We’re just beginning the AI revolution, but things are already advancing way faster than we would have ever imagined.
Stability.ai now reports that the company’s image generator is not only capable of rendering your thoughts into media but also that it can do it in real time. We don’t know what would qualify if that's not next level.
From the blog post announcing the update:
“Today, we are releasing SDXL Turbo, a new text-to-image mode. SDXL Turbo is based on a novel distillation technique called Adversarial Diffusion Distillation (ADD), which enables the model to synthesize image outputs in a single step and generate real-time text-to-image outputs while maintaining high sampling fidelity.”
While there are a range of technical advancements detailed in the post, there is also some reasoning for this from a user standpoint and that is the goal of creating a single-step image generation process.
“Featuring new advancements in diffusion model technologies, SDXL Turbo iterates on the foundation of SDXL 1.0 and implements a new distillation technique for text-to-image models: Adversarial Diffusion Distillation. By incorporating ADD, SDXL Turbo gains many advantages shared with GANs (Generative Adversarial Networks), such as single-step image outputs, while avoiding artifacts or blurriness often observed in other distillation methods.”
You can also view a video on YouTube demonstrating the new real-time image generation at this link.
This certainly raises the bar for the competition. If you’ve followed this blog, you’ll know that’s quite a crowded field. From image generation via Google’s search bar to Amazon’s effort, the AI field is spreading into every facet of our lives, including social media.
Any thoughts on real-time image generation using AI are welcome in the comments below.
Check out some of our other photography news at this link right here.