Enum InferenceModality

Namespace

LMKit.Inference

Assembly

LM-Kit.NET.dll

Specifies which modality (or combination of modalities) should be used when performing inference on the input data.

public enum InferenceModality

Fields

Text = 0

Perform inference using only text-based processing. Any image content will be ignored or treated as non-text.

Vision = 1

Perform inference using only image-based (vision) processing. Any text content will be ignored.

Multimodal = 2

Perform inference using both text and image modalities. The model will combine signals from text and vision.

BestModality = 3

Automatically select the single best modality (Text or Image) based on the input characteristics.