Seedance1Model<T>
Models & Types · AiDotNet.Diffusion.Video
Seedance 1 ranked #1 on T2V and I2V leaderboards.
Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → VideoDiffusionModelBase<T> → Seedance1Model<T>
For Beginners
Seedance 1 from ByteDance ranks first on video generation leaderboards for both text-to-video and image-to-video. It produces highly detailed, temporally consistent videos with excellent prompt adherence.
How It Works
References:
- Reference: ByteDance Seedance 1 (2025)
Seedance 1 from ByteDance achieved #1 ranking on the Artificial Analysis T2V and I2V leaderboards. The model combines efficient DiT architecture with advanced temporal modeling and precise text understanding for state-of-the-art video generation quality.
Technical specifications:
- Architecture: Efficient DiT + Advanced Temporal Modeling
- 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, 90, 160 });
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 Seedance1Model<float>(options: options))
.Build(trainX, trainY);
var video = result.Predict(noise);
Constructors
| Constructor | Summary |
|---|---|
Seedance1Model(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 Seedance1Model 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() |