Community, Leadership, Experimentation, Diversity, & Education
Pittsburgh Arts, Regional Theatre, New Work, Producing, Copyright, Labor Unions,
New Products, Coping Skills, J-O-Bs...
Theatre industry news, University & School of Drama Announcements, plus occasional course support for
Carnegie Mellon School of Drama Faculty, Staff, Students, and Alumni.
CMU School of Drama
Wednesday, March 29, 2023
Generating 3D models and meshes from text prompts? We asked Shutterstock about its team-up with NVIDIA
befores & afters: NVIDIA’s Picasso generative AI cloud service will be relied upon to convert text into high-fidelity 3D content. The idea is, software makers, service providers and enterprises can use Picasso to train NVIDIA Edify foundation models on their proprietary data to build applications that use natural text prompts to create and customize visual content.
Subscribe to:
Post Comments (Atom)
2 comments:
This seems really awesome to be honest. I feel like this could be used by many industries including our own; I see a lot of potential for props work, or design as well. I’ve read articles about text and AI generated images, but 3D models/mesh is different in that it could be directly printed, creating a physical object from text instead of just an image. The physical aspect of this brings on an entirely new potential for what we use, that is AI generated. There is also some thought to the idea that the mesh can also be edited as well, it could act as just a starting point for designs and models – it could cut the production process time speed up a bit. I’m curious to see how this develops, as always I do believe that it will be a long time until we realistically see this used frequently in our industry, but it is fun to think about the possibilities.
As someone who has been using many products by NVIDIA, it is honestly not surprising to me in what they are capable of doing and they wishes in changing the world the technical world around us. For me personally, someone who understands and makes 3D models, I’m really happy for this technology as it will make my job easier and I will have more time in putting in the actual design rather than just trying to make a design come true. This can truest benefit us in multiple ways such as when I’m mainly costume, just by simply putting the information into the machine and what I want, it was generate a model based on my idea. This saves up a lot of time. However, I can also see in why people would dislike this technology. It does takes away some of the work of a professional 3D model making designer and can potentially have copyright issues.
Post a Comment