Welcome to CompVis!

We host public weights for Latent Diffusion and Stable Diffusion models. There are several options to choose from, please check the details below.

Stable Diffusion Models

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion works, please have a look at 🤗's Stable Diffusion with 🧨 Diffusers blog.

We recommend you use Stable Diffusion with 🤗 Diffusers library. You can also use the original CompVis code. There are variants of the weights depending on:

• The library they are intended for.
• The training regime. There are 4 training versions: v1-1 through v1-4 . Each one was created from the checkpoint of the previous version, and was trained for additional steps in specific variants of the dataset.

  Please, refer to the details in the following table to choose the weights appropriate for your use.

  Model	Library	Details
  stable-diffusion-v1-1	🤗 Diffusers	237k steps at resolution 256x256 on laion2B-en. 194k steps at resolution 512x512 on laion-high-resolution.
  stable-diffusion-v1-2	🤗 Diffusers	v1-1 plus: 515k steps at 512x512 on "laion-improved-aesthetics".
  stable-diffusion-v1-3	🤗 Diffusers	v1-2 plus: 195k steps at 512x512 on "laion-improved-aesthetics", with 10% dropping of text-conditioning.
  stable-diffusion-v1-4	🤗 Diffusers	v1-2 plus: 225k steps at 512x512 on "laion-aesthetics v2 5+", with 10% dropping of text conditioning.
  stable-diffusion-v-1-1-original	CompVis	237k steps at resolution 256x256 on laion2B-en. 194k steps at resolution 512x512 on laion-high-resolution.
  stable-diffusion-v-1-2-original	CompVis	v1-1 plus: 515k steps at 512x512 on "laion-improved-aesthetics".
  stable-diffusion-v-1-3-original	CompVis	v1-2 plus: 195k steps at 512x512 on "laion-improved-aesthetics", with 10% dropping of text-conditioning.
  stable-diffusion-v-1-4-original	CompVis	v1-2 plus: 225k steps at 512x512 on "laion-aesthetics v2 5+", with 10% dropping of text conditioning.