alt Hacker NewsCensorship on image generation models works on another level. The models can generate NSFW, but there are extra computer vision models checking if the images can be shown to the users. It's especially obvious for Grok and ChatGPT.
Censorship on image generation models works on another level. The models can generate NSFW, but there are extra computer vision models checking if the images can be shown to the users. It's especially obvious for Grok and ChatGPT.
There are image models with censorship at every stage from pretraining to posttraining.
Most recently Ideogram released an open weight model that will denoise into a grey image with the text "Blocked by safety filter" notice for certain prompts
Of course, because it's open weights people have found defeats