google-genai-kotlin/com.google.genai.kotlin.types/VeoHyperParameters

VeoHyperParameters

@Serializable
data class VeoHyperParameters(val epochCount: Long? = null, val learningRateMultiplier: Double? = null, val tuningTask: TuningTask? = null, val veoDataMixtureRatio: Double? = null, val adapterSize: AdapterSize? = null, val tuningSpeed: TuningSpeed? = null)

Hyperparameters for Veo. This data type is not supported in Gemini API.

Constructors

Link copied to clipboard
constructor(epochCount: Long? = null, learningRateMultiplier: Double? = null, tuningTask: TuningTask? = null, veoDataMixtureRatio: Double? = null, adapterSize: AdapterSize? = null, tuningSpeed: TuningSpeed? = null)

Properties

Link copied to clipboard
val adapterSize: AdapterSize? = null

Optional. The adapter size for LoRA tuning.

Link copied to clipboard
val epochCount: Long? = null

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

Link copied to clipboard
val learningRateMultiplier: Double? = null

Optional. Multiplier for adjusting the default learning rate.

Link copied to clipboard
val tuningSpeed: TuningSpeed? = null

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

Link copied to clipboard
val tuningTask: TuningTask? = null

The tuning task for Veo.

Link copied to clipboard
val veoDataMixtureRatio: Double? = null

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.