Kling26Model<T>

Models & Types · AiDotNet.Diffusion.Video

Kling 2.6 with simultaneous audio-visual generation.

Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → VideoDiffusionModelBase<T> → Kling26Model<T>

For Beginners

Kling 2.6 generates videos with simultaneous audio and visual output, producing synchronized sound effects and dialogue. It excels at audio-visual coherence where sounds match the visual content naturally.

How It Works

References:

  • Reference: Kuaishou Kling 2.6 (2025)

Kling 2.6 delivers fast output with natural sound effects and strong motion consistency. The model generates synchronized audio-visual content in a single pass, making it particularly effective for product demonstrations and action sequences. Features advanced depth and cinematic shot capabilities.

Technical specifications:

  • Architecture: DiT + Simultaneous Audio-Visual Generation
  • Latent channels: 16
  • Default: 120 frames at 24 FPS
  • Supports I2V: Yes | T2V: Yes | V2V: No

Example

var options = new DiffusionModelOptions<float> { LatentChannels = 16, DefaultInferenceSteps = 30 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 16, 120, 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 Kling26Model<float>(options: options))
    .Build(trainX, trainY);
var video = result.Predict(noise);

Constructors

Constructor Summary
Kling26Model(NeuralNetworkArchitecture<T> architecture, DiffusionModelOptions<T> options, INoiseScheduler<T> scheduler, DiTNoisePredictor<T> predictor, TemporalVAE<T> temporalVAE, IConditioningModule<T> conditioner, int defaultNumFrames, int defaultFPS) Initializes a new instance of Kling26Model 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()