The Stable Diffusion framework trains a Latent Diffusion Model on 512×512 photographs from a subset of the LAION-5B database. It makes use of a frozen CLIP ViT-L/14 text encoder to condition the model on textual…
The Stable Diffusion framework trains a Latent Diffusion Model on 512×512 photographs from a subset of the LAION-5B database. It makes use of a frozen CLIP ViT-L/14 text encoder to condition the model on textual…