AVIDOptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the AVID (Audio-Visual Inpainting Diffusion) video inpainting model.
Inheritance: ModelOptions → AVIDOptions
For Beginners
AVID options control adaptive video inpainting via diffusion models.
How It Works
References:
- Paper: “AVID: Any-Length Video Inpainting with Diffusion Model” (Zhang et al., CVPR 2024)
AVID uses a diffusion-based approach for video inpainting, supporting arbitrary video lengths through an autoregressive temporal pipeline with overlapping windows for consistency.
Constructors
| Constructor | Summary |
|---|---|
AVIDOptions() |
Initializes a new instance with default values. |
AVIDOptions(AVIDOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
ONNX runtime options for inference mode. |
VideoModelVariant Variant { get; set; } |
Model variant controlling capacity and speed trade-off. |
double DropoutRate { get; set; } |
Dropout rate for regularization. |
double LearningRate { get; set; } |
Learning rate for training. |
int NumDiffusionSteps { get; set; } |
Number of diffusion steps for the denoising process. |
int NumFeatures { get; set; } |
Number of base feature channels in the diffusion U-Net. |
int NumHeads { get; set; } |
Number of attention heads in the temporal transformer layers. |
int NumResBlocks { get; set; } |
Number of residual blocks per U-Net level. |
int TemporalOverlap { get; set; } |
Size of overlapping temporal window for long video processing. |
string ModelPath { get; set; } |
Path to the ONNX model file for inference mode. |