Remmy

joined 1 year ago
[–] Remmy@artemis.camp 17 points 1 year ago

Coming from the guy who never voted until he was 30. Who has never had any experience in politics at all...

[–] Remmy@artemis.camp 62 points 1 year ago (2 children)

What year is it? I haven't heard anyone talk about web portals since 1996...

[–] Remmy@artemis.camp 2 points 1 year ago

Image to image software isn't going to return an image of you unless you create Lora, Lycoris or Textual Inversion of your face for it to work with. It doesn't "know" what you look like. For things like this, it "looks" at the image based on shapes and colors alone and generates a face that fits those general dimensions. For AI, the word professional would simply mean the picture was taken in a studio.

She used Playground.ai which uses stable diffusion models. I'm not familiar with their interface, but definitely relies on a good prompt for the model to give you good results. Asking it to do something isn't how diffusion models work. They weight keywords and infer based on those.