Table of Contents

Class CogVideo<T>

Namespace
AiDotNet.Video.Generation
Assembly
AiDotNet.dll

CogVideo: Text-to-Video Diffusion Model for generating videos from text descriptions.

public class CogVideo<T> : NeuralNetworkBase<T>, INeuralNetworkModel<T>, INeuralNetwork<T>, IFullModel<T, Tensor<T>, Tensor<T>>, IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>, IModelSerializer, ICheckpointableModel, IParameterizable<T, Tensor<T>, Tensor<T>>, IFeatureAware, IFeatureImportance<T>, ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>, IGradientComputable<T, Tensor<T>, Tensor<T>>, IJitCompilable<T>, IInterpretableModel<T>, IInputGradientComputable<T>, IDisposable

Type Parameters

T

The numeric type used for calculations (typically float or double).

Inheritance
CogVideo<T>
Implements
IFullModel<T, Tensor<T>, Tensor<T>>
IModel<Tensor<T>, Tensor<T>, ModelMetadata<T>>
IParameterizable<T, Tensor<T>, Tensor<T>>
ICloneable<IFullModel<T, Tensor<T>, Tensor<T>>>
IGradientComputable<T, Tensor<T>, Tensor<T>>
Inherited Members
Extension Methods

Remarks

CogVideo is a state-of-the-art text-to-video generation model that: - Generates coherent video clips from text prompts - Uses diffusion-based denoising in latent space - Produces temporally consistent animations

For Beginners: CogVideo creates videos from text descriptions. You provide a prompt like "a cat playing with a ball" and it generates a video showing that scene. It works by: 1. Starting with random noise 2. Gradually denoising to create coherent frames 3. Ensuring temporal consistency across frames

Example usage (native mode for training):

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 32, inputWidth: 32, inputDepth: 4);
var model = new CogVideo<double>(arch);
model.Train(noisyLatent, cleanLatent);
var videoFrames = model.Generate(textEmbedding, numSteps: 50);

Example usage (ONNX mode for inference only):

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 32, inputWidth: 32, inputDepth: 4);
var model = new CogVideo<double>(arch, "cogvideo.onnx");
var videoFrames = model.Generate(textEmbedding);

Reference: "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer" https://arxiv.org/abs/2408.06072

Constructors

CogVideo(NeuralNetworkArchitecture<T>, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>?, ILossFunction<T>?, int, int, int, int)

Creates a CogVideo model using native layers for training and inference.

public CogVideo(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>? optimizer = null, ILossFunction<T>? lossFunction = null, int embedDim = 1024, int numLayers = 24, int numFrames = 16, int numTimesteps = 1000)

Parameters

architecture NeuralNetworkArchitecture<T>

Architecture for the video generation network.

optimizer IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>>

Optional optimizer for training. Default: Adam.

lossFunction ILossFunction<T>

Optional loss function. Default: MSE.

embedDim int

Embedding dimension (default: 1024).

numLayers int

Number of transformer layers (default: 24).

numFrames int

Number of frames to generate (default: 16).

numTimesteps int

Remarks

For Beginners: Create a trainable CogVideo model: 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 32, inputWidth: 32, inputDepth: 4);
var model = new CogVideo<double>(arch);

CogVideo(NeuralNetworkArchitecture<T>, string, int, int)

Creates a CogVideo model using a pretrained ONNX model for inference.

public CogVideo(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, int numFrames = 16, int numTimesteps = 1000)

Parameters

architecture NeuralNetworkArchitecture<T>

The neural network architecture configuration.

onnxModelPath string

Path to the pretrained ONNX model.

numFrames int

Number of frames the model generates (default: 16).

numTimesteps int

Remarks

For Beginners: Use this constructor when you have a pretrained model in ONNX format. Training is not supported in ONNX mode. 

var arch = new NeuralNetworkArchitecture<double>(
    inputType: InputType.ThreeDimensional,
    inputHeight: 32, inputWidth: 32, inputDepth: 4);
var model = new CogVideo<double>(arch, "cogvideo.onnx");
var video = model.Generate(textEmbedding);

Exceptions

FileNotFoundException

Thrown if the ONNX model file is not found.

Properties

SupportsTraining

Gets whether training is supported (only in native mode).

public override bool SupportsTraining { get; }

Property Value

bool

Methods

CreateNewInstance()

Creates a new instance of the same type as this neural network.

protected override IFullModel<T, Tensor<T>, Tensor<T>> CreateNewInstance()

Returns

IFullModel<T, Tensor<T>, Tensor<T>>

A new instance of the same neural network type.

