LumaRay2Model<T>
Models & Types · AiDotNet.Diffusion.Video
Luma Ray 2 video model with fast natural motion and better physics.
Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → VideoDiffusionModelBase<T> → LumaRay2Model<T>
For Beginners
Luma Ray 2 produces videos with fast, natural motion using 10x more compute than its predecessor. It excels at realistic movement patterns and physical interactions between objects.
How It Works
References:
- Reference: Luma AI Ray 2 (2025)
Ray 2 was trained with 10x more compute than Ray1, offering fast, natural coherent motion and physics understanding. The model generates videos with natural motion dynamics and good temporal consistency. Features improved physics simulation for realistic object interactions.
Technical specifications:
- Architecture: DiT + Enhanced Physics + 10x Compute
- Latent channels: 16
- Default: 120 frames at 24 FPS
- Supports I2V: Yes | T2V: Yes | V2V: No
Example
var options = new DiffusionModelOptions<float> { LatentChannels = 16, DefaultInferenceSteps = 30 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 16, 120, 135, 240 });
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 LumaRay2Model<float>(options: options))
.Build(trainX, trainY);
var video = result.Predict(noise);
Constructors
| Constructor | Summary |
|---|---|
LumaRay2Model(NeuralNetworkArchitecture<T> architecture, DiffusionModelOptions<T> options, INoiseScheduler<T> scheduler, DiTNoisePredictor<T> predictor, TemporalVAE<T> temporalVAE, IConditioningModule<T> conditioner, int defaultNumFrames, int defaultFPS) |
Initializes a new instance of LumaRay2Model with full customization support. |
Properties
| Property | Summary |
|---|---|
IConditioningModule<T> Conditioner { get; } |
|
INoisePredictor<T> NoisePredictor { get; } |
|
IVAEModel<T> TemporalVAE { get; } |
|
IVAEModel<T> VAE { get; } |
|
bool SupportsImageToVideo { get; } |
|
bool SupportsTextToVideo { get; } |
|
bool SupportsVideoToVideo { get; } |
|
int LatentChannels { get; } |
Methods
| Method | Summary |
|---|---|
ModelMetadata<T> GetModelMetadata() |