IImageEditingVLM<T>

Interfaces · AiDotNet.VisionLanguage.Interfaces

Interface for VLMs that edit images based on natural language instructions.

Implements: IVisualEncoder<T>

Known implementations: EmuEdit<T>, MGIE<T>, SmartEdit<T>

How It Works

Image editing VLMs take an input image and a text instruction and produce an edited version. These models understand the semantic intent of the instruction and apply targeted modifications.

Properties

Property Summary
int OutputImageSize { get; } Gets the output image resolution.

Methods

Method Summary
Tensor<T> EditImage(Tensor<T> image, string instruction) Edits an image according to a natural language instruction.