Home Creators Posts Import Register Favorites Logout
haven't archived this post yet. have a subscription? use the importer!

Content

Yesterday, they released the new version of Stable Diffusion, a theoretically much more powerful model that will allow for more coherent generations. However, they have removed most of the artists and any trace of NSFW from the training data, so it is not very useful at the moment. A real disappointment.

--

Ayer lanzaron la nueva versión de Stable Diffusion, un modelo teóricamente mucho mas potente que permitirá generaciones mas coherentes. Sin embargo han retirado del training data la mayoría de los artistas y cualquier rastro de NSFW, por lo que ahora mismo no sirve de mucho. Una auténtica decepción.

Files

Previews only

Comments