Getty Images, a preeminent global visual content creator and marketplace, has announced the launch of an updated model for its commercially safe generative AI services and tools. The latest enhancement delivers generation speeds set to reach around 6 seconds for 4 images, doubling the performance of the previous model, with speeds at the forefront of the industry. With this rapid generation time, customers can experience significantly enhanced creative potential and efficiency, allowing for the production of high-quality, detailed images.
The updated model is built on the NVIDIA Edify model architecture, part of NVIDIA Picasso, a foundry for building and deploying generative AI models for visual design. Updates to NVIDIA Edify provide substantial advancements in output speed and quality, better alignment with user prompts, longer prompt capabilities, and improved 4K upscaling, as well as the ability to fine-tune models.
Building on the initial launch of Getty Images’ generative AI tools, including Generative AI by Getty Images and Generative AI by iStock, this update introduces several key features:
- Industry-leading generation speed: Image generation speeds set to reach around 6 seconds, doubling the performance of the previous model, putting it at the forefront of the industry.
- Advanced 4K generation detail: Enhanced detail and fidelity in generated images, with advanced upscaling and increased 4K generation detail.
- Expanded support and adherence for more detailed prompts: Higher level of detail prompts results in images that more closely match the descriptions provided in the text prompt.
- Longer prompts: Supports more complex and longer prompts, up to 250 words.
- Advanced camera controls: Greater control over output using shot type and depth of field.
Also Read: Talkpush Introduces Sam, the First Gen AI-Powered Voice Interviewer
As part of the update, the company is also rolling out AI modification capabilities, enabling customers to modify both generated AI images and existing pre-shot creative images. These new features include the ability to add or change individual elements, extend the canvas, or remove backgrounds in a single click. AI modification features are now available on iStock and will soon be available on Getty Images.
“We continue to push the boundaries of what’s possible with responsible AI-generated imagery,” said Grant Farhall, Chief Product Officer of Getty Images. “This updated model, and the new capabilities we are launching, will provide more opportunities for our customers to leverage AI, including alongside our amazing pre-shot content, to bring their visions to life more efficiently than before, and in a manner that is commercially safe with the legal protections Getty Images is known for.”
The updated model and ongoing rollout of additional AI functionalities are designed to benefit customers across a broad range of industries. These advancements provide professionals and enthusiasts with powerful tools to enhance their creative workflows, enabling safe and effective experimentation with AI.
The company also recently released fine-tuning capabilities, empowering enterprise customers to build their own tailored model by bringing their brand assets into Getty Images’ generative AI model which is clean of trademarks, logos and other elements protected by third-party intellectual property rights.
The model is trained solely from Getty Images’ vast creative library, including exclusive premium content, with indemnification included for commercial use. Alongside the company’s broader services, Generative AI by Getty Images and Generative AI by iStock work seamlessly with the company’s expansive library of authentic and compelling visuals and Custom Content solutions, empowering customers to elevate their entire end-to-end creative process and find the right visual content for any need.
SOURCE: GlobeNewswire
