Item — HN Reader

Not to be a skeptic or anything, but how do we know normal maps etc weren’t enriched into the datasets by the image gen companies?

I understand this paper links to open source model where that can be verified, but maybe this is one secret sauce of these more advanced models?

1 comments

You would need to train on pairings of normal map images to source images. To my knowledge, that’s not a common training technique and this ability seems to bridge across several open models.

It’s also kind of cool if it “understands” a normal map and that it maps to specific 3D geometry. People generally use 3D tools like Zbrush to sculpt the details to normals. Probably some people can draw them too