Reads
Cloud depth-estimation model
Cloud Engine · 1 Credit
Depth that reads like anatomy, not brightness.
AI Depth sends your image to a real AI depth-estimation model instead of computing height from grayscale tone. The result is closer to a 3D scan of the subject — it understands that a nose comes forward and an eye socket recedes, regardless of how the photo happens to be lit.
Two modes, one cloud call
AI Depth uses the cloud model's output directly. AI Depth + Detail takes that same base depth and adds an additive local high-pass texture layer on top, controlled by the Surface Detail slider — this is what puts fine skin, fabric, and hair texture back into an otherwise smooth AI-estimated surface. Surface Detail at 0% returns exactly the raw AI Depth base with no texture added.
Both modes call the same cloud model, so both cost the same: 1 AI credit per generation, whether or not you add Surface Detail afterward.
Surface Detail
0–200%, default 60%
Cost
1 credit / generation
Preview vs. Export
Lit Relief Smoothing — a preview control, not a data change
The cloud model's depth data is quantized to 256 levels on the way back — completely invisible in the actual exported height map. But the Lit Relief preview mode uses raking-light shading to make surface detail pop, and that lighting math can amplify single-level quantization steps into visible contour-ring banding on screen, especially at higher working resolutions.
The Lit Relief Smoothing slider (default 12px) only smooths the lighting-normal calculation behind that one preview mode. It never touches the exported height map, STL, or any other preview mode — Height Map, Slope Map, and Compare are unaffected either way. If you still see rings in Lit Relief at the default, raise it; set it to 0 to see the raw, unsmoothed data.
Want to skip the source photo entirely?
The Relief Generator builds a sculpted relief from a text prompt alone — no image required.
See Relief Generator →