AI generated images

Stable Diffusion is a machine learning, text-to-image model developed by StabilityAI, in collaboration with EleutherAI and LAION, to generate digital images from natural language descriptions. The model can be used for other tasks too, like generating image-to-image translations guided by a text prompt.

SD was trained on a subset of the LAION-Aesthetics V2 dataset, using 256 Nvidia A100 GPUs !
Unlike models like DALL-E, Stable Diffusion makes its source code available. It can run on most consumer hardware equipped with a decent GPU.