Show1Model<T>
Models & Types · AiDotNet.Diffusion.Video.LongVideo
Show-1 marrying pixel and latent diffusion for text-to-video.
Inheritance: DiffusionModelBase<T> → LatentDiffusionModelBase<T> → VideoDiffusionModelBase<T> → Show1Model<T>
For Beginners
Show-1 combines pixel-space and latent-space diffusion in a two-stage pipeline. The first stage generates coarse video in pixel space, then the second refines it in latent space for high-quality output.
How It Works
References:
- Paper: “Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation” (2023)
Show-1 combines pixel-space and latent-space diffusion models in a cascaded pipeline. The pixel diffusion model handles low-resolution generation for accurate motion, while the latent diffusion model performs super-resolution for visual quality. This marriage leverages the strengths of both approaches.
Technical specifications:
- Architecture: Pixel Diffusion + Latent Super-Resolution Cascade
- Latent channels: 4
- Default: 29 frames at 8 FPS
- Supports I2V: Yes | T2V: Yes | V2V: No
Example
var options = new DiffusionModelOptions<float> { LatentChannels = 4, DefaultInferenceSteps = 50 };
var noise = Tensor<float>.CreateRandom(new[] { 1, 4, 29, 32, 32 });
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 Show1Model<float>(options: options))
.Build(trainX, trainY);
var video = result.Predict(noise);
Constructors
| Constructor | Summary |
|---|---|
Show1Model(NeuralNetworkArchitecture<T> architecture, DiffusionModelOptions<T> options, INoiseScheduler<T> scheduler, VideoUNetPredictor<T> predictor, TemporalVAE<T> temporalVAE, IConditioningModule<T> conditioner, int defaultNumFrames, int defaultFPS, int? seed) |
Initializes a new instance of Show1Model 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() |