Glossary

ControlNet

A model that constrains image generation to match a reference's pose, depth, edges or layout.

ControlNet is a family of auxiliary models that let you control composition. Feed in a pose skeleton, a depth map, or a canny-edge sketch, and the diffusion model will generate an image that matches that structure while still respecting your prompt.

Synexa's pose-clone and img2img tools use ControlNet under the hood.

← All glossary terms

Ready to generate?

Free credits on signup. No card. 4K output, no watermark.