Show HN: Local implementation of text-to-3D using Shap-E

I'm a little confused...doesn't Shap-E itself run locally?

I played with Shap-E when released. It did download a model on first run, but the actual processing happened locally.

Does this embed the model in the repo? Or does it still need to download the model from somewhere at some point?

You're exactly right. I'm not sure what the point of this is.

I think this tech will really be what kicks off the "metaverse". Right now 3D content generation is just too labour intensive. And Autogen too boring.

Looking forward to more developments on this.

Looks cool. I teach 3D modelling. I would love to see the meshes this approach produces. I'm gonna guess that they are poorly topologized. Agreeable topology enables ease of texturing, editing, animation and dozens of other things. If this could be generated then I may well be out of a job in a few years.

Any idea what the minimum amount of vram required is?

For any heightmap based 3d models this can easily be done with customised image diffusers. It’s hilariously trivial to implement for terrains, human faces or anything that relies on grayscale alpha maps.