UnifiedVisionOptions
Options & Configuration · AiDotNet.VisionLanguage.Unified
Base configuration options for unified understanding + generation vision models.
Inheritance: ModelOptions → GenerativeVLMOptions → UnifiedVisionOptions
Known derived types: ChameleonOptions, JanusOptions, JanusProOptions, OmniGen2Options, SEEDXOptions, ShowO2Options, ShowOOptions, TransfusionOptions
For Beginners
These options configure the UnifiedVision model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
UnifiedVisionOptions() |
Initializes a new instance with default values. |
UnifiedVisionOptions(UnifiedVisionOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
bool SupportsGeneration { get; set; } |
Gets or sets whether the model supports image generation. |
int NumVisualTokens { get; set; } |
Gets or sets the number of discrete visual tokens in the vocabulary. |
int OutputImageSize { get; set; } |
Gets or sets the generated image resolution. |
string LanguageModelName { get; set; } |
Gets or sets the language model backbone name. |