Skip to content

Tile bias at inference time #232

Description

@schrum2

Consider the output of a diffusion model, which should represent a bunch of nearly one-hot encoded vectors. If I wanted to bias the generation to make certain classes of tiles more likely, I could simply add some constant value to that channel of the tensor output, thus making that tile type more likely. This could be a useful knob at inference time. Worth considering.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions