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, the startup that makes the popular AI art tool Stable Diffusion, faces two lawsuits. They allege the company infringes on copyrights by scraping the web to train its art algorithms ...

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 ...

A smaller model like Stable Diffusion simply does not have the same amount of storage space to store most of that training data. That could very much change in the next few years.

Stable Diffusion is developed by startup Stability AI and is one of the most popular generative AI models for image creation in use today, often competing against OpenAI’s DALL-E.

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 ...

Paper: Stable Diffusion “memorizes” some images, sparking privacy concerns But out of 300,000 high-probability images tested, researchers found a 0.03% memorization rate.