Archinect - News2024-12-04T03:41:25-05:00https://archinect.com/news/article/150349366/with-openai-s-new-3d-model-tool-shap-e-text-to-3d-printing-may-soon-be-a-reality
With OpenAI’s new 3D model tool Shap-E, text-to-3D printing may soon be a reality Niall Patrick Walsh2023-05-10T12:11:00-04:00>2024-10-25T04:07:38-04:00
<img src="https://archinect.gumlet.io/uploads/92/92159961d2e6bd5d0acc653b173ffd88.jpg?fit=crop&auto=compress%2Cformat&enlarge=true&w=1200" border="0" /><p><a href="https://archinect.com/news/tag/2201760/openai" target="_blank">OpenAI</a>, the company behind AI applications such as <a href="https://archinect.com/news/tag/2200819/chatgpt" target="_blank">ChatGPT</a> and text-to-image tool <a href="https://archinect.com/features/article/150326467/you-me-and-dall-e-on-the-relationship-between-architecture-data-and-artificial-intelligence" target="_blank">DALL-E</a>, has unveiled a new model that allows users to generate 3D objects from text or images. Named Shap-E, and available for free on <a href="https://github.com/openai/shap-e" target="_blank">GitHub</a>, the tool generates 3D objects that can be opened in Microsoft Paint 3D and converted into STL files for use in <a href="https://archinect.com/news/tag/475/3d-printing" target="_blank">3D printers</a>.</p>
<p>Unlike ChatGPT and DALL-E, Shap-E does not operate over an online application and is instead downloaded onto a PC for local use. The tool works in three modes: a ‘text-to-3D’ mode that uses text prompts to generate models, an ‘image-to-3D’ mode that turns a 2D image into a 3D object, and ‘encode-model’ which takes an existing 3D model and transforms it into another model.</p>
<figure><p><a href="https://archinect.gumlet.io/uploads/19/199829d1995faabf22383b923ce9eca9.png?auto=compress%2Cformat&enlarge=true&w=1028" target="_blank"><img src="https://archinect.gumlet.io/uploads/19/199829d1995faabf22383b923ce9eca9.png?auto=compress%2Cformat&enlarge=true&w=514"></a></p><figcaption>3D objects generated from text prompts by Shap-E. Image credit: OpenAI</figcaption></figure><p>According to a <a href="https://arxiv.org/abs/2305.02463" target="_blank">paper by OpenAI</a> announcing the tool, Shap-E can produce both textured meshes (3D objects formed of polygons overlayed by colored textures) and neural radiance fields (3D scenes generated b...</p>