EditingVLMOptions
Options & Configuration · AiDotNet.VisionLanguage.Editing
Base configuration options for image editing VLMs.
Inheritance: ModelOptions → GenerativeVLMOptions → EditingVLMOptions
Known derived types: EmuEditOptions, MGIEOptions, SmartEditOptions
For Beginners
These options configure the Editing model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
EditingVLMOptions() |
Initializes a new instance with default values. |
EditingVLMOptions(EditingVLMOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
double GuidanceScale { get; set; } |
Gets or sets the guidance scale for classifier-free guidance. |
int EditHeadLayers { get; set; } |
Depth of the edit head that carries MLLM visual tokens into the diffusion model. |
int NumDiffusionSteps { get; set; } |
Gets or sets the number of diffusion denoising steps. |
int OutputImageSize { get; set; } |
Gets or sets the output image resolution. |