Stability AI has introduced the early preview of Stable Diffusion 3, a new text-to-image model, to render images from textual prompts.
The model ranges from 800M to 8B parameters and combines a diffusion transformer architecture and flow matching. Additionally, the model can depict multi-subject prompts, create images, and correct spelling.
The company claims that this early preview offers improved model performance and safety by gathering insights before releasing the model.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.