Stability claims its newest Stable Diffusion models generate more 'diverse' images
AI startup Stability AI has announced its newest family of image generation models, Stable Diffusion 3.5, with several promised improvements.
Following a string of controversies stemming from technical hiccups and licensing changes, AI startup Stability AI has announced its latest family of image generation models.
While Stable Diffusion 3.5 Large and 3.5 Large Turbo are available today, 3.5 Medium won’t be released until October 29.
Stability says that the Stable Diffusion 3.5 models should generate more “diverse” outputs — that is to say, images depicting people with different skin tones and features — without the need for “extensive” prompting.
“During training, each image is captioned with multiple versions of prompts, with shorter prompts prioritized,” Hanno Basse, Stability’s chief technology officer, told TechCrunch in an interview. “This ensures a broader and more diverse distribution of image concepts for any given text description. Like most generative AI companies, we train on a wide variety of data, including filtered publicly available datasets and synthetic data.”
Article