The official Stable Diffusion launch announcement, with links to source code, the full model (via HuggingFace), two key research papers on the fundamentals of diffusion models, and the training dataset, which is 5.85 billion CLIP-filtered image-text pairs, 14x bigger than than the previous largest dataset.

"Stable Diffusion is a text-to-image model that will empower billions of people to create stunning art within seconds. It is a breakthrough in speed and quality meaning that it can run on consumer GPUs."

"Stable Diffusion runs on under 10 GB of VRAM on consumer GPUs, generating images at 512x512 pixels in a few seconds. This will allow both researchers and soon the public to run this under a range of conditions, democratizing image generation. We look forward to the open ecosystem that will emerge around this and further models to truly explore the boundaries of latent space."

Stable Diffusion launch announcement

#solidstatelife #ai #computervision #generativeai #diffusionmodels