A text-to-image diffusion model capable of generating photo-realistic images
About Stable Diffusion
Stable Diffusion is a deep learning, text-to-image model released in 2022 by Stability.ai. It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt.
Stable Diffusion uses MiDaS for monocular depth estimation in their Depth2Image feature. MiDAS is a state-of-the-art model created by Intel and ETH Zurich researchers that can infer depth using a single 2D photo as an input.