Stable Diffusion uses a variational autoencoder (VAE) to generate detailed images from a caption with only a few words. Unlike prior autoencoder-based diffusion models, Stable Diffusion incorporates a ...

This is because Stable Diffusion, like many other AI applications, is optimised for Nvidia’s CUDA interface, which performs floating point calculations on the graphics card’s shaders.

Stability AI Stable Audio The architecture of Stable Audio consists of a variational autoencoder (VAE), a text encoder, and a U-Net-based conditioned diffusion model. The VAE plays a crucial role ...

Stability AI’s new Stable Audio platform comprises not one but three neural networks. Its core component is U-Net, a latent diffusion model with 907 million parameters.

Stable Diffusion doesn’t generate direct copies like this very often. Researchers tried to reproduce 350,000 images from Stable Diffusion’s training set but only succeeded with 109 of them—a ...

Cute AI critters generated by the author using Stable Diffusion on his PC. For comparison's sake, a GeForce RTX 2060 card can draw as much as 200 watts to do the same task in only about half the time.

Stability AI has released Stable Diffusion 3.5 Large, its most powerful text-to-image generation model to date, and Stable Diffusion 3.5 Large Turbo, with special emphasis on customizability, efficien ...

You can run Stable Diffusion locally yourself if you follow a series of somewhat arcane steps. For the past two weeks, we've been running it on a Windows PC with an Nvidia RTX 3060 12GB GPU. It ...

The latest update to Stable Diffusion also includes an adult content filter limiting the generation of NSFW images. Text-to-image example from Stable Diffusion 2.0. Photo: Stability AI Github.

Stable Diffusion is a powerful tool, but it needs quite a powerful PC to run it well. Here's what you need to get up and running with this exciting AI.