Shutterstock and NVIDIA recently teamed up to train custom 3D models to create generative 3D assets from simple text prompts. Now this unique partnership has enabled creators to quickly create and customize 3D scene backgrounds with the help of generative AI, thanks to cutting-edge tools from Shutterstock.
NVIDIA has just shared highlights of how Shutterstock uses NVIDIA’s cloud-based foundry, Picasso, building on its services for developing AI models for visual design. By incorporating Picasso’s latest feature, artists can enhance, and light 3D scenes based on simple text or image prompts, all with AI models built using fully licensed, rights-reserved data.
“We’re committed to hyper-enabling 3D artists and collaborators — helping them build the immersive environments they envision faster than ever before and streamlining their content-creation workflows using NVIDIA Picasso,” said Dade Orgeron, vice president of 3D innovation at Shutterstock.
Highlights of the announcement include:
- Generating Photorealistic Environment Maps – Users can provide a prompt, whether text or a reference image, and Picasso’s 360 HDRi services will quickly generate panoramic images.
- Collaboration to Boost 3D World-Building – Autodesk will integrate generative AI content creation services, developed using foundation models in Picasso, with its popular 3D software Maya.
- Generative AI Model Foundry -The foundry will adopt new NVIDIA research to generate physics-based rendering materials from text and image prompts, demonstrated at SIGGRAPH’s Real-Time Live competition.
Picasso runs on the NVIDIA Omniverse Cloud platform-as-a-service accessible via a serverless application programming interface that content and service providers like Shutterstock can easily connect to their websites and applications.
Learn more – watch NVIDIA founder and CEO Jensen Huang’s SIGGRAPH keynote.
Head on over to the NVIDIA blog to get the complete rundown.
Dan Sarto is Publisher and Editor-in-Chief of Animation World Network.