Vertex AI v1beta1 API - Class VeoHyperParameters (1.0.0-beta78)

public sealed class VeoHyperParameters : IMessage<VeoHyperParameters>, IEquatable<VeoHyperParameters>, IDeepCloneable<VeoHyperParameters>, IBufferMessage, IMessage

Reference documentation and code samples for the Vertex AI v1beta1 API class VeoHyperParameters.

Hyperparameters for Veo.

Inheritance

object > VeoHyperParameters

Namespace

Google.Cloud.AIPlatform.V1Beta1

Assembly

Google.Cloud.AIPlatform.V1Beta1.dll

Constructors

VeoHyperParameters()

public VeoHyperParameters()

VeoHyperParameters(VeoHyperParameters)

public VeoHyperParameters(VeoHyperParameters other)
Parameter
Name Description
other VeoHyperParameters

Properties

AdapterSize

public VeoHyperParameters.Types.AdapterSize AdapterSize { get; set; }

Optional. The adapter size for LoRA tuning.

Property Value
Type Description
VeoHyperParametersTypesAdapterSize

EpochCount

public long EpochCount { get; set; }

Optional. Number of complete passes the model makes over the entire training dataset during training.

Property Value
Type Description
long

HasTuningSpeed

public bool HasTuningSpeed { get; }

Gets whether the "tuning_speed" field is set

Property Value
Type Description
bool

HasVeoDataMixtureRatio

public bool HasVeoDataMixtureRatio { get; }

Gets whether the "veo_data_mixture_ratio" field is set

Property Value
Type Description
bool

LearningRateMultiplier

public double LearningRateMultiplier { get; set; }

Optional. Multiplier for adjusting the default learning rate.

Property Value
Type Description
double

TuningSpeed

public VeoHyperParameters.Types.TuningSpeed TuningSpeed { get; set; }

The speed of the tuning job. Only supported for Veo 3.0 models.

Property Value
Type Description
VeoHyperParametersTypesTuningSpeed

TuningTask

public VeoHyperParameters.Types.TuningTask TuningTask { get; set; }

Optional. The tuning task. Either I2V or T2V.

Property Value
Type Description
VeoHyperParametersTypesTuningTask

VeoDataMixtureRatio

public double VeoDataMixtureRatio { get; set; }

Optional. The ratio of Google internal dataset to use in the training mixture, in range of [0, 1). If 0.2, it means 20% of Google internal dataset and 80% of user dataset will be used for training. If not set, the default value is 0.1.

Property Value
Type Description
double