Other Modalities
Building models of more than just language.
Projects
Summary Block
This block has no content yet. Items you add to the page connected to this block will display here.
Featured
Releases
Featured
A diffusion-based model for upscaling images to higher resolution, trained by Katherine Crowson in collaboration with Stability AI.
A technique for doing text-to-image synthesis cheaply using pretrained CLIP and diffusion models.
A highly efficient text-to-image model that can be trained without captioned images.
A dataset of prompts, synthetic AI generated images, and aesthetic ratings of those images.
A technique for doing text-to-image synthesis cheaply using pretrained CLIP and VQGAN models.

