3D Printing

Advanced Manufacturing

Generating 3D Models from Simple Text Prompts: OpenAI’s Point-E System

Things are moving very quickly in the text to 3D model AI space.

listen to this story

An example of some crude 3D models automatically generated from the corresponding text prompts [Source: ArXiv]

An example of some crude 3D models automatically generated from the corresponding text prompts [Source: ArXiv]

Luma AI has released a tool that can literally generate 3D printable 3D models from a text prompt. 

Now OpenAI, one of the leading companies in the AI space, and the one that created GPT and DALL-E, released “Point-E”, a “System for Generating 3D Point Clouds from Complex Prompts.” 

Note: a “Point Cloud” is a collection of points in 3D space that represent an object. They can easily be converted into a mesh model, like STL format, with many existing software tools. 

The idea here is that a user could input simple text requests (a “prompt”) to obtain a 3D printable model, or one that could be used as a 3D asset in a game. An example prompt might be: “An ornate victorian wooden chair, with velvet cushion” 

The system would generate the 3D model in a manner similar to that which is done to create artificial images in several popular systems, such as MidJourney, DALL-E and Stable Diffusion.

To read the full story, visit Fabbaloo.com