Applications

Text-to-Image

Generating original images from a written description, as tools like DALL-E, Midjourney, and Stable Diffusion do.

Text-to-image models turn a prompt into a new picture, having learned the link between language and visuals from huge sets of captioned images. Most leading systems are diffusion models, which sculpt an image out of noise guided by the text. The technology made generative AI visually famous and raised fresh questions about art, copyright, and authenticity.

Reference: Wikipedia: Text-to-Image