B^ EDIT Integrations

Karlo stands as a groundbreaking model for generating images based on text prompts. It builds upon OpenAI's remarkable unCLIP architecture but takes a step further by enhancing the standard super-resolution model, allowing it to recover intricate details at a remarkable resolution of 256px, all while minimizing noise through a limited number of denoising steps. To create Karlo, we embarked on an extensive training process. We started from scratch, utilizing a vast dataset of 115 million image-text pairs, which included COYO-100M, CC3M, and CC12M. In the case of the Prior and Decoder components, we harnessed the power of ViT-L/14, a text encoder from OpenAI's CLIP repository. To optimize efficiency, we made a significant modification to the original unCLIP implementation. Instead of employing a trainable transformer in the decoder, we integrated the text encoder from ViT-L/14.