Stability AI has unveiled its latest family of image generation models: Stable Diffusion 3.5. According to the company, it includes three variants – Large, Large Turbo and Medium – that are said to be characterized by improved adaptability and versatility. The Large variant with 8 billion parameters is available immediately, while the Medium model is scheduled for release on October 29.
The company says the new models can produce more diverse results, including representations of people with different skin colors and features. Stability AI also touts the models’ ability to produce different art styles, such as 3D art, photography, and painting. The Large Turbo variant is said to be particularly fast.
According to Stability AI, the use of the models is free for non-commercial purposes and for companies with an annual turnover of less than $1 million. Licenses are required for larger companies. The company emphasizes that it is taking measures to prevent misuse of the technology, but does not provide specific details.
Sources: TechCrunch, Stability AI