WikiVisually
Infinite photos and videos for every Wiki article · Find something interesting to watch in seconds
Animals Celebrities British Monarchs Tallest Buildings Crown Jewels Countries of the World Kings of France Richest US Counties Largest Palaces Famous Castles Great Museums Ancient Marvels Great Cities History by Country Best Campuses Presidents Wonders of Nature Great Artists World Banknotes Supercars Rare Coins Wars and Battles Sports Recovered Treasures Largest Empires Orders and Medals
more top lists
History
Stable Diffusion
Videos
Page
Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. It is considered to be a part of the ongoing artifical intelligence boom.
An image generated with Stable Diffusion based on the text prompt "a photograph of an astronaut riding a horse"
An image generated with Stable Diffusion based on the text prompt "a photograph of an astronaut riding a horse"
Image: Night City Sphere (SD1.5)
Image: Night City Sphere (SD1.5)
Image: Night City Sphere (SDXL)
Image: Night City Sphere (SDXL)
Text-to-image model
Videos
Page
A text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description.
Examples of images and captions from three public datasets which are commonly used to train text-to-image models
Examples of images and captions from three public datasets which are commonly used to train text-to-image models