Property VlmImageDetail

Namespace

LMKit.Document.Conversion

Assembly

LM-Kit.NET.dll

VlmImageDetail

Gets or sets the image-detail level forwarded to the vision model. Higher detail improves fidelity on dense pages (small fonts, tight tables, footnotes) but raises the token budget the VLM consumes per page. Defaults to High.

public ImageDetail VlmImageDetail { get; set; }

Property Value

ImageDetail

Examples

using LMKit.Inference.Vision;

// Lower fidelity, faster inference, fewer tokens per page.
var options = new DocumentToMarkdownOptions { VlmImageDetail = ImageDetail.Low };