Edify: Nvidia and Shutterstock launch text-to-3D service
Nvidia and Shutterstock are launching a text-to-3D service, and Getty Images is launching a service that gives creative professionals more control over AI image generation.
Shutterstock's 3D generation is based on a new version of Nvidia's Edify, a multimodal architecture for visual generative AI. New features include 3D asset generation and more control over 2D image generation. The new text-to-3D service is now available via API as part of an early access program.
At GTC, Shutterstock will also demonstrate a collaboration with HP to 3D print models created with Edify 3D. The prototype will demonstrate how the combination of these methods opens up new possibilities for designers to create prototypes.
Getty Images launches fine-tuning and new image editing methods for businesses
Getty Images is expanding the capabilities of its commercially secure generative AI service, offering services to customize the Edify base model to a company's brand and visual style beginning in May. New APIs will soon provide access to additional features such as sketch, depth, and segmentation to more precisely control image generation.
The pre-built Edify models from Getty Images and Shutterstock can also be tested as APIs through Nvidia NIM, a collection of inference microservices announced today at Nvidia GTC. Developers can also train and deploy their own generative AI models using the Edify architecture through Nvidia Picasso.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe nowRead on for the full picture.
Subscribe for hype-free coverage.
- Full access to every article on THE DECODER
- No ads
- Join the comments and community discussions
- A weekly AI news recap via mail
- 6x/year: "AI Radar" — deep dives on the AI topics that matter most
- Daily AI news, always up to date
- Our full ten-year archive
- Covered by a team with 10+ years in AI