What does a depth map ControlNet control?

It controls the spatial layout and three-dimensional composition of the scene — what is near, what is far, and the overall sense of volume and perspective. Unlike Canny, it does not constrain fine edges, so the model has freedom in surface detail while keeping your scene structure.

MiDaS vs LeReS vs ZoeDepth — which estimator?

MiDaS is the fast, reliable default for general scenes. LeReS captures more fine foreground detail and sharper depth boundaries, useful for portraits and objects. ZoeDepth produces metric (real-scale) depth, which helps when accurate relative distances matter. Start with MiDaS and switch only if depth separation looks wrong.

How is a depth map read?

It is a grayscale image where brightness encodes distance — by convention lighter pixels are closer to the camera and darker pixels are farther away. Checking the map before generating tells you whether the foreground and background have separated correctly.

Can I combine depth with other ControlNets?

Yes, and it is common. Depth handles overall scene volume while another module adds specifics — pair it with Canny to keep both composition and edges, or with OpenPose to place a posed figure correctly within a 3D scene. Lower each module's strength when stacking so they do not over-constrain the result.

Depth Map ControlNet Guide

Depth map ControlNet guide

A depth map ControlNet controls the spatial composition of an image — the sense of near and far, of volume and perspective — without locking down fine edges. It is the right tool when you want to preserve a scene’s three-dimensional layout but give the model freedom over surface detail. The two choices that drive quality are the depth estimator you use to build the map and the control strength you apply.

How it works

A depth estimator analyzes the source image and outputs a grayscale depth map: lighter pixels are nearer the camera, darker pixels are farther away. MiDaS is the fast, general-purpose default; LeReS resolves finer foreground detail and crisper depth boundaries; ZoeDepth produces metric-scale depth for accurate relative distances. ControlNet feeds this map to the diffusion model, which builds a new image whose spatial structure matches the map. Control strength scales how strictly that structure is enforced.

Tips for spatial control

Start with MiDaS. It is reliable for most scenes; only switch to LeReS or ZoeDepth when foreground detail or true scale matters.
Inspect the map first. If foreground and background blur into the same gray, the model will not separate them either — try a different estimator.
Use moderate strength for natural depth. High strength enforces layout rigidly; mid strength keeps the composition while letting the scene breathe.
Stack with other modules. Combine depth with Canny for composition plus edges, or with OpenPose to seat a figure correctly in 3D — lower each strength when stacking so they don’t fight.