MovieGenModel<T>

Models & Types · AiDotNet.Diffusion.Video

MovieGen 30B foundation model for video, audio, and editing.

Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → VideoDiffusionModelBase<T> → MovieGenModel<T>

For Beginners

Movie Gen from Meta is a massive 30B parameter model that generates 16-second video clips at 16 FPS with synchronized audio. It is one of the largest video generation models, designed for high-fidelity movie-quality content.

How It Works

References:

  • Paper: “Movie Gen: A Cast of Media Foundation Models” (Meta, 2024)

MovieGen is Meta’s 30B parameter foundation model generating 1080p HD videos at 16 FPS with synchronized audio. Trained with a maximum context of 73K video tokens for 16-second generation. Sets state-of-the-art across text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation.

Technical specifications:

  • Architecture: 30B DiT + Audio Generation + Video Editing
  • Latent channels: 16
  • Default: 256 frames at 16 FPS
  • Supports I2V: Yes | T2V: Yes | V2V: Yes

Example

var options = new DiffusionModelOptions<float> { LatentChannels = 16, DefaultInferenceSteps = 50 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 16, 256, 96, 96 });
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 MovieGenModel<float>(options: options))
    .Build(trainX, trainY);
var video = result.Predict(noise);

Constructors

Constructor Summary
MovieGenModel(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 MovieGenModel 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()