{"id":140079,"date":"2022-11-26T16:40:35","date_gmt":"2022-11-26T16:40:35","guid":{"rendered":"https:\/\/harchi90.com\/stable-diffusion-update-removes-ability-to-copy-artist-styles-or-make-nsfw-works\/"},"modified":"2022-11-26T16:40:35","modified_gmt":"2022-11-26T16:40:35","slug":"stable-diffusion-update-removes-ability-to-copy-artist-styles-or-make-nsfw-works","status":"publish","type":"post","link":"https:\/\/harchi90.com\/stable-diffusion-update-removes-ability-to-copy-artist-styles-or-make-nsfw-works\/","title":{"rendered":"Stable Diffusion update removes ability to copy artist styles or make NSFW works"},"content":{"rendered":"
Stable Diffusion, the AI \u200b\u200bthat 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<\/em> has reported. <\/p>\n 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 also includes a new NSFW filter from LAION designed to remove adult content.<\/p>\n <\/p>\n Other features include a depth-to-image diffusion model that allows one to create transformations “that look radically different from the original but still preserve the coherence and depth from an image,” according to Stability AI. In other words, if you create a new version of an image, objects will still correctly appear in front of or behind other objects. Finally, a text-guided inpainting model makes it easy to switch out parts of an image, keeping a cat’s face while changing out its body, for example. <\/p>\n