Press Space to continue
Curated tech posts from X on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
Press Space to continue
Press Space to continue
This is a new model that specializes in 3D rendering and geometry. You give it an image and a rough 3D mesh, and it creates a more detailed 3D shape. The model was trained on 2 million 3D assets, which is a ton of data! This is probably why it can generate pretty good results. I read the report, and the model has a 90% success rate in generating models that are ready for 3D printing.
