NEW Text-to-Image AI with Unseen Photorealism - DeepFloyd IF

DeepFloyd IF, a novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding. DeepFloyd IF is a modular composed of a frozen text encoder and three cascaded pixel diffusion modules: a base model that generates 64x64 px image based on text prompt and two super-resolution models, each designed to generate images of increasing resolution: 256x256 px and 1024x1024 px. All stages of the model utilize a frozen text encoder based on the T5 transformer to extract …

architecture art deepfloyd deepfloyd if diffusion encoder extract image images language language understanding modular modules novel pixel prompt state text text-to-image text-to-image ai transformer understanding unet