Stability AI debuts next-gen photorealistic image generation model
Generative artificial intelligence company Stability AI Ltd. today released an updated version of its popular open-source photorealistic image generation model.
London-based Stability AI is the developer of Stable Diffusion, an AI model that can automatically generate realistic-looking images based on text prompts. It’s not the only AI model with that capability, but what differentiates it is that it’s available under an open-source license and can run on relatively simple hardware. These two features have helped it quickly amass a large user base.
The latest model is called Stable Diffusion XL, and it’s the latest addition to the Stable Diffusion suite. It’s being made available through an application programming interface and caters to enterprise developers. Using SDXL, developers will be able to create more detailed imagery. The company says it represents a key step forward in its image generation models.
SDXL is said to bring next-level photorealism capabilities to AI image generation, with enhanced functionality around image composition and face generation. Moreover, developers can now make use of much simpler prompts to create descriptive images, Stability AI said.
Another benefit is that SDXL goes beyond text-to-image prompting. Now, developers can also use it to create images with image-to-image prompting, meaning they can input one image and generate numerous variations of that picture. There’s also a new inpainting feature that allows users to reconstruct the missing parts of an image, and an outpainting feature that makes it possible to extend existing images.
The company said SDXL now powers the most recent version of its premium consumer imaging application, called DreamStudio, and is also the engine behind applications like NightCafe Studio.
“SDXL brings a richness to image generation that is transformative across several industries, including graphic design and architecture, with results taking place in front of our eyes,” said Stability AI Chief Technology Officer Tom Mason.
Holger Mueller of Constellation Research Inc. said that with all the recent buzz around generative AI and chat programs, it’s easy to forget that its implications for picture generation are just as huge. “The latest release of Stability AI’s Stable Diffusion shows us that generative AI-based image generation is becoming faster and bigger, with higher resolution and more creativity,” Mueller said. “Advances like this will quickly change the future of work for creatives working on visual content.”
With all the recent hoopla on LLMs, it is easy to forget the picture generation see change created by generative AI. And that area does not stand still as one can see the latest release of Stability AI’s Stable Diffusion XL… and it is all about being faster and bigger – more resolution, faster generation and the ability to generate better text. The combination of these will quicky change the future of work for creatives working on pictures, graphics and other visuals.
In the coming days, Stability AI plans to follow up with the open-source release of SDXL, which is currently available in beta testing. Like all of Stability AI’s open-source models, SDXL will be optimized for accessibility, making it available to as many users as possible.
Mason recently appeared on SiliconANGLE Media’s video studio theCUBE during the AWS Startup Showcase: “Top Startups Building Generative AI on AWS” event. He discussed how the startup is leveraging Amazon Web Services Inc.’s cloud infrastructure to power its Stable Diffusion models:
Images: Stability AI
A message from John Furrier, co-founder of SiliconANGLE:
Your vote of support is important to us and it helps us keep the content FREE.
One-click below supports our mission to provide free, deep and relevant content.
Join our community on YouTube
Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger and many more luminaries and experts.