Shutterstock has launched its generative 3D API, giving enterprises a fast and ethical way to produce realistic 3D models with artificial intelligence (AI). This generative API, built on the multimodal NVIDIA Edify generative AI architecture, was trained exclusively on Shutterstock content, including more than half a million ethically-sourced 3D models, more than 650 million images, and detailed Shutterstock metadata.

In addition, Shutterstock has begun early access to its 360 HDRi generator API, also built on NVIDIA Edify, which generates rich and detailed natural environments for lighting 3D scenes.

“With our new generative 3D capabilities, studios and developers can revolutionize their pipelines, leveraging the only generative 3D service entirely trained on licensed data to ensure fair compensation for the original creators who also have the option to opt-out,” said Dade Orgeron, vice president of innovation at Shutterstock. “What’s truly groundbreaking is that our generative technology transforms a traditionally lengthy process, that usually takes hours, into one that can be accomplished in minutes, dramatically reducing barriers to 3D creation and opening up new possibilities for enterprises across multiple industries.”

With the recent expansion of 3D worldwide, companies face an increasing imperative to engage in ethical AI solutions. In response, Shutterstock has released this text-to-3D and image-to-3D generator API platform, allowing enterprises to immediately begin using their ethically trained AI API to accelerate pipelines, populate virtual worlds, or even bring generative technology to the 3D tools artists use every day. The API can seamlessly be integrated into any application or pipeline, drastically reducing the time from concept to creation. Each 3D generation begins with a 2D preview image that users can approve or change. Once approved, the cloud-based generator produces the 3D files, which are returned in GLB, USDz, and OBJ formats as triangles and quad meshes, complete with physically based rendering (PBR) materials.

With each successive training cycle over the past 16 months, quality and prompt adherence has improved by a significant margin, leading to assets that are ideal to use for prototyping, previsualization, and as stepping stones to final designs. As part of this process, Shutterstock is also putting TRUST safeguards in place, which includes ensuring ethical compliance, legal integrity, and brand safety for its customers and their audiences through tailored protections and content controls. This also includes implementing and improving guardrails to protect against inappropriate content and content that resembles major brand IP.

To further help users, the API is launching with intuitive documentation that can even help non-developers integrate it in a couple of hours, as well as lightweight plugins and code samples for Blender and Gradio.

The API is available now for enterprise customers, with a self-serve option coming soon. With generative credit packs starting at $25, Shutterstock says companies and enterprises of all sizes will be able to utilize these next generation 3D capabilities.