SpotDiffusionModel<T>

Models & Types · AiDotNet.Diffusion.Panorama

SpotDiffusion model for spatially-organized text-guided panorama generation.

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

For Beginners

SpotDiffusion lets you create panoramas where different parts show different things — like a beach on the left transitioning to mountains on the right. You describe each section separately and it blends them smoothly.

How It Works

SpotDiffusion enables spatial layout control in panoramic generation by assigning different text prompts to different spatial regions. Each region is independently guided while seamless blending is maintained in overlap zones.

Example

var options = new DiffusionModelOptions<float> { LatentChannels = 4, DefaultInferenceSteps = 30 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 4, 64, 256 });
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 SpotDiffusionModel<float>(options: options))
    .Build(trainX, trainY);
var panorama = result.Predict(noise);

Constructors

Constructor Summary
SpotDiffusionModel(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()