Stable Diffusion update removes ability to copy artist styles or make NSFW works

2017-08-24_00h03_35 ガジェット総合
Stable Diffusion, the AI that can generate images from text in an astonishingly realistic way, has been updated with a bunch of new features. However, many users aren't happy, complaining that the new software can no longer generate pictures in the styles of specific artists or generate NSFW artworks, The Verge has reported. Version 2 does introduce a number of new features. Key among those is a new text encoder called OpenCLIP that "greatly improves the quality of the generated images compared to earlier V1 releases," according to Stability AI, the company behind Stable Diffusion. It als