LLaVAVideoOptions
Options & Configuration · AiDotNet.VisionLanguage.VideoLanguage
Configuration options for LLaVA-Video: synthetic dataset-trained video instruction model.
Inheritance: ModelOptions → GenerativeVLMOptions → VideoLanguageOptions → LLaVAVideoOptions
For Beginners
These options configure the LLaVAVideo model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
LLaVAVideoOptions() |
Initializes a new instance with default values. |
LLaVAVideoOptions(LLaVAVideoOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
int ImageChannels { get; set; } |
Number of channels per video frame. |
int PatchSize { get; set; } |
Patch size for the vision encoder. |