Stability AI / Stable Diffusion

This is a specific version of Stability AI’s Stable Diffusion. It’s a general‐purpose text-to-image diffusion model, allowing configuration of resolution, prompt vs negative prompt, number of inference steps, guidance scale, etc. The default image size is 768×768 (or other dimensions that are multiples of 64). It’s suitable for a broad range of visual generation tasks: illustrations, concept art, creative art, etc.