack” and MDM produces the corresponding body movement animation with realistic joint rotations and timing.

How It Works

MDM generates human motion sequences from text descriptions using a transformer-based diffusion model. It operates in joint rotation space, producing temporally coherent body animations that match the text description.

Reference: Tevet et al., “Human Motion Diffusion Model”, ICLR 2023

Example

var options = new DiffusionModelOptions<float> { LatentChannels = 263, DefaultInferenceSteps = 50 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 263, 196 });
var trainX = Tensor<float>.CreateRandom(4, 8);
var trainY = Tensor<float>.CreateRandom(4, 2);
var result = new AiModelBuilder<float, Tensor<float>, Tensor<float>>()
    .ConfigureModel(new MotionDiffusionModel<float>(options: options))
    .Build(trainX, trainY);
var motion = result.Predict(noise);

Constructors

Constructor Summary
MotionDiffusionModel(NeuralNetworkArchitecture<T> architecture, DiffusionModelOptions<T> options, INoiseScheduler<T> scheduler, SiTPredictor<T> predictor, StandardVAE<T> vae, IConditioningModule<T> conditioner, int? seed)

Properties

Property Summary
IConditioningModule<T> Conditioner { get; }
INoisePredictor<T> NoisePredictor { get; }
IVAEModel<T> VAE { get; }
int LatentChannels { get; }

Methods

Method Summary
ModelMetadata<T> GetModelMetadata()