Remarks

For Beginners: This creates a blank version of the same type of neural network.

It's used internally by methods like DeepCopy and Clone to create the right type of network before copying the data into it.

Denoise(Tensor<T>, Tensor<T>, double)

Performs a single denoising step.

public Tensor<T> Denoise(Tensor<T> noisyInput, Tensor<T> textEmbedding, double timestep)

Parameters

noisyInput Tensor<T>

Current noisy input tensor.

textEmbedding Tensor<T>

Text conditioning embedding.

timestep double

Current timestep (0-1 range).

Returns

Tensor<T>

Denoised output tensor.

DeserializeNetworkSpecificData(BinaryReader)

Deserializes network-specific data that was not covered by the general deserialization process.

protected override void DeserializeNetworkSpecificData(BinaryReader reader)

Parameters

reader BinaryReader

The BinaryReader to read the data from.

Remarks

This method is called at the end of the general deserialization process to allow derived classes to read any additional data specific to their implementation.

For Beginners: Continuing the suitcase analogy, this is like unpacking that special compartment. After the main deserialization method has unpacked the common items (layers, parameters), this method allows each specific type of neural network to unpack its own unique items that were stored during serialization.

Generate(Tensor<T>, int)

Generates video frames from a text embedding.

public Tensor<T> Generate(Tensor<T> textEmbedding, int numSteps = 50)

Parameters

textEmbedding Tensor<T>

Text embedding from a text encoder.

numSteps int

Number of denoising steps (default: 50).

Returns

Tensor<T>

Generated video frames tensor.

Remarks

For Beginners: This method creates a video from a text description. The text must first be encoded using a text encoder (like CLIP). More denoising steps generally produce better quality but take longer.

GetModelMetadata()

Gets the metadata for this neural network model.

public override ModelMetadata<T> GetModelMetadata()

Returns

ModelMetadata<T>

A ModelMetaData object containing information about the model.

InitializeLayers()

Initializes the layers of the neural network based on the architecture.

protected override void InitializeLayers()

Remarks

For Beginners: This method sets up all the layers in your neural network according to the architecture you've defined. It's like assembling the parts of your network before you can use it.

Predict(Tensor<T>)

Makes a prediction using the neural network.

public override Tensor<T> Predict(Tensor<T> input)

Parameters

input Tensor<T>

The input data to process.

Returns

Tensor<T>

The network's prediction.

Remarks

For Beginners: This is the main method you'll use to get results from your trained neural network. You provide some input data (like an image or text), and the network processes it through all its layers to produce an output (like a classification or prediction).

SerializeNetworkSpecificData(BinaryWriter)

Serializes network-specific data that is not covered by the general serialization process.

protected override void SerializeNetworkSpecificData(BinaryWriter writer)

Parameters

writer BinaryWriter

The BinaryWriter to write the data to.

Remarks

This method is called at the end of the general serialization process to allow derived classes to write any additional data specific to their implementation.

For Beginners: Think of this as packing a special compartment in your suitcase. While the main serialization method packs the common items (layers, parameters), this method allows each specific type of neural network to pack its own unique items that other networks might not have.

Train(Tensor<T>, Tensor<T>)

Trains the neural network on a single input-output pair.

public override void Train(Tensor<T> input, Tensor<T> expectedOutput)

Parameters

input Tensor<T>

The input data.

expectedOutput Tensor<T>

The expected output for the given input.

Remarks

This method performs one training step on the neural network using the provided input and expected output. It updates the network's parameters to reduce the error between the network's prediction and the expected output.

For Beginners: This is how your neural network learns. You provide: - An input (what the network should process) - The expected output (what the correct answer should be)

The network then:

  1. Makes a prediction based on the input
  2. Compares its prediction to the expected output
  3. Calculates how wrong it was (the loss)
  4. Adjusts its internal values to do better next time

After training, you can get the loss value using the GetLastLoss() method to see how well the network is learning.

UpdateParameters(Vector<T>)

Updates the network's parameters with new values.

public override void UpdateParameters(Vector<T> parameters)

Parameters

parameters Vector<T>

The new parameter values to set.

Remarks

For Beginners: During training, a neural network's internal values (parameters) get adjusted to improve its performance. This method allows you to update all those values at once by providing a complete set of new parameters.

This is typically used by optimization algorithms that calculate better parameter values based on training data.

Edit this page