FashionVDMModel<T>

Models & Types · AiDotNet.Diffusion.VirtualTryOn

FashionVDM model for video-based virtual try-on with temporal consistency.

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

For Beginners

FashionVDM shows how clothes look in motion — not just a single photo, but a video of someone walking, turning, or posing while wearing the garment. The clothes look consistent and realistic throughout the entire video.

How It Works

FashionVDM extends virtual try-on to video by incorporating temporal attention layers that ensure garment appearance remains consistent across frames while adapting to body movement. Uses a video diffusion model backbone for frame-to-frame coherence.

Example

var options = new DiffusionModelOptions<float> { LatentChannels = 4, DefaultInferenceSteps = 30 };
var input = Tensor<float>.CreateRandom(new[] { 1, 4, 64, 48 });
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 FashionVDMModel<float>(options: options))
    .Build(trainX, trainY);
var tryOnVideo = result.Predict(input);

Constructors

Constructor Summary
FashionVDMModel(NeuralNetworkArchitecture<T> architecture, DiffusionModelOptions<T> options, INoiseScheduler<T> scheduler, UNetNoisePredictor<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()