Announcing Stable Diffusion 3 in early preview, our most capable text-to-image model with greatly improved performance in multi-subject prompts, image quality, and spelling abilities.
Wtf, they just released stable cascade like a week ago. All they are doing is just confusing the users and model trainers. From the blog post it’s not even clear why I would want to use this one over the other one that they just released.
As far as I understand, Stable Cascade is a pretty large architecture change from the existing Stable Diffusion models. Sable Diffusion 3 will likely be an interitive improvement with similar architecture over the existing Stage Diffusion models. The blog post for Stable Cascade does a better job explaining the difference than the Stable Diffusion 3 blog post does. Here’s a god quote from that post:
Stable Cascade differs from our Stable Diffusion lineup of models as it is built on a pipeline comprising three distinct models: Stages A, B, and C. This architecture allows for a hierarchical compression of images, achieving remarkable outputs while utilizing a highly compressed latent space.
Wtf, they just released stable cascade like a week ago. All they are doing is just confusing the users and model trainers. From the blog post it’s not even clear why I would want to use this one over the other one that they just released.
Cascade is an experiment, SD3 is their mainline model. Also this isn’t released, it’s just a preview whole they work on SD3.
to add to the other answers, stable cascade isn’t open source :(
As far as I understand, Stable Cascade is a pretty large architecture change from the existing Stable Diffusion models. Sable Diffusion 3 will likely be an interitive improvement with similar architecture over the existing Stage Diffusion models. The blog post for Stable Cascade does a better job explaining the difference than the Stable Diffusion 3 blog post does. Here’s a god quote from that post:
Hope this helps!