Thank you! That effect is easier than you'd think. Normal maps/depth maps are actually fairly easy to generate via diffusion models. Once I had the designs for the tarot site in diffui, I just copied the build plan, pasted it into claude, and asked it to "generate normal/depth/roughness maps for each of the card designs and dynamically light and displace them based on the mouse position."

The build plan has tooling built in to generate these. Under the hood the model I'm routing to is Fal.ai's Patina model, which does a fantastic job at creating maps.

File is here btw if you want to explore: https://diffui.ai/app/canvas/be49d1a3-df57-4c61-9305-4aef472...