Sora2Model<T>
Models & Types · AiDotNet.Diffusion.Video
Sora 2 cinematic video generation with physics simulation and synced audio.
Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → VideoDiffusionModelBase<T> → Sora2Model<T>
For Beginners
Sora 2 is OpenAI’s advanced video generation model producing cinematic-quality videos with realistic physics simulation and synchronized audio. It understands 3D scene consistency, camera motion, and can generate videos up to a minute long.
How It Works
References:
- Reference: OpenAI Sora 2 (2025)
Sora 2 generates cinematic-quality videos with realistic physics simulation, synchronized audio, and strong prompt adherence. The model demonstrates understanding of cause-and-effect relationships and can produce videos with natural lighting, reflections, and physical interactions.
Technical specifications:
- Architecture: DiT + Physics Simulation + Audio Sync
- Latent channels: 16
- Default: 240 frames at 24 FPS
- Supports I2V: Yes | T2V: Yes | V2V: No
Example
var options = new DiffusionModelOptions<float> { LatentChannels = 16, DefaultInferenceSteps = 50 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 16, 240, 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 Sora2Model<float>(options: options))
.Build(trainX, trainY);
var video = result.Predict(noise);
Constructors
| Constructor | Summary |
|---|---|
Sora2Model(NeuralNetworkArchitecture<T> architecture, DiffusionModelOptions<T> options, INoiseScheduler<T> scheduler, DiTNoisePredictor<T> predictor, TemporalVAE<T> temporalVAE, IConditioningModule<T> conditioner, int defaultNumFrames, int defaultFPS, int? seed) |
Initializes a new instance of Sora2Model 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() |