Carved Light guide

Help

Short answers to what goes wrong most often.

Why does it say my pictures need WebGPU?

Reading depth runs a model on your graphics card through WebGPU, which current Chrome, Edge and Safari have. Some graphics cards cannot run this model even then, and some browsers cannot run its runtime; the page says which. Either way the sample still lights, and the light still falls on your own pictures, flat, without shape or shadows.

Why is the first picture slow?

The depth model downloads once, 47 MB, and is kept in the browser. After that a picture is read in a few seconds. Meanwhile the light falls on it flat, and it takes its shape after the first pass, before the fine detail is in.

The light looks flat on my picture

Its depth is not read yet, so the light falls on it as on a flat card. If the depth model could not be downloaded, the line at the top of the picture says so and tries again by itself; press Try again there to try at once.

A light seems to do nothing

It may be behind the subject: its ring is dashed and it says behind. Raise it with the wheel. It may be muted or another light soloed, or its Reach under Lamp may be too short to arrive.

There are dark wedges behind thin things

Lower Solidity under Shadow, so light passes under hair and horns, and lower Length for shorter shadows.

Where do my pictures go?

Nowhere. They are read and lit in your browser. The only things it downloads are the sample, the runtime and the depth model; nothing is uploaded.

Whose depth model is it?

Depth Anything V2 Small, from the Depth Anything V2 paper by Lihe Yang and others (2024), converted to ONNX by the onnx-community on Hugging Face. It is under the Apache License 2.0; the notice and the licence text are at /lab/_carved/MODEL-LICENSE.txt, and beside the model file itself.