Stable Diffusion

Stable Diffusion is a text-to-image model that generates photo-realistic images given any text input.

What makes Stable Diffusion unique ?

  • It is completely open source. The model and the code that uses the model to generate the image (also known as inference code).
  • Highly accessible: It runs on a consumer grade laptop/computer. If you have a GPU (Nvidia/AMD/MAC M1/M2) with 6 GB memory, you can run it on your own hardware.
  • Vibrant community: In just a few months, we are seeing artists, AI researchers, engineers and users create and share amazing digital art, tools, libraries. It feels as if a treasure box has been unlocked in a tiny part of internet.

Text to Image examples

Photorealistic image of a cute kitten wearing a santa hat. Christmas tree in the background. hyperrealism. High definition. 4K